We report on the interfacial electronic properties of HfO2 gate dielectrics both, with GaN towards normally-OFF recessed HEMT architectures and the AlGaN barrier for normally-ON AlGaN/GaN MISHEMTs for GaN device platforms on Si. A conduction band offset of 1.9 eV is extracted for HfO2/GaN along with a very low density of fixed bulk and interfacial charges. Conductance measurements on HfO2/GaN MOSCAPs reveal an interface trap state continuum with a density of 9.37x1012 eV-1cm-2 centered at 0.48 eV below EC. The forward and reverse current densities are shown to be governed by Fowler-Nordheim tunneling and Poole-Frenkel emission respectively. Normally-ON HfO2/AlGaN/GaN MISHEMTs exhibit negligible shifts in threshold voltage, transconductances of 110mS/mm for 3 {\mu}m gate length devices, and three-terminal OFF-state gate leakage currents of 20 nA/mm at a VD of 100 V. Dynamic capacitance dispersion measurements show two peaks at the AlGaN/GaN interface corresponding to slow and fast interface traps with a peak Dit of 5.5x1013 eV-1cm-2 and 1.5x1013 eV-1cm-2 at trap levels 0.55 eV and 0.46 eV below EC respectively. The HfO2/AlGaN interface exhibits a peak Dit of 4.4x1013 eV-1cm- 2 at 0.45 eV below EC.
https://arxiv.org/abs/1708.03811
In the coming years, it is likely that the first potentially Earth-like planets will be discovered orbiting other stars. Once found, the characterisation of those planets will play a vital role in determining which will be chosen as the first targets for the search for life beyond the Solar System. We must thus be able to gauge the relative importance of the various factors proposed to influence potential planetary habitability, in order to best focus that search. One of the plethora of factors to be considered in that process is the climatic variability of the exo-Earths in question. In the Solar System, the Earth’s long-term climate is driven by several factors, including the modifying influence of life on our atmosphere, and the temporal evolution of solar luminosity. The gravitational influence of the other planets in the Solar System adds an extra complication, driving the Milankovitch cycles that are thought to have caused the on-going series of glacial and interglacial periods that have dominated Earth’s climate for the past few million years. Here we present preliminary results of three suites of integrations that together examine the influence of Solar System architecture on the Earth’s Milankovitch cycles. We consider separately the influence of the planets Jupiter, Mars and Venus, each of which contributes to the forcing of Earth’s orbital evolution. Our results illustrate how small changes to the architecture of a given planetary system can result in marked changes in the potential habitability of the planets therein, and are an important first step in developing a means by which the nature of climate variability on planets beyond our Solar System can be characterised.
https://arxiv.org/abs/1708.03448
Despite the substantial progress in recent years, the image captioning techniques are still far from being perfect.Sentences produced by existing methods, e.g. those based on RNNs, are often overly rigid and lacking in variability. This issue is related to a learning principle widely used in practice, that is, to maximize the likelihood of training samples. This principle encourages high resemblance to the “ground-truth” captions while suppressing other reasonable descriptions. Conventional evaluation metrics, e.g. BLEU and METEOR, also favor such restrictive methods. In this paper, we explore an alternative approach, with the aim to improve the naturalness and diversity – two essential properties of human expression. Specifically, we propose a new framework based on Conditional Generative Adversarial Networks (CGAN), which jointly learns a generator to produce descriptions conditioned on images and an evaluator to assess how well a description fits the visual content. It is noteworthy that training a sequence generator is nontrivial. We overcome the difficulty by Policy Gradient, a strategy stemming from Reinforcement Learning, which allows the generator to receive early feedback along the way. We tested our method on two large datasets, where it performed competitively against real people in our user study and outperformed other methods on various tasks.
https://arxiv.org/abs/1703.06029
In this paper, we introduce a hybrid search for attention-based neural machine translation (NMT). A target phrase learned with statistical MT models extends a hypothesis in the NMT beam search when the attention of the NMT model focuses on the source words translated by this phrase. Phrases added in this way are scored with the NMT model, but also with SMT features including phrase-level translation probabilities and a target language model. Experimental results on German->English news domain and English->Russian e-commerce domain translation tasks show that using phrase-based models in NMT search improves MT quality by up to 2.3% BLEU absolute as compared to a strong NMT baseline.
https://arxiv.org/abs/1708.03271
In this work we formulate the problem of image captioning as a multimodal translation task. Analogous to machine translation, we present a sequence-to-sequence recurrent neural networks (RNN) model for image caption generation. Different from most existing work where the whole image is represented by convolutional neural network (CNN) feature, we propose to represent the input image as a sequence of detected objects which feeds as the source sequence of the RNN model. In this way, the sequential representation of an image can be naturally translated to a sequence of words, as the target sequence of the RNN model. To represent the image in a sequential way, we extract the objects features in the image and arrange them in a order using convolutional neural networks. To further leverage the visual information from the encoded objects, a sequential attention layer is introduced to selectively attend to the objects that are related to generate corresponding words in the sentences. Extensive experiments are conducted to validate the proposed approach on popular benchmark dataset, i.e., MS COCO, and the proposed model surpasses the state-of-the-art methods in all metrics following the dataset splits of previous work. The proposed approach is also evaluated by the evaluation server of MS COCO captioning challenge, and achieves very competitive results, e.g., a CIDEr of 1.029 (c5) and 1.064 (c40).
https://arxiv.org/abs/1702.05658
Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both visual content of images and textual content of questions. To support the VQA task, we need to find good solutions for the following three issues: 1) fine-grained feature representations for both the image and the question; 2) multi-modal feature fusion that is able to capture the complex interactions between multi-modal features; 3) automatic answer prediction that is able to consider the complex correlations between multiple diverse answers for the same question. For fine-grained image and question representations, a `co-attention’ mechanism is developed by using a deep neural network architecture to jointly learn the attentions for both the image and the question, which can allow us to reduce the irrelevant features effectively and obtain more discriminative features for image and question representations. For multi-modal feature fusion, a generalized Multi-modal Factorized High-order pooling approach (MFH) is developed to achieve more effective fusion of multi-modal features by exploiting their correlations sufficiently, which can further result in superior VQA performance as compared with the state-of-the-art approaches. For answer prediction, the KL (Kullback-Leibler) divergence is used as the loss function to achieve more accurate characterization of the complex correlations between multiple diverse answers with same or similar meaning, which can allow us to achieve faster convergence rate and obtain slightly better accuracy on answer prediction. A deep neural network architecture is designed to integrate all these aforementioned modules into one unified model for achieving superior VQA performance. With an ensemble of 9 models, we achieve the state-of-the-art performance on the large-scale VQA datasets and win the runner-up in the VQA Challenge 2017.
https://arxiv.org/abs/1708.03619
We address the mechanism of early stages of growth and shape transition of the unique nanowall network (NwN) nanostructure of GaN by experimentally monitoring its controlled growth using PA-MBE and complementing it by \textit{first-principles} calculations. Using electron microscopy, we observe the formation of tetrahedron shaped (3 faced pyramid) islands at early stages of growth, which later grows anisotropically along their edges of the (20$\overline{2}$1) facets, to form the wall like structure. The mechanism of this crystal growth is discussed in light of surface free energies of the different surfaces, adsorption energy and diffusion barrier of Ga ad-atoms on the (20$\overline{2}$1) facets. By \textit{first-principles} calculations, we find that the diffusion barrier of ad-atoms decreases with decreasing width of facets, and is responsible for the anisotropic growth and formation of the nanowall network. This study suggest that formation of NwN is a archetype example of structure dependent attachment kinetic (SDAK) instability induced shape transition in thin film growth.
https://arxiv.org/abs/1708.03094
It is a well-known fact that adding noise to the input data often improves network performance. While the dropout technique may be a cause of memory loss, when it is applied to recurrent connections, Tikhonov regularization, which can be regarded as the training with additive noise, avoids this issue naturally, though it implies regularizer derivation for different architectures. In case of feedforward neural networks this is straightforward, while for networks with recurrent connections and complicated layers it leads to some difficulties. In this paper, a Tikhonov regularizer is derived for Long-Short Term Memory (LSTM) networks. Although it is independent of time for simplicity, it considers interaction between weights of the LSTM unit, which in theory makes it possible to regularize the unit with complicated dependences by using only one parameter that measures the input data perturbation. The regularizer that is proposed in this paper has three parameters: one to control the regularization process, and other two to maintain computation stability while the network is being trained. The theory developed in this paper can be applied to get such regularizers for different recurrent neural networks with Hadamard products and Lipschitz continuous functions.
https://arxiv.org/abs/1708.02979
For large-scale visual search, highly compressed yet meaningful representations of images are essential. Structured vector quantizers based on product quantization and its variants are usually employed to achieve such compression while minimizing the loss of accuracy. Yet, unlike binary hashing schemes, these unsupervised methods have not yet benefited from the supervision, end-to-end learning and novel architectures ushered in by the deep learning revolution. We hence propose herein a novel method to make deep convolutional neural networks produce supervised, compact, structured binary codes for visual search. Our method makes use of a novel block-softmax non-linearity and of batch-based entropy losses that together induce structure in the learned encodings. We show that our method outperforms state-of-the-art compact representations based on deep hashing or structured quantization in single and cross-domain category retrieval, instance retrieval and classification. We make our code and models publicly available online.
https://arxiv.org/abs/1708.02932
The region-based Convolutional Neural Network (CNN) detectors such as Faster R-CNN or R-FCN have already shown promising results for object detection by combining the region proposal subnetwork and the classification subnetwork together. Although R-FCN has achieved higher detection speed while keeping the detection performance, the global structure information is ignored by the position-sensitive score maps. To fully explore the local and global properties, in this paper, we propose a novel fully convolutional network, named as CoupleNet, to couple the global structure with local parts for object detection. Specifically, the object proposals obtained by the Region Proposal Network (RPN) are fed into the the coupling module which consists of two branches. One branch adopts the position-sensitive RoI (PSRoI) pooling to capture the local part information of the object, while the other employs the RoI pooling to encode the global and context information. Next, we design different coupling strategies and normalization ways to make full use of the complementary advantages between the global and local branches. Extensive experiments demonstrate the effectiveness of our approach. We achieve state-of-the-art results on all three challenging datasets, i.e. a mAP of 82.7% on VOC07, 80.4% on VOC12, and 34.4% on COCO. Codes will be made publicly available.
https://arxiv.org/abs/1708.02863
The ability to ask questions is a powerful tool to gather information in order to learn about the world and resolve ambiguities. In this paper, we explore a novel problem of generating discriminative questions to help disambiguate visual instances. Our work can be seen as a complement and new extension to the rich research studies on image captioning and question answering. We introduce the first large-scale dataset with over 10,000 carefully annotated images-question tuples to facilitate benchmarking. In particular, each tuple consists of a pair of images and 4.6 discriminative questions (as positive samples) and 5.9 non-discriminative questions (as negative samples) on average. In addition, we present an effective method for visual discriminative question generation. The method can be trained in a weakly supervised manner without discriminative images-question tuples but just existing visual question answering datasets. Promising results are shown against representative baselines through quantitative evaluations and user studies.
https://arxiv.org/abs/1708.02760
This paper presents a state-of-the-art model for visual question answering (VQA), which won the first place in the 2017 VQA Challenge. VQA is a task of significant importance for research in artificial intelligence, given its multimodal nature, clear evaluation protocol, and potential real-world applications. The performance of deep neural networks for VQA is very dependent on choices of architectures and hyperparameters. To help further research in the area, we describe in detail our high-performing, though relatively simple model. Through a massive exploration of architectures and hyperparameters representing more than 3,000 GPU-hours, we identified tips and tricks that lead to its success, namely: sigmoid outputs, soft training targets, image features from bottom-up attention, gated tanh activations, output embeddings initialized using GloVe and Google Images, large mini-batches, and smart shuffling of training data. We provide a detailed analysis of their impact on performance to assist others in making an appropriate selection.
https://arxiv.org/abs/1708.02711
This paper presents a framework for localization or grounding of phrases in images using a large collection of linguistic and visual cues. We model the appearance, size, and position of entity bounding boxes, adjectives that contain attribute information, and spatial relationships between pairs of entities connected by verbs or prepositions. Special attention is given to relationships between people and clothing or body part mentions, as they are useful for distinguishing individuals. We automatically learn weights for combining these cues and at test time, perform joint inference over all phrases in a caption. The resulting system produces state of the art performance on phrase localization on the Flickr30k Entities dataset and visual relationship detection on the Stanford VRD dataset.
https://arxiv.org/abs/1611.06641
Recent advances in computer vision-in the form of deep neural networks-have made it possible to query increasing volumes of video data with high accuracy. However, neural network inference is computationally expensive at scale: applying a state-of-the-art object detector in real time (i.e., 30+ frames per second) to a single video requires a $4000 GPU. In response, we present NoScope, a system for querying videos that can reduce the cost of neural network video analysis by up to three orders of magnitude via inference-optimized model search. Given a target video, object to detect, and reference neural network, NoScope automatically searches for and trains a sequence, or cascade, of models that preserves the accuracy of the reference network but is specialized to the target video and are therefore far less computationally expensive. NoScope cascades two types of models: specialized models that forego the full generality of the reference model but faithfully mimic its behavior for the target video and object; and difference detectors that highlight temporal differences across frames. We show that the optimal cascade architecture differs across videos and objects, so NoScope uses an efficient cost-based optimizer to search across models and cascades. With this approach, NoScope achieves two to three order of magnitude speed-ups (265-15,500x real-time) on binary classification tasks over fixed-angle webcam and surveillance video while maintaining accuracy within 1-5% of state-of-the-art neural networks.
https://arxiv.org/abs/1703.02529
We present a framework for specifying, training, evaluating, and deploying machine learning models. Our focus is on simplifying cutting edge machine learning for practitioners in order to bring such technologies into production. Recognizing the fast evolution of the field of deep learning, we make no attempt to capture the design space of all possible model architectures in a domain- specific language (DSL) or similar configuration language. We allow users to write code to define their models, but provide abstractions that guide develop- ers to write models in ways conducive to productionization. We also provide a unifying Estimator interface, making it possible to write downstream infrastructure (e.g. distributed training, hyperparameter tuning) independent of the model implementation. We balance the competing demands for flexibility and simplicity by offering APIs at different levels of abstraction, making common model architectures available out of the box, while providing a library of utilities designed to speed up experimentation with model architectures. To make out of the box models flexible and usable across a wide range of problems, these canned Estimators are parameterized not only over traditional hyperparameters, but also using feature columns, a declarative specification describing how to interpret input data. We discuss our experience in using this framework in re- search and production environments, and show the impact on code health, maintainability, and development speed.
https://arxiv.org/abs/1708.02637
Non-maximum suppression is an integral part of the object detection pipeline. First, it sorts all detection boxes on the basis of their scores. The detection box M with the maximum score is selected and all other detection boxes with a significant overlap (using a pre-defined threshold) with M are suppressed. This process is recursively applied on the remaining boxes. As per the design of the algorithm, if an object lies within the predefined overlap threshold, it leads to a miss. To this end, we propose Soft-NMS, an algorithm which decays the detection scores of all other objects as a continuous function of their overlap with M. Hence, no object is eliminated in this process. Soft-NMS obtains consistent improvements for the coco-style mAP metric on standard datasets like PASCAL VOC 2007 (1.7% for both R-FCN and Faster-RCNN) and MS-COCO (1.3% for R-FCN and 1.1% for Faster-RCNN) by just changing the NMS algorithm without any additional hyper-parameters. Using Deformable-RFCN, Soft-NMS improves state-of-the-art in object detection from 39.8% to 40.9% with a single model. Further, the computational complexity of Soft-NMS is the same as traditional NMS and hence it can be efficiently implemented. Since Soft-NMS does not require any extra training and is simple to implement, it can be easily integrated into any object detection pipeline. Code for Soft-NMS is publicly available on GitHub (this http URL).
https://arxiv.org/abs/1704.04503
Video captioning, the task of describing the content of a video, has seen some promising improvements in recent years with sequence-to-sequence models, but accurately learning the temporal and logical dynamics involved in the task still remains a challenge, especially given the lack of sufficient annotated data. We improve video captioning by sharing knowledge with two related directed-generation tasks: a temporally-directed unsupervised video prediction task to learn richer context-aware video encoder representations, and a logically-directed language entailment generation task to learn better video-entailed caption decoder representations. For this, we present a many-to-many multi-task learning model that shares parameters across the encoders and decoders of the three tasks. We achieve significant improvements and the new state-of-the-art on several standard video captioning datasets using diverse automatic and human evaluations. We also show mutual multi-task improvements on the entailment generation task.
https://arxiv.org/abs/1704.07489
Cross-modal hashing is usually regarded as an effective technique for large-scale textual-visual cross retrieval, where data from different modalities are mapped into a shared Hamming space for matching. Most of the traditional textual-visual binary encoding methods only consider holistic image representations and fail to model descriptive sentences. This renders existing methods inappropriate to handle the rich semantics of informative cross-modal data for quality textual-visual search tasks. To address the problem of hashing cross-modal data with semantic-rich cues, in this paper, a novel integrated deep architecture is developed to effectively encode the detailed semantics of informative images and long descriptive sentences, named as Textual-Visual Deep Binaries (TVDB). In particular, region-based convolutional networks with long short-term memory units are introduced to fully explore image regional details while semantic cues of sentences are modeled by a text convolutional network. Additionally, we propose a stochastic batch-wise training routine, where high-quality binary codes and deep encoding functions are efficiently optimized in an alternating manner. Experiments are conducted on three multimedia datasets, i.e. Microsoft COCO, IAPR TC-12, and INRIA Web Queries, where the proposed TVDB model significantly outperforms state-of-the-art binary coding methods in the task of cross-modal retrieval.
https://arxiv.org/abs/1708.02531
In this paper, we study band-to-band and intersubband characteristics of GaN/AlN heterostructures (planar and nanowires) structurally designed to absorb in the short-wavelength infrared region, particularly at 1.55 microns. We compare the effect of doping the GaN sections with Si and Ge, and we discuss the variation of free-carrier screening with the doping density and well/nanodisk size. We observe that nanowire heterostructures consistently present longer photoluminescence decay times than their planar counterparts, which supports the existence of an in-plane piezoelectric field associated to the shear component of the strain tensor, leading to lateral electron-hole separation. We report intersubband absorption covering 1.45 microns to 1.75 microns using Ge-doped quantum wells, with comparable performance to well-studied Si-doped planar heterostructures. We also report comparable intersubband absorption in Si- and Ge-doped nanowire heterostructures indicating that the choice of dopant is not an intrinsic barrier for observing intersubband phenomena. In addition, we calculate the spectral shift of the intersubband absorption due to many body effects as a function of the doping concentration.
https://arxiv.org/abs/1705.04096
Video reviews are the natural evolution of written product reviews. In this paper we target this phenomenon and introduce the first dataset created from closed captions of YouTube product review videos as well as a new attention-RNN model for aspect extraction and joint aspect extraction and sentiment classification. Our model provides state-of-the-art performance on aspect extraction without requiring the usage of hand-crafted features on the SemEval ABSA corpus, while it outperforms the baseline on the joint task. In our dataset, the attention-RNN model outperforms the baseline for both tasks, but we observe important performance drops for all models in comparison to SemEval. These results, as well as further experiments on domain adaptation for aspect extraction, suggest that differences between speech and written text, which have been discussed extensively in the literature, also extend to the domain of product reviews, where they are relevant for fine-grained opinion mining.
https://arxiv.org/abs/1708.02420
Visual Question Answering (VQA) has attracted a lot of attention in both Computer Vision and Natural Language Processing communities, not least because it offers insight into the relationships between two important sources of information. Current datasets, and the models built upon them, have focused on questions which are answerable by direct analysis of the question and image alone. The set of such questions that require no external information to answer is interesting, but very limited. It excludes questions which require common sense, or basic factual knowledge to answer, for example. Here we introduce FVQA, a VQA dataset which requires, and supports, much deeper reasoning. FVQA only contains questions which require external information to answer. We thus extend a conventional visual question answering dataset, which contains image-question-answerg triplets, through additional image-question-answer-supporting fact tuples. The supporting fact is represented as a structural triplet, such as <Cat,CapableOf,ClimbingTrees>. We evaluate several baseline models on the FVQA dataset, and describe a novel model which is capable of reasoning about an image on the basis of supporting facts.
https://arxiv.org/abs/1606.05433
Knowledge distillation describes a method for training a student network to perform better by learning from a stronger teacher network. Translating a sentence with an Neural Machine Translation (NMT) engine is time expensive and having a smaller model speeds up this process. We demonstrate how to transfer the translation quality of an ensemble and an oracle BLEU teacher network into a single NMT system. Further, we present translation improvements from a teacher network that has the same architecture and dimensions of the student network. As the training of the student model is still expensive, we introduce a data filtering method based on the knowledge of the teacher model that not only speeds up the training, but also leads to better translation quality. Our techniques need no code change and can be easily reproduced with any NMT architecture to speed up the decoding process.
https://arxiv.org/abs/1702.01802
Dense captioning is a newly emerging computer vision topic for understanding images with dense language descriptions. The goal is to densely detect visual concepts (e.g., objects, object parts, and interactions between them) from images, labeling each with a short descriptive phrase. We identify two key challenges of dense captioning that need to be properly addressed when tackling the problem. First, dense visual concept annotations in each image are associated with highly overlapping target regions, making accurate localization of each visual concept challenging. Second, the large amount of visual concepts makes it hard to recognize each of them by appearance alone. We propose a new model pipeline based on two novel ideas, joint inference and context fusion, to alleviate these two challenges. We design our model architecture in a methodical manner and thoroughly evaluate the variations in architecture. Our final model, compact and efficient, achieves state-of-the-art accuracy on Visual Genome for dense captioning with a relative gain of 73\% compared to the previous best algorithm. Qualitative experiments also reveal the semantic capabilities of our model in dense captioning.
https://arxiv.org/abs/1611.06949
Sequence-to-sequence models have shown promising improvements on the temporal task of video captioning, but they optimize word-level cross-entropy loss during training. First, using policy gradient and mixed-loss methods for reinforcement learning, we directly optimize sentence-level task-based metrics (as rewards), achieving significant improvements over the baseline, based on both automatic metrics and human evaluation on multiple datasets. Next, we propose a novel entailment-enhanced reward (CIDEnt) that corrects phrase-matching based metrics (such as CIDEr) to only allow for logically-implied partial matches and avoid contradictions, achieving further significant improvements over the CIDEr-reward model. Overall, our CIDEnt-reward model achieves the new state-of-the-art on the MSR-VTT dataset.
https://arxiv.org/abs/1708.02300
Recently, very deep convolutional neural networks (CNNs) have been attracting considerable attention in image restoration. However, as the depth grows, the long-term dependency problem is rarely realized for these very deep models, which results in the prior states/layers having little influence on the subsequent ones. Motivated by the fact that human thoughts have persistency, we propose a very deep persistent memory network (MemNet) that introduces a memory block, consisting of a recursive unit and a gate unit, to explicitly mine persistent memory through an adaptive learning process. The recursive unit learns multi-level representations of the current state under different receptive fields. The representations and the outputs from the previous memory blocks are concatenated and sent to the gate unit, which adaptively controls how much of the previous states should be reserved, and decides how much of the current state should be stored. We apply MemNet to three image restoration tasks, i.e., image denosing, super-resolution and JPEG deblocking. Comprehensive experiments demonstrate the necessity of the MemNet and its unanimous superiority on all three tasks over the state of the arts. Code is available at this https URL.
https://arxiv.org/abs/1708.02209
Intrinsically motivated spontaneous exploration is a key enabler of autonomous lifelong learning in human children. It allows them to discover and acquire large repertoires of skills through self-generation, self-selection, self-ordering and self-experimentation of learning goals. We present the unsupervised multi-goal reinforcement learning formal framework as well as an algorithmic approach called intrinsically motivated goal exploration processes (IMGEP) to enable similar properties of autonomous learning in machines. The IMGEP algorithmic architecture relies on several principles: 1) self-generation of goals as parameterized reinforcement learning problems; 2) selection of goals based on intrinsic rewards; 3) exploration with parameterized time-bounded policies and fast incremental goal-parameterized policy search; 4) systematic reuse of information acquired when targeting a goal for improving other goals. We present a particularly efficient form of IMGEP that uses a modular representation of goal spaces as well as intrinsic rewards based on learning progress. We show how IMGEPs automatically generate a learning curriculum within an experimental setup where a real humanoid robot can explore multiple spaces of goals with several hundred continuous dimensions. While no particular target goal is provided to the system beforehand, this curriculum allows the discovery of skills of increasing complexity, that act as stepping stone for learning more complex skills (like nested tool use). We show that learning several spaces of diverse problems can be more efficient for learning complex skills than only trying to directly learn these complex skills. We illustrate the computational efficiency of IMGEPs as these robotic experiments use a simple memory-based low-level policy representations and search algorithm, enabling the whole system to learn online and incrementally on a Raspberry Pi 3.
https://arxiv.org/abs/1708.02190
Visual attention, which assigns weights to image regions according to their relevance to a question, is considered as an indispensable part by most Visual Question Answering models. Although the questions may involve complex relations among multiple regions, few attention models can effectively encode such cross-region relations. In this paper, we demonstrate the importance of encoding such relations by showing the limited effective receptive field of ResNet on two datasets, and propose to model the visual attention as a multivariate distribution over a grid-structured Conditional Random Field on image regions. We demonstrate how to convert the iterative inference algorithms, Mean Field and Loopy Belief Propagation, as recurrent layers of an end-to-end neural network. We empirically evaluated our model on 3 datasets, in which it surpasses the best baseline model of the newly released CLEVR dataset by 9.5%, and the best published model on the VQA dataset by 1.25%. Source code is available at https: //github.com/zhuchen03/vqa-sva.
https://arxiv.org/abs/1708.02071
Neural machine translation (NMT) has achieved notable success in recent times, however it is also widely recognized that this approach has limitations with handling infrequent words and word pairs. This paper presents a novel memory-augmented NMT (M-NMT) architecture, which stores knowledge about how words (usually infrequently encountered ones) should be translated in a memory and then utilizes them to assist the neural model. We use this memory mechanism to combine the knowledge learned from a conventional statistical machine translation system and the rules learned by an NMT system, and also propose a solution for out-of-vocabulary (OOV) words based on this framework. Our experiments on two Chinese-English translation tasks demonstrated that the M-NMT architecture outperformed the NMT baseline by $9.0$ and $2.7$ BLEU points on the two tasks, respectively. Additionally, we found this architecture resulted in a much more effective OOV treatment compared to competitive methods.
https://arxiv.org/abs/1708.02005
Fully convolutional neural networks (FCNs) have shown outstanding performance in many dense labeling problems. One key pillar of these successes is mining relevant information from features in convolutional layers. However, how to better aggregate multi-level convolutional feature maps for salient object detection is underexplored. In this work, we present Amulet, a generic aggregating multi-level convolutional feature framework for salient object detection. Our framework first integrates multi-level feature maps into multiple resolutions, which simultaneously incorporate coarse semantics and fine details. Then it adaptively learns to combine these feature maps at each resolution and predict saliency maps with the combined features. Finally, the predicted results are efficiently fused to generate the final saliency map. In addition, to achieve accurate boundary inference and semantic enhancement, edge-aware feature maps in low-level layers and the predicted results of low resolution features are recursively embedded into the learning framework. By aggregating multi-level convolutional features in this efficient and flexible manner, the proposed saliency model provides accurate salient object labeling. Comprehensive experiments demonstrate that our method performs favorably against state-of-the art approaches in terms of near all compared evaluation metrics.
https://arxiv.org/abs/1708.02001
Phrases play an important role in natural language understanding and machine translation (Sag et al., 2002; Villavicencio et al., 2005). However, it is difficult to integrate them into current neural machine translation (NMT) which reads and generates sentences word by word. In this work, we propose a method to translate phrases in NMT by integrating a phrase memory storing target phrases from a phrase-based statistical machine translation (SMT) system into the encoder-decoder architecture of NMT. At each decoding step, the phrase memory is first re-written by the SMT model, which dynamically generates relevant target phrases with contextual information provided by the NMT model. Then the proposed model reads the phrase memory to make probability estimations for all phrases in the phrase memory. If phrase generation is carried on, the NMT decoder selects an appropriate phrase from the memory to perform phrase translation and updates its decoding state by consuming the words in the selected phrase. Otherwise, the NMT decoder generates a word from the vocabulary as the general NMT decoder does. Experiment results on the Chinese to English translation show that the proposed model achieves significant improvements over the baseline on various test sets.
https://arxiv.org/abs/1708.01980
Real-world image recognition systems need to recognize tens of thousands of classes that constitute a plethora of visual concepts. The traditional approach of annotating thousands of images per class for training is infeasible in such a scenario, prompting the use of webly supervised data. This paper explores the training of image-recognition systems on large numbers of images and associated user comments. In particular, we develop visual n-gram models that can predict arbitrary phrases that are relevant to the content of an image. Our visual n-gram models are feed-forward convolutional networks trained using new loss functions that are inspired by n-gram models commonly used in language modeling. We demonstrate the merits of our models in phrase prediction, phrase-based image retrieval, relating images and captions, and zero-shot transfer.
https://arxiv.org/abs/1612.09161
In the encoder-decoder architecture for neural machine translation (NMT), the hidden states of the recurrent structures in the encoder and decoder carry the crucial information about the sentence.These vectors are generated by parameters which are updated by back-propagation of translation errors through time. We argue that propagating errors through the end-to-end recurrent structures are not a direct way of control the hidden vectors. In this paper, we propose to use word predictions as a mechanism for direct supervision. More specifically, we require these vectors to be able to predict the vocabulary in target sentence. Our simple mechanism ensures better representations in the encoder and decoder without using any extra data or annotation. It is also helpful in reducing the target side vocabulary and improving the decoding efficiency. Experiments on Chinese-English and German-English machine translation tasks show BLEU improvements by 4.53 and 1.3, respectively
https://arxiv.org/abs/1708.01771
Training object detectors with only image-level annotations is very challenging because the target objects are often surrounded by a large number of background clutters. Many existing approaches tackle this problem through object proposal mining. However, the collected positive regions are either low in precision or lack of diversity, and the strategy of collecting negative regions is not carefully designed, neither. Moreover, training is often slow because region selection and object detector training are processed separately. In this context, the primary contribution of this work is to improve weakly supervised detection with an optimized region selection strategy. The proposed method collects purified positive training regions by progressively removing easy background clutters, and selects discriminative negative regions by mining class-specific hard samples. This region selection procedure is further integrated into a CNN-based weakly supervised detection (WSD) framework, and can be performed in each stochastic gradient descent mini-batch during training. Therefore, the entire model can be trained end-to-end efficiently. Extensive evaluation results on PASCAL VOC 2007, VOC 2010 and VOC 2012 datasets are presented which demonstrate that the proposed method effectively improves WSD.
https://arxiv.org/abs/1708.01723
This work proposes Recurrent Neural Network (RNN) models to predict structured ‘image situations’ – actions and noun entities fulfilling semantic roles related to the action. In contrast to prior work relying on Conditional Random Fields (CRFs), we use a specialized action prediction network followed by an RNN for noun prediction. Our system obtains state-of-the-art accuracy on the challenging recent imSitu dataset, beating CRF-based models, including ones trained with additional data. Further, we show that specialized features learned from situation prediction can be transferred to the task of image captioning to more accurately describe human-object interactions.
https://arxiv.org/abs/1703.06233
Since 2010 IceCube observed around 50 high-energy neutrino events of cosmic origin above 60 TeV, but the astrophysical sources of these events are still unknown. We recently proposed high-energy emitting BL Lac (HBL) objects as candidate emitters of high-energy neutrinos. Assuming a direct proportionality between high-energy gamma-ray and very-high energy neutrino fluxes, we calculated the expected neutrino event number in a year for IceCube and the presently under construction Km3NeT. To give a value of the significance of a detection we considered also the background for the single sources. To this aim we derived the through-going muon rate, generated by muon neutrino including the effect of Earth absorption, the density of the Earth and the cross section $\nu N$. Applying this calculation both to HBL sources and the atmospherical neutrino background, we can calculate the expected significance of the detection by IceCube, showing that our scenario is compatible with a no detection of HBL.
https://arxiv.org/abs/1708.01540
Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both the visual content of images and the textual content of questions. The approaches used to represent the images and questions in a fine-grained manner and questions and to fuse these multi-modal features play key roles in performance. Bilinear pooling based models have been shown to outperform traditional linear models for VQA, but their high-dimensional representations and high computational complexity may seriously limit their applicability in practice. For multi-modal feature fusion, here we develop a Multi-modal Factorized Bilinear (MFB) pooling approach to efficiently and effectively combine multi-modal features, which results in superior performance for VQA compared with other bilinear pooling approaches. For fine-grained image and question representation, we develop a co-attention mechanism using an end-to-end deep network architecture to jointly learn both the image and question attentions. Combining the proposed MFB approach with co-attention learning in a new network architecture provides a unified model for VQA. Our experimental results demonstrate that the single MFB with co-attention model achieves new state-of-the-art performance on the real-world VQA dataset. Code available at this https URL.
https://arxiv.org/abs/1708.01471
This manuscript introduces the problem of prominent object detection and recognition inspired by the fact that human seems to priorities perception of scene elements. The problem deals with finding the most important region of interest, segmenting the relevant item/object in that area, and assigning it an object class label. In other words, we are solving the three problems of saliency modeling, saliency detection, and object recognition under one umbrella. The motivation behind such a problem formulation is (1) the benefits to the knowledge representation-based vision pipelines, and (2) the potential improvements in emulating bio-inspired vision systems by solving these three problems together. We are foreseeing extending this problem formulation to fully semantically segmented scenes with instance object priority for high-level inferences in various applications including assistive vision. Along with a new problem definition, we also propose a method to achieve such a task. The proposed model predicts the most important area in the image, segments the associated objects, and labels them. The proposed problem and method are evaluated against human fixations, annotated segmentation masks, and object class categories. We define a chance level for each of the evaluation criterion to compare the proposed algorithm with. Despite the good performance of the proposed baseline, the overall evaluations indicate that the problem of prominent object detection and recognition is a challenging task that is still worth investigating further.
https://arxiv.org/abs/1704.07402
To bridge the gap between humans and machines in image understanding and describing, we need further insight into how people describe a perceived scene. In this paper, we study the agreement between bottom-up saliency-based visual attention and object referrals in scene description constructs. We investigate the properties of human-written descriptions and machine-generated ones. We then propose a saliency-boosted image captioning model in order to investigate benefits from low-level cues in language models. We learn that (1) humans mention more salient objects earlier than less salient ones in their descriptions, (2) the better a captioning model performs, the better attention agreement it has with human descriptions, (3) the proposed saliency-boosted model, compared to its baseline form, does not improve significantly on the MS COCO database, indicating explicit bottom-up boosting does not help when the task is well learnt and tuned on a data, (4) a better generalization is, however, observed for the saliency-boosted model on unseen data.
https://arxiv.org/abs/1704.07434
Photorealistic frontal view synthesis from a single face image has a wide range of applications in the field of face recognition. Although data-driven deep learning methods have been proposed to address this problem by seeking solutions from ample face data, this problem is still challenging because it is intrinsically ill-posed. This paper proposes a Two-Pathway Generative Adversarial Network (TP-GAN) for photorealistic frontal view synthesis by simultaneously perceiving global structures and local details. Four landmark located patch networks are proposed to attend to local textures in addition to the commonly used global encoder-decoder network. Except for the novel architecture, we make this ill-posed problem well constrained by introducing a combination of adversarial loss, symmetry loss and identity preserving loss. The combined loss function leverages both frontal face distribution and pre-trained discriminative deep face models to guide an identity preserving inference of frontal views from profiles. Different from previous deep learning methods that mainly rely on intermediate features for recognition, our method directly leverages the synthesized identity preserving image for downstream tasks like face recognition and attribution estimation. Experimental results demonstrate that our method not only presents compelling perceptual results but also outperforms state-of-the-art results on large pose face recognition.
https://arxiv.org/abs/1704.04086
Progress has been achieved recently in object detection given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their applicability in robotics, where solutions must scale to a large number of objects and variety of conditions. This work proposes an autonomous process for training a Convolutional Neural Network (CNN) for object detection and pose estimation in robotic setups. The focus is on detecting objects placed in cluttered, tight environments, such as a shelf with multiple objects. In particular, given access to 3D object models, several aspects of the environment are physically simulated. The models are placed in physically realistic poses with respect to their environment to generate a labeled synthetic dataset. To further improve object detection, the network self-trains over real images that are labeled using a robust multi-view pose estimation process. The proposed training process is evaluated on several existing datasets and on a dataset collected for this paper with a Motoman robotic arm. Results show that the proposed approach outperforms popular training processes relying on synthetic - but not physically realistic - data and manual annotation. The key contributions are the incorporation of physical reasoning in the synthetic data generation process and the automation of the annotation process over real images.
https://arxiv.org/abs/1703.03347
The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural networks such as GoogleNet and VGG, novel object detection frameworks such as R-CNN and its successors, Fast R-CNN and Faster R-CNN, play an essential role in improving the state-of-the-art. Despite their effectiveness on still images, those frameworks are not specifically designed for object detection from videos. Temporal and contextual information of videos are not fully investigated and utilized. In this work, we propose a deep learning framework that incorporates temporal and contextual information from tubelets obtained in videos, which dramatically improves the baseline performance of existing still-image detection frameworks when they are applied to videos. It is called T-CNN, i.e. tubelets with convolutional neueral networks. The proposed framework won the recently introduced object-detection-from-video (VID) task with provided data in the ImageNet Large-Scale Visual Recognition Challenge 2015 (ILSVRC2015).
https://arxiv.org/abs/1604.02532
Linguistic resources such as part-of-speech (POS) tags have been extensively used in statistical machine translation (SMT) frameworks and have yielded better performances. However, usage of such linguistic annotations in neural machine translation (NMT) systems has been left under-explored. In this work, we show that multi-task learning is a successful and a easy approach to introduce an additional knowledge into an end-to-end neural attentional model. By jointly training several natural language processing (NLP) tasks in one system, we are able to leverage common information and improve the performance of the individual task. We analyze the impact of three design decisions in multi-task learning: the tasks used in training, the training schedule, and the degree of parameter sharing across the tasks, which is defined by the network architecture. The experiments are conducted for an German to English translation task. As additional linguistic resources, we exploit POS information and named-entities (NE). Experiments show that the translation quality can be improved by up to 1.5 BLEU points under the low-resource condition. The performance of the POS tagger is also improved using the multi-task learning scheme.
https://arxiv.org/abs/1708.00993
Future frame prediction in videos is a promising avenue for unsupervised video representation learning. Video frames are naturally generated by the inherent pixel flows from preceding frames based on the appearance and motion dynamics in the video. However, existing methods focus on directly hallucinating pixel values, resulting in blurry predictions. In this paper, we develop a dual motion Generative Adversarial Net (GAN) architecture, which learns to explicitly enforce future-frame predictions to be consistent with the pixel-wise flows in the video through a dual-learning mechanism. The primal future-frame prediction and dual future-flow prediction form a closed loop, generating informative feedback signals to each other for better video prediction. To make both synthesized future frames and flows indistinguishable from reality, a dual adversarial training method is proposed to ensure that the future-flow prediction is able to help infer realistic future-frames, while the future-frame prediction in turn leads to realistic optical flows. Our dual motion GAN also handles natural motion uncertainty in different pixel locations with a new probabilistic motion encoder, which is based on variational autoencoders. Extensive experiments demonstrate that the proposed dual motion GAN significantly outperforms state-of-the-art approaches on synthesizing new video frames and predicting future flows. Our model generalizes well across diverse visual scenes and shows superiority in unsupervised video representation learning.
https://arxiv.org/abs/1708.00284
Research in Simultaneous Localization And Mapping (SLAM) is increasingly moving towards richer world representations involving objects and high level features that enable a semantic model of the world for robots, potentially leading to a more meaningful set of robot-world interactions. Many of these advances are grounded in state-of-the-art computer vision techniques primarily developed in the context of image-based benchmark datasets, leaving several challenges to be addressed in adapting them for use in robotics. In this paper, we derive a formulation for Simultaneous Localization And Mapping (SLAM) that uses dual quadrics as 3D landmark representations, and show how 2D bounding boxes (such as those typically obtained from visual object detection systems) can directly constrain the quadric parameters. Our paper demonstrates how to jointly estimate the robot pose and dual quadric parameters in factor graph based SLAM with a general perspective camera, and covers the use-cases of a robot moving with a monocular camera with and without the availability of additional depth information.
https://arxiv.org/abs/1708.00965
Language Models based on recurrent neural networks have dominated recent image caption generation tasks. In this paper, we introduce a Language CNN model which is suitable for statistical language modeling tasks and shows competitive performance in image captioning. In contrast to previous models which predict next word based on one previous word and hidden state, our language CNN is fed with all the previous words and can model the long-range dependencies of history words, which are critical for image captioning. The effectiveness of our approach is validated on two datasets MS COCO and Flickr30K. Our extensive experimental results show that our method outperforms the vanilla recurrent neural network based language models and is competitive with the state-of-the-art methods.
https://arxiv.org/abs/1612.07086
Intelligent selection of training data has proven a successful technique to simultaneously increase training efficiency and translation performance for phrase-based machine translation (PBMT). With the recent increase in popularity of neural machine translation (NMT), we explore in this paper to what extent and how NMT can also benefit from data selection. While state-of-the-art data selection (Axelrod et al., 2011) consistently performs well for PBMT, we show that gains are substantially lower for NMT. Next, we introduce dynamic data selection for NMT, a method in which we vary the selected subset of training data between different training epochs. Our experiments show that the best results are achieved when applying a technique we call gradual fine-tuning, with improvements up to +2.6 BLEU over the original data selection approach and up to +3.1 BLEU over a general baseline.
https://arxiv.org/abs/1708.00712
In this paper, we investigate a weakly-supervised object detection framework. Most existing frameworks focus on using static images to learn object detectors. However, these detectors often fail to generalize to videos because of the existing domain shift. Therefore, we investigate learning these detectors directly from boring videos of daily activities. Instead of using bounding boxes, we explore the use of action descriptions as supervision since they are relatively easy to gather. A common issue, however, is that objects of interest that are not involved in human actions are often absent in global action descriptions known as “missing label”. To tackle this problem, we propose a novel temporal dynamic graph Long Short-Term Memory network (TD-Graph LSTM). TD-Graph LSTM enables global temporal reasoning by constructing a dynamic graph that is based on temporal correlations of object proposals and spans the entire video. The missing label issue for each individual frame can thus be significantly alleviated by transferring knowledge across correlated objects proposals in the whole video. Extensive evaluations on a large-scale daily-life action dataset (i.e., Charades) demonstrates the superiority of our proposed method. We also release object bounding-box annotations for more than 5,000 frames in Charades. We believe this annotated data can also benefit other research on video-based object recognition in the future.
https://arxiv.org/abs/1708.00666
In this work, we propose an efficient and effective approach for unconstrained salient object detection in images using deep convolutional neural networks. Instead of generating thousands of candidate bounding boxes and refining them, our network directly learns to generate the saliency map containing the exact number of salient objects. During training, we convert the ground-truth rectangular boxes to Gaussian distributions that better capture the ROI regarding individual salient objects. During inference, the network predicts Gaussian distributions centered at salient objects with an appropriate covariance, from which bounding boxes are easily inferred. Notably, our network performs saliency map prediction without pixel-level annotations, salient object detection without object proposals, and salient object subitizing simultaneously, all in a single pass within a unified framework. Extensive experiments show that our approach outperforms existing methods on various datasets by a large margin, and achieves more than 100 fps with VGG16 network on a single GPU during inference.
https://arxiv.org/abs/1708.00079
Visual question answering as recently proposed multimodal learning task has enjoyed wide attention from the deep learning community. Lately, the focus was on developing new representation fusion methods and attention mechanisms to achieve superior performance. On the other hand, very little focus has been put on the models’ loss function, arguably one of the most important aspects of training deep learning models. The prevailing practice is to use cross entropy loss function that penalizes the probability given to all the answers in the vocabulary except the single most common answer for the particular question. However, the VQA evaluation function compares the predicted answer with all the ground-truth answers for the given question and if there is a matching, a partial point is given. This causes a discrepancy between the model’s cross entropy loss and the model’s accuracy as calculated by the VQA evaluation function. In this work, we propose a novel loss, termed as soft cross entropy, that considers all ground-truth answers and thus reduces the loss-accuracy discrepancy. The proposed loss leads to an improved training convergence of VQA models and an increase in accuracy as much as 1.6%.
https://arxiv.org/abs/1708.00584
In this paper, we offer an in-depth analysis about the modeling and search performance. We address the question if a more complex search algorithm is necessary. Furthermore, we investigate the question if more complex models which might only be applicable during rescoring are promising. By separating the search space and the modeling using $n$-best list reranking, we analyze the influence of both parts of an NMT system independently. By comparing differently performing NMT systems, we show that the better translation is already in the search space of the translation systems with less performance. This results indicate that the current search algorithms are sufficient for the NMT systems. Furthermore, we could show that even a relatively small $n$-best list of $50$ hypotheses already contain notably better translations.
https://arxiv.org/abs/1708.00563