Whole-body Control (WBC) has emerged as an important framework in locomotion control for legged robots. However, most of WBC frameworks fail to generalize beyond rigid terrains. Legged locomotion over soft terrain is difficult due to the presence of unmodeled contact dynamics that WBCs do not account for. This introduces uncertainty in locomotion and affects the stability and performance of the system. In this paper, we propose a novel soft terrain adaptation algorithm called STANCE: Soft Terrain Adaptation and Compliance Estimation. STANCE consists of a WBC that exploits the knowledge of the terrain to generate an optimal solution that is contact consistent and an online terrain compliance estimator that provides the WBC with terrain knowledge. We validated STANCE both in simulation and experiment on the Hydraulically actuated Quadruped (HyQ) robot, and we compared it against the state of the art WBC. We demonstrated the capabilities of STANCE with multiple terrains of different compliances, aggressive maneuvers, different forward velocities, and external disturbances. STANCE allowed HyQ to adapt online to terrains with different compliances (rigid and soft) without pre-tuning. HyQ was able to successfully deal with the transition between different terrains and showed the ability to differentiate between compliances under each foot.
http://arxiv.org/abs/1904.12306
We present RL-GAN-Net, where a reinforcement learning (RL) agent provides fast and robust control of a generative adversarial network (GAN). Our framework is applied to point cloud shape completion that converts noisy, partial point cloud data into a high-fidelity completed shape by controlling the GAN. While a GAN is unstable and hard to train, we circumvent the problem by (1) training the GAN on the latent space representation whose dimension is reduced compared to the raw point cloud input and (2) using an RL agent to find the correct input to the GAN to generate the latent space representation of the shape that best fits the current input of incomplete point cloud. The suggested pipeline robustly completes point cloud with large missing regions. To the best of our knowledge, this is the first attempt to train an RL agent to control the GAN, which effectively learns the highly nonlinear mapping from the input noise of the GAN to the latent space of point cloud. The RL agent replaces the need for complex optimization and consequently makes our technique real time. Additionally, we demonstrate that our pipelines can be used to enhance the classification accuracy of point cloud with missing data.
http://arxiv.org/abs/1904.12304
This paper presents an improved scheme for the generation and adaption of synthetic images for the training of deep Convolutional Neural Networks(CNNs) to perform the object detection task in smart vending machines. While generating synthetic data has proved to be effective for complementing the training data in supervised learning methods, challenges still exist for generating virtual images which are similar to those of the complex real scenes and minimizing redundant training data. To solve these problems, we consider the simulation of cluttered objects placed in a virtual scene and the wide-angle camera with distortions used to capture the whole scene in the data generation process, and post-processed the generated images with a elaborately-designed generative network to make them more similar to the real images. Various experiments have been conducted to prove the efficiency of using the generated virtual images to enhance the detection precision on existing datasets with limited real training data and the generalization ability of applying the trained network to datasets collected in new environment.
http://arxiv.org/abs/1904.12294
Automatic feature extraction using neural networks has accomplished remarkable success for images, but for sound recognition, these models are usually modified to fit the nature of the multi-dimensional temporal representation of the audio signal in spectrograms. This may not efficiently harness the time-frequency representation of the signal. The ConditionaL Neural Network (CLNN) takes into consideration the interrelation between the temporal frames, and the Masked ConditionaL Neural Network (MCLNN) extends upon the CLNN by forcing a systematic sparseness over the network’s weights using a binary mask. The masking allows the network to learn about frequency bands rather than bins, mimicking a filterbank used in signal transformations such as MFCC. Additionally, the Mask is designed to consider various combinations of features, which automates the feature hand-crafting process. We applied the MCLNN for the Environmental Sound Recognition problem using the Urbansound8k, YorNoise, ESC-10 and ESC-50 datasets. The MCLNN have achieved competitive performance compared to state-of-the-art Convolutional Neural Networks and hand-crafted attempts.
http://arxiv.org/abs/1802.02617
This paper focuses on the temporal aspect for recognizing human activities in videos; an important visual cue that has long been undervalued. We revisit the conventional definition of activity and restrict it to Complex Action: a set of one-actions with a weak temporal pattern that serves a specific purpose. Related works use spatiotemporal 3D convolutions with fixed kernel size, too rigid to capture the varieties in temporal extents of complex actions, and too short for long-range temporal modeling. In contrast, we use multi-scale temporal convolutions, and we reduce the complexity of 3D convolutions. The outcome is Timeception convolution layers, which reasons about minute-long temporal patterns, a factor of 8 longer than best related works. As a result, Timeception achieves impressive accuracy in recognizing the human activities of Charades, Breakfast Actions, and MultiTHUMOS. Further, we demonstrate that Timeception learns long-range temporal dependencies and tolerate temporal extents of complex actions.
http://arxiv.org/abs/1812.01289
Deep neural network architectures designed for application domains other than sound, especially image recognition, may not optimally harness the time-frequency representation when adapted to the sound recognition problem. In this work, we explore the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural Network (MCLNN) for multi-dimensional temporal signal recognition. The CLNN considers the inter-frame relationship, and the MCLNN enforces a systematic sparseness over the network’s links to enable learning in frequency bands rather than bins allowing the network to be frequency shift invariant mimicking a filterbank. The mask also allows considering several combinations of features concurrently, which is usually handcrafted through exhaustive manual search. We applied the MCLNN to the environmental sound recognition problem using the ESC-10 and ESC-50 datasets. MCLNN achieved competitive performance, using 12% of the parameters and without augmentation, compared to state-of-the-art Convolutional Neural Networks.
http://arxiv.org/abs/1802.05792
The prevalence of accessible depth sensing and 3D laser scanning techniques has enabled the convenient acquisition of 3D dynamic point clouds, which provide efficient representation of arbitrarily-shaped objects in motion. Nevertheless, dynamic point clouds are often perturbed by noise due to hardware, software or other causes. While many methods have been proposed for the denoising of static point clouds, dynamic point cloud denoising has not been studied in the literature yet. Hence, we address this problem based on the proposed spatio-temporal graph modeling, exploiting both the intra-frame similarity and inter-frame consistency. Specifically, we first represent a point cloud sequence on graphs and model it via spatio-temporal Gaussian Markov Random Fields on defined patches. Then for each target patch, we pose a Maximum a Posteriori estimation, and propose the corresponding likelihood and prior functions via spectral graph theory, leveraging its similar patches within the same frame and corresponding patch in the previous frame. This leads to our problem formulation, which jointly optimizes the underlying dynamic point cloud and spatio-temporal graph. Finally, we propose an efficient algorithm for patch construction, similar/corresponding patch search, intra- and inter-frame graph construction, and the optimization of our problem formulation via alternating minimization. Experimental results show that the proposed method outperforms frame-by-frame denoising from state-of-the-art static point cloud denoising approaches.
http://arxiv.org/abs/1904.12284
Neural network based architectures used for sound recognition are usually adapted from other application domains such as image recognition, which may not harness the time-frequency representation of a signal. The ConditionaL Neural Networks (CLNN) and its extension the Masked ConditionaL Neural Networks (MCLNN) are designed for multidimensional temporal signal recognition. The CLNN is trained over a window of frames to preserve the inter-frame relation, and the MCLNN enforces a systematic sparseness over the network’s links that mimics a filterbank-like behavior. The masking operation induces the network to learn in frequency bands, which decreases the network susceptibility to frequency-shifts in time-frequency representations. Additionally, the mask allows an exploration of a range of feature combinations concurrently analogous to the manual handcrafting of the optimum collection of features for a recognition task. MCLNN have achieved competitive performance on the Ballroom music dataset compared to several hand-crafted attempts and outperformed models based on state-of-the-art Convolutional Neural Networks.
http://arxiv.org/abs/1801.05504
Path planning is a major problem in autonomous vehicles. In recent years, with the increase in applications of Unmanned Aerial Vehicles (UAVs), one of the main challenges is path planning, particularly in adversarial environments. In this paper, we consider the problem of planning a collision-free path for a UAV in a polygonal domain from a source point to a target point. Based on the characteristics of UAVs, we assume two basic limitations on the generated paths: an upper bound on the turning angle at each turning point (maximum turning angle) and a lower bound on the distance between two consecutive turns (minimum route leg length). We describe an algorithm that runs in $O(n^4)$ time and finds a feasible path in accordance with the above limitations, where $n$ is the number of obstacle vertices. As shown by experiments, the output of the algorithm is much close to the shortest path with this requirements. We further demonstrate how to decompose the algorithm into two phases, preprocessing time and query time. In this way, given a fixed start point and a set of obstacles, we can preprocess a data-structure of size $O(n^4)$ in $O(n^4)$ time, such that for any query target point we can find a path with the given requirements in $O(n^2)$ time. Finally, we modify the algorithm to find a feasible (almost shortest) path that reach the target point within a given range of directions.
http://arxiv.org/abs/1904.12283
Recurrent Neural Networks have lately gained a lot of popularity in language modelling tasks, especially in neural machine translation(NMT). Very recent NMT models are based on Encoder-Decoder, where a deep LSTM based encoder is used to project the source sentence to a fixed dimensional vector and then another deep LSTM decodes the target sentence from the vector. However there has been very little work on exploring architectures that have more than one layer in space(i.e. in each time step). This paper examines the effectiveness of the simple Recurrent Highway Networks(RHN) in NMT tasks. The model uses Recurrent Highway Neural Network in encoder and decoder, with attention .We also explore the reconstructor model to improve adequacy. We demonstrate the effectiveness of all three approaches on the IWSLT English-Vietnamese dataset. We see that RHN performs on par with LSTM based models and even better in some cases.We see that deep RHN models are easy to train compared to deep LSTM based models because of highway connections. The paper also investigates the effects of increasing recurrent depth in each time step.
http://arxiv.org/abs/1905.01996
Subspace clustering is a problem of exploring the low-dimensional subspaces of high-dimensional data. State-of-the-arts approaches are designed by following the model of spectral clustering based method. These methods pay much attention to learn the representation matrix to construct a suitable similarity matrix and overlook the influence of the noise term on subspace clustering. However, the real data are always contaminated by the noise and the noise usually has a complicated statistical distribution. To alleviate this problem, we in this paper propose a subspace clustering method based on Cauchy loss function (CLF). Particularly, it uses CLF to penalize the noise term for suppressing the large noise mixed in the real data. This is due to that the CLF’s influence function has a upper bound which can alleviate the influence of a single sample, especially the sample with a large noise, on estimating the residuals. Furthermore, we theoretically prove the grouping effect of our proposed method, which means that highly correlated data can be grouped together. Finally, experimental results on five real datasets reveal that our proposed method outperforms several representative clustering methods.
http://arxiv.org/abs/1904.12274
In the advent of a digital health revolution, vast amounts of clinical data are being generated, stored and processed on a daily basis. This has made the storage and retrieval of large volumes of health-care data, especially, high-resolution medical images, particularly challenging. Effective image compression for medical images thus plays a vital role in today’s healthcare information system, particularly in teleradiology. In this work, an X-ray image compression method based on a Convolutional Recurrent Neural Networks RNN-Conv is presented. The proposed architecture can provide variable compression rates during deployment while it requires each network to be trained only once for a specific dimension of X-ray images. The model uses a multi-level pooling scheme that learns contextualized features for effective compression. We perform our image compression experiments on the National Institute of Health (NIH) ChestX-ray8 dataset and compare the performance of the proposed architecture with a state-of-the-art RNN based technique and JPEG 2000. The experimental results depict improved compression performance achieved by the proposed method in terms of Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR) metrics. To the best of our knowledge, this is the first reported evaluation on using a deep convolutional RNN for medical image compression.
http://arxiv.org/abs/1904.12271
Vygotsky’s notions of Zone of Proximal Development and Dynamic Assessment emphasize the importance of personalized learning that adapts to the needs and abilities of the learners and enables more efficient learning. In this work we introduce a novel adaptive learning engine called E-gostky that builds on these concepts to personalize the learning path within an e-learning system. E-gostky uses machine learning techniques to select the next content item that will challenge the student but will not be overwhelming, keeping students in their Zone of Proximal Development. To evaluate the system, we conducted an experiment where hundreds of students from several different elementary schools used our engine to learn fractions for five months. Our results show that using E-gostky can significantly reduce the time required to reach similar mastery. Specifically, in our experiment, it took students who were using the adaptive learning engine $17\%$ less time to reach a similar level of mastery as of those who didn’t. Moreover, students made greater efforts to find the correct answer rather than guessing and class teachers reported that even students with learning disabilities showed higher engagement.
http://arxiv.org/abs/1904.12268
A dialogue act (DA) represents the meaning of an utterance at the illocutionary force level (Austin 1962) such as a question, a request, and a greeting. Since DAs take charge of the most fundamental part of communication, we believe that the elucidation of DA learning mechanism is important for cognitive science and artificial intelligence. The purpose of this study is to verify that scaffolding takes place when a human teaches a robot, and to let a robot learn to estimate DAs and to make a response based on them step by step utilizing scaffolding provided by a human. To realize that, it is necessary for the robot to detect changes in utterance and rewards given by the partner and continue learning accordingly. Experimental results demonstrated that participants who continued interaction for a sufficiently long time often gave scaffolding for the robot. Although the number of experiments is still insufficient to obtain a definite conclusion, we observed that 1) the robot quickly learned to respond to DAs in most cases if the participants only spoke utterances that match the situation, 2) in the case of participants who builds scaffolding differently from what we assumed, learning did not proceed quickly, and 3) the robot could learn to estimate DAs almost exactly if the participants kept interaction for a sufficiently long time even if the scaffolding was unexpected.
http://arxiv.org/abs/1810.09949
Video-based person re-identification (ReID) is a challenging problem, where some video tracks of people across non-overlapping cameras are available for matching. Feature aggregation from a video track is a key step for video-based person ReID. Many existing methods tackle this problem by average/maximum temporal pooling or RNNs with attention. However, these methods cannot deal with temporal dependency and spatial misalignment problems at the same time. We are inspired by video action recognition that involves the identification of different actions from video tracks. Firstly, we use 3D convolutions on video volume, instead of using 2D convolutions across frames, to extract spatial and temporal features simultaneously. Secondly, we use a non-local block to tackle the misalignment problem and capture spatial-temporal long-range dependencies. As a result, the network can learn useful spatial-temporal information as a weighted sum of the features in all space and temporal positions in the input feature map. Experimental results on three datasets show that our framework outperforms state-of-the-art approaches by a large margin on multiple metrics.
http://arxiv.org/abs/1807.05073
Sequence-to-sequence (S2S) modeling is becoming a popular paradigm for automatic speech recognition (ASR) because of its ability to jointly optimize all the conventional ASR components in an end-to-end (E2E) fashion. This report investigates the ability of E2E ASR from standard close-talk to far-field applications by encompassing entire multichannel speech enhancement and ASR components within the S2S model. There have been previous studies on jointly optimizing neural beamforming alongside E2E ASR for denoising. It is clear from both recent challenge outcomes and successful products that far-field systems would be incomplete without solving both denoising and dereverberation simultaneously. This report uses a recently developed architecture for far-field ASR by composing neural extensions of dereverberation and beamforming modules with the S2S ASR module as a single differentiable neural network and also clearly defining the role of each subnetwork. The original implementation of this architecture was successfully applied to the noisy speech recognition task (CHiME-4), while we applied this implementation to noisy reverberant tasks (DIRHA and REVERB). Our investigation shows that the method achieves better performance than conventional pipeline methods on the DIRHA English dataset and comparable performance on the REVERB dataset. It also has additional advantages of being neither iterative nor requiring parallel noisy and clean speech data.
http://arxiv.org/abs/1904.09049
This work formulates a novel loss term which can be appended to an RGB only image localization network’s loss function to improve its performance. A common technique used when regressing a camera’s pose from an image is to formulate the loss as a linear combination of positional and rotational error (using tuned hyperparameters as coefficients). In this work we observe that changes to rotation and position mutually affect the captured image, and in order to improve performance, a network’s loss function should include a term which combines error in both position and rotation. To that end we design a geometric loss term which considers the similarity between the predicted and ground truth poses using both position and rotation, and use it to augment the existing image localization network PoseNet. The loss term is simply appended to the loss function of the already existing image localization network. We achieve improvements in the localization accuracy of the network for indoor scenes: with decreases of up to 9.64% and 2.99% in the median positional and rotational error when compared to similar pipelines.
http://arxiv.org/abs/1905.03692
Video deblurring is a challenging task due to the spatially variant blur caused by camera shake, object motions, and depth variations, etc. Existing methods usually estimate optical flow in the blurry video to align consecutive frames or approximate blur kernels. However, they tend to generate artifacts or cannot effectively remove blur when the estimated optical flow is not accurate. To overcome the limitation of separate optical flow estimation, we propose a Spatio-Temporal Filter Adaptive Network (STFAN) for the alignment and deblurring in a unified framework. The proposed STFAN takes both blurry and restored images of the previous frame as well as blurry image of the current frame as input, and dynamically generates the spatially adaptive filters for the alignment and deblurring. We then propose a new Filter Adaptive Convolutional (FAC) layers to align the deblurred features of the previous frame with the current frame and remove the spatially variant blur from the features of the current frame. Finally, we develop a reconstruction network which takes the fusion of two transformed features to restore the clear frames. Both quantitative and qualitative evaluation results on the benchmark datasets and real-world videos demonstrate that the proposed algorithm performs favorably against state-of-the-art methods in terms of accuracy, speed as well as model size.
http://arxiv.org/abs/1904.12257
Remote sensing can provide crucial information for planetary rovers. However, they must validate these orbital observations with in situ measurements. Typically, this involves validating hyperspectral data using a spectrometer on-board the field robot. In order to achieve this, the robot must visit sampling locations that jointly improve a model of the environment while satisfying sampling constraints. However, current planners follow sub-optimal greedy strategies that are not scalable to larger regions. We demonstrate how the problem can be effectively defined in an MDP framework and propose a planning algorithm based on Monte Carlo Tree Search, which is devoid of the common drawbacks of existing planners and also provides superior performance. We evaluate our approach using hyperspectral imagery of a well-studied geologic site in Cuprite, Nevada.
http://arxiv.org/abs/1904.12255
Cross-modal transfer is helpful to enhance modality-specific discriminative power for scene recognition. To this end, this paper presents a unified framework to integrate the tasks of cross-modal translation and modality-specific recognition, termed as Translate-to-Recognize Network (TRecgNet). Specifically, both translation and recognition tasks share the same encoder network, which allows to explicitly regularize the training of recognition task with the help of translation, and thus improve its final generalization ability. For translation task, we place a decoder module on top of the encoder network and it is optimized with a new layer-wise semantic loss, while for recognition task, we use a linear classifier based on the feature embedding from encoder and its training is guided by the standard cross-entropy loss. In addition, our TRecgNet allows to exploit large numbers of unlabeled RGB-D data to train the translation task and thus improve the representation power of encoder network. Empirically, we verify that this new semi-supervised setting is able to further enhance the performance of recognition network. We perform experiments on two RGB-D scene recognition benchmarks: NYU Depth v2 and SUN RGB-D, demonstrating that TRecgNet achieves superior performance to the existing state-of-the-art methods, especially for recognition solely based on a single modality.
http://arxiv.org/abs/1904.12254
Exploiting the temporal dependency among video frames or subshots is very important for the task of video summarization. Practically, RNN is good at temporal dependency modeling, and has achieved overwhelming performance in many video-based tasks, such as video captioning and classification. However, RNN is not capable enough to handle the video summarization task, since traditional RNNs, including LSTM, can only deal with short videos, while the videos in the summarization task are usually in longer duration. To address this problem, we propose a hierarchical recurrent neural network for video summarization, called H-RNN in this paper. Specifically, it has two layers, where the first layer is utilized to encode short video subshots cut from the original video, and the final hidden state of each subshot is input to the second layer for calculating its confidence to be a key subshot. Compared to traditional RNNs, H-RNN is more suitable to video summarization, since it can exploit long temporal dependency among frames, meanwhile, the computation operations are significantly lessened. The results on two popular datasets, including the Combined dataset and VTW dataset, have demonstrated that the proposed H-RNN outperforms the state-of-the-arts.
http://arxiv.org/abs/1904.12251
We propose Unified Visual-Semantic Embeddings (UniVSE) for learning a joint space of visual and textual concepts. The space unifies the concepts at different levels, including objects, attributes, relations, and full scenes. A contrastive learning approach is proposed for the fine-grained alignment from only image-caption pairs. Moreover, we present an effective approach for enforcing the coverage of semantic components that appear in the sentence. We demonstrate the robustness of Unified VSE in defending text-domain adversarial attacks on cross-modal retrieval tasks. Such robustness also empowers the use of visual cues to resolve word dependencies in novel sentences.
https://arxiv.org/abs/1904.05521
When analyzing the spread of viruses, epidemiologists often need to identify the location of infected hosts. This information can be found in public databases, such as GenBank, however, information provided in these databases are usually limited to the country or state level. More fine-grained localization information requires phylogeographers to manually read relevant scientific articles. In this work we propose an approach to automate the process of place name identification from medical (epidemiology) articles. The focus of this paper is to propose a deep learning based model for toponym detection and experiment with the use of external linguistic features and domain specific information. The model was evaluated using a collection of 105 epidemiology articles from PubMed Central provided by the recent SemEval task 12. Our best detection model achieves an F1 score of $80.13\%$, a significant improvement compared to the state of the art of $69.84\%$. These results underline the importance of domain specific embedding as well as specific linguistic features in toponym detection in medical journals.
https://arxiv.org/abs/1904.11018
In recent years, binary code learning, a.k.a hashing, has received extensive attention in large-scale multimedia retrieval. It aims to encode high-dimensional data points to binary codes, hence the original high-dimensional metric space can be efficiently approximated via Hamming space. However, most existing hashing methods adopted offline batch learning, which is not suitable to handle incremental datasets with streaming data or new instances. In contrast, the robustness of the existing online hashing remains as an open problem, while the embedding of supervised/semantic information hardly boosts the performance of the online hashing, mainly due to the defect of unknown category numbers in supervised learning. In this paper, we proposed an online hashing scheme, termed Hadamard Codebook based Online Hashing (HCOH), which aims to solve the above problems towards robust and supervised online hashing. In particular, we first assign an appropriate high-dimensional binary codes to each class label, which is generated randomly by Hadamard codes to each class label, which is generated randomly by Hadamard codes. Subsequently, LSH is adopted to reduce the length of such Hadamard codes in accordance with the hash bits, which can adapt the predefined binary codes online, and theoretically guarantee the semantic similarity. Finally, we consider the setting of stochastic data acquisition, which facilitates our method to efficiently learn the corresponding hashing functions via stochastic gradient descend (SGD) online. Notably, the proposed HCOH can be embedded with supervised labels and it not limited to a predefined category number. Extensive experiments on three widely-used benchmarks demonstrate the merits of the proposed scheme over the state-of-the-art methods.
http://arxiv.org/abs/1905.03694
In dark channel based methods, local constant assumption is widely used to make the algorithms invertible. It inevitably introduces defects since the assumption can not perfectly avoid depth discontinuities and meanwhile cover enough pixels. Unfortunately, because of the limitation of the prior, which only confirms the existence of dark things but does not specify their locations or likelihood, no fidelity measurement is available in refinement thus the defects are either under-corrected or over-corrected. In this paper, we go deeper than the dark channel theory to overcome this problem. We split the concept of dark channel into dark pixels and local constant assumption, and then, control the problematic assumption based on a novel weight map. With such effort, our methods show significant improvement on quality and have competitive speed. In the last, we show that the method is highly robust to initial transmission estimates and can be ever-improved by providing better dark pixel locations.
http://arxiv.org/abs/1904.12245
We propose a light-weight video frame interpolation algorithm. Our key innovation is an instance-level supervision that allows information to be learned from the high-resolution version of similar objects. Our experiment shows that the proposed method can generate state-of-the-art results across different datasets, with fractional computation resources (time and memory) of competing methods. Given two image frames, a cascade network creates an intermediate frame with 1) a flow-warping module that computes coarse bi-directional optical flow and creates an interpolated image via flow-based warping, followed by 2) an image synthesis module to make fine-scale corrections. In the learning stage, object detection proposals are generated on the interpolated image.Lower resolution objects are zoomed into, and the learning algorithms using an adversarial loss trained on high-resolution objects to guide the system towards the instance-level refinement corrects details of object shape and boundaries.
http://arxiv.org/abs/1812.01210
Accurate retrieval of the power equipment information plays an important role in guiding the full-lifecycle management of power system assets. Because of data duplication, database decentralization, weak data relations, and sluggish data updates, the power asset management system eager to adopt a new strategy to avoid the information losses, bias, and improve the data storage efficiency and extraction process. Knowledge graph has been widely developed in large part owing to its schema-less nature. It enables the knowledge graph to grow seamlessly and allows new relations addition and entities insertion when needed. This study proposes an approach for constructing power equipment knowledge graph by merging existing multi-source heterogeneous power equipment related data. A graph-search method to illustrate exhaustive results to the desired information based on the constructed knowledge graph is proposed. A case of a 500 kV station example is then demonstrated to show relevant search results and to explain that the knowledge graph can improve the efficiency of power equipment management.
http://arxiv.org/abs/1904.12242
MLaaS (ML-as-a-Service) offerings by cloud computing platforms are becoming increasingly popular these days. Pre-trained machine learning models are deployed on the cloud to support prediction based applications and services. For achieving higher throughput, incoming requests are served by running multiple replicas of the model on different machines concurrently. Incidence of straggler nodes in distributed inference is a significant concern since it can increase inference latency, violate SLOs of the service. In this paper, we propose a novel coded inference model to deal with stragglers in distributed image classification. We propose modified single shot object detection models, Collage-CNN models, to provide necessary resilience efficiently. A Collage-CNN model takes collage images formed by combining multiple images as its input and performs multi-image classification in one shot. We generate custom training collages using images from standard image classification datasets and train the model to achieve high classification accuracy. Deploying the Collage-CNN models in the cloud, we demonstrate that the 99th percentile latency can be reduced by 1.45X to 2.46X compared to replication based approaches and without compromising prediction accuracy.
http://arxiv.org/abs/1904.12222
Discriminatively trained neural classifiers can be trusted, only when the input data comes from the training distribution (in-distribution). Therefore, detecting out-of-distribution (OOD) samples is very important to avoid classification errors. In the context of OOD detection for image classification, one of the recent approaches proposes training a classifier called “confident-classifier” by minimizing the standard cross-entropy loss on in-distribution samples and minimizing the KL divergence between the predictive distribution of OOD samples in the low-density regions of in-distribution and the uniform distribution (maximizing the entropy of the outputs). Thus, the samples could be detected as OOD if they have low confidence or high entropy. In this paper, we analyze this setting both theoretically and experimentally. We conclude that the resulting confident-classifier still yields arbitrarily high confidence for OOD samples far away from the in-distribution. We instead suggest training a classifier by adding an explicit “reject” class for OOD samples.
http://arxiv.org/abs/1904.12220
When translating phrases (words or group of words), human translators, consciously or not, resort to different translation processes apart from the literal translation, such as Idiom Equivalence, Generalization, Particularization, Semantic Modulation, etc. Translators and linguists (such as Vinay and Darbelnet, Newmark, etc.) have proposed several typologies to characterize the different translation processes. However, to the best of our knowledge, there has not been effort to automatically classify these fine-grained translation processes. Recently, an English-French parallel corpus of TED Talks has been manually annotated with translation process categories, along with established annotation guidelines. Based on these annotated examples, we propose an automatic classification of translation processes at subsentential level. Experimental results show that we can distinguish non-literal translation from literal translation with an accuracy of 87.09%, and 55.20% for classifying among five non-literal translation processes. This work demonstrates that it is possible to automatically classify translation processes. Even with a small amount of annotated examples, our experiments show the directions that we can follow in future work. One of our long term objectives is leveraging this automatic classification to better control paraphrase extraction from bilingual parallel corpora.
http://arxiv.org/abs/1904.12213
Knowledge graphs (KGs), i.e. representation of information as a semantic graph, provide a significant test bed for many tasks including question answering, recommendation, and link prediction. Various amount of scholarly metadata have been made vailable as knowledge graphs from the diversity of data providers and agents. However, these high-quantities of data remain far from quality criteria in terms of completeness while growing at a rapid pace. Most of the attempts in completing such KGs are following traditional data digitization, harvesting and collaborative curation approaches. Whereas, advanced AI-related approaches such as embedding models - specifically designed for such tasks - are usually evaluated for standard benchmarks such as Freebase and Wordnet. The tailored nature of such datasets prevents those approaches to shed the lights on more accurate discoveries. Application of such models on domain-specific KGs takes advantage of enriched meta-data and provides accurate results where the underlying domain can enormously benefit. In this work, the TransE embedding model is reconciled for a specific link prediction task on scholarly metadata. The results show a significant shift in the accuracy and performance evaluation of the model on a dataset with scholarly metadata. The newly proposed version of TransE obtains 99.9% for link prediction task while original TransE gets 95%. In terms of accuracy and Hit@10, TransE outperforms other embedding models such as ComplEx, TransH and TransR experimented over scholarly knowledge graphs
http://arxiv.org/abs/1904.12211
As an intuitive way of expression emotion, the animated Graphical Interchange Format (GIF) images have been widely used on social media. Most previous studies on automated GIF emotion recognition fail to effectively utilize GIF’s unique properties, and this potentially limits the recognition performance. In this study, we demonstrate the importance of human related information in GIFs and conduct human-centered GIF emotion recognition with a proposed Keypoint Attended Visual Attention Network (KAVAN). The framework consists of a facial attention module and a hierarchical segment temporal module. The facial attention module exploits the strong relationship between GIF contents and human characters, and extracts frame-level visual feature with a focus on human faces. The Hierarchical Segment LSTM (HS-LSTM) module is then proposed to better learn global GIF representations. Our proposed framework outperforms the state-of-the-art on the MIT GIFGIF dataset. Furthermore, the facial attention module provides reliable facial region mask predictions, which improves the model’s interpretability.
http://arxiv.org/abs/1904.12201
Magnetic resonance imaging (MRI) is being increasingly utilized to assess, diagnose, and plan treatment for a variety of diseases. The ability to visualize tissue in varied contrasts in the form of MR pulse sequences in a single scan provides valuable insights to physicians, as well as enabling automated systems performing downstream analysis. However many issues like prohibitive scan time, image corruption, different acquisition protocols, or allergies to certain contrast materials may hinder the process of acquiring multiple sequences for a patient. This poses challenges to both physicians and automated systems since complementary information provided by the missing sequences is lost. In this paper, we propose a variant of generative adversarial network (GAN) capable of leveraging redundant information contained within multiple available sequences in order to generate one or more missing sequences for a patient scan. The proposed network is designed as a multi-input, multi-output network which combines information from all the available pulse sequences, implicitly infers which sequences are missing, and synthesizes the missing ones in a single forward pass. We demonstrate and validate our method on two brain MRI datasets each with four sequences, and show the applicability of the proposed method in simultaneously synthesizing all missing sequences in any possible scenario where either one, two, or three of the four sequences may be missing. We compare our approach with competing unimodal and multi-modal methods, and show that we outperform both quantitatively and qualitatively.
http://arxiv.org/abs/1904.12200
This paper demonstrates emergence of computational creativity in the field of music. Different aspects of creativity such as producer, process, product and press are studied and formulated. Different notions of computational creativity such as novelty, quality and typicality of compositions as products are studied and evaluated. We formulate an algorithmic perception on human creativity and propose a prototype that is capable of demonstrating human-level creativity. We then validate the proposed prototype by applying various creativity benchmarks with the results obtained and compare the proposed prototype with the other existing computational creative systems.
http://arxiv.org/abs/1904.12194
In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Unlike recent robustness research, this benchmark evaluates performance on commonplace corruptions not worst-case adversarial corruptions. We find that there are negligible changes in relative corruption robustness from AlexNet to ResNet classifiers, and we discover ways to enhance corruption robustness. Then we propose a new dataset called Icons-50 which opens research on a new kind of robustness, surface variation robustness. With this dataset we evaluate the frailty of classifiers on new styles of known objects and unexpected instances of known classes. We also demonstrate two methods that improve surface variation robustness. Together our benchmarks may aid future work toward networks that learn fundamental class structure and also robustly generalize.
http://arxiv.org/abs/1807.01697
Recent progress in biomedical image segmentation based on deep convolutional neural networks (CNNs) has drawn much attention. However, its vulnerability towards adversarial samples cannot be overlooked. This paper is the first one that discovers that all the CNN-based state-of-the-art biomedical image segmentation models are sensitive to adversarial perturbations. This limits the deployment of these methods in safety-critical biomedical fields. In this paper, we discover that global spatial dependencies and global contextual information in a biomedical image can be exploited to defend against adversarial attacks. To this end, non-local context encoder (NLCE) is proposed to model short- and long range spatial dependencies and encode global contexts for strengthening feature activations by channel-wise attention. The NLCE modules enhance the robustness and accuracy of the non-local context encoding network (NLCEN), which learns robust enhanced pyramid feature representations with NLCE modules, and then integrates the information across different levels. Experiments on both lung and skin lesion segmentation datasets have demonstrated that NLCEN outperforms any other state-of-the-art biomedical image segmentation methods against adversarial attacks. In addition, NLCE modules can be applied to improve the robustness of other CNN-based biomedical image segmentation methods.
http://arxiv.org/abs/1904.12181
FRI methods are less popular in the practical application domain. One possible reason is the missing common framework. There are many FRI methods developed independently, having different interpolation concepts and features. One trial for setting up a common FRI framework was the MATLAB FRI Toolbox, developed by Johany'ak et. al. in 2006. The goals of this paper are divided as follows: firstly, to present a brief introduction of the FRI methods. Secondly, to introduce a brief description of the refreshed and extended version of the original FRI Toolbox. And thirdly, to use different unified numerical benchmark examples to evaluate and analyze the Fuzzy Rule Interpolation Techniques (FRI) (KH, KH Stabilized, MACI, IMUL, CRF, VKK, GM, FRIPOC, LESFRI, and SCALEMOVE), that will be classified and compared based on different features by following the abnormality and linearity conditions [15].
http://arxiv.org/abs/1904.12178
Hyperspectral images (HSI) provide rich spectral information that contributed to the successful performance improvement of numerous computer vision tasks. However, it can only be achieved at the expense of images’ spatial resolution. Hyperspectral image super-resolution (HSI-SR) addresses this problem by fusing low resolution (LR) HSI with multispectral image (MSI) carrying much higher spatial resolution (HR). All existing HSI-SR approaches require the LR HSI and HR MSI to be well registered and the reconstruction accuracy of the HR HSI relies heavily on the registration accuracy of different modalities. This paper exploits the uncharted problem domain of HSI-SR without the requirement of multi-modality registration. Given the unregistered LR HSI and HR MSI with overlapped regions, we design a unique unsupervised learning structure linking the two unregistered modalities by projecting them into the same statistical space through the same encoder. The mutual information (MI) is further adopted to capture the non-linear statistical dependencies between the representations from two modalities (carrying spatial information) and their raw inputs. By maximizing the MI, spatial correlations between different modalities can be well characterized to further reduce the spectral distortion. A collaborative $l_{2,1}$ norm is employed as the reconstruction error instead of the more common $l_2$ norm, so that individual pixels can be recovered as accurately as possible. With this design, the network allows to extract correlated spectral and spatial information from unregistered images that better preserves the spectral information. The proposed method is referred to as unregistered and unsupervised mutual Dirichlet Net ($u^2$-MDN). Extensive experimental results using benchmark HSI datasets demonstrate the superior performance of $u^2$-MDN as compared to the state-of-the-art.
http://arxiv.org/abs/1904.12175
We investigate the use of Minimax distances to extract in a nonparametric way the features that capture the unknown underlying patterns and structures in the data. We develop a general-purpose framework to employ Minimax distances with many machine learning methods that perform on numerical data. For this purpose, first, we compute the pairwise Minimax distances between the objects, using the equivalence of Minimax distances over a graph and over a minimum spanning tree constructed on that. Then, we perform an embedding of the pairwise Minimax distances into a new vector space, such that their squared Euclidean distances in the new space equal to the pairwise Minimax distances in the original space. In the following, we study the case of having multiple pairwise Minimax matrices, instead of a single one. Thereby, we propose an embedding via first summing up the centered matrices and then performing an eigenvalue decomposition. Finally, we perform several experimental studies to illustrate the effectiveness of our framework.
http://arxiv.org/abs/1904.13223
Large crowdsourced datasets are widely used for training and evaluating neural models on natural language inference (NLI). Despite these efforts, neural models have a hard time capturing logical inferences, including those licensed by phrase replacements, so-called monotonicity reasoning. Since no large dataset has been developed for monotonicity reasoning, it is still unclear whether the main obstacle is the size of datasets or the model architectures themselves. To investigate this issue, we introduce a new dataset, called HELP, for handling entailments with lexical and logical phenomena. We add it to training data for the state-of-the-art neural models and evaluate them on test sets for monotonicity phenomena. The results showed that our data augmentation improved the overall accuracy. We also find that the improvement is better on monotonicity inferences with lexical replacements than on downward inferences with disjunction and modification. This suggests that some types of inferences can be improved by our data augmentation while others are immune to it.
http://arxiv.org/abs/1904.12166
Predicting future frames for a video sequence is a challenging generative modeling task. Promising approaches include probabilistic latent variable models such as the Variational Auto-Encoder. While VAEs can handle uncertainty and model multiple possible future outcomes, they have a tendency to produce blurry predictions. In this work we argue that this is a sign of underfitting. To address this issue, we propose to increase the expressiveness of the latent distributions and to use higher capacity likelihood models. Our approach relies on a hierarchy of latent variables, which defines a family of flexible prior and posterior distributions in order to better model the probability of future sequences. We validate our proposal through a series of ablation experiments and compare our approach to current state-of-the-art latent variable models. Our method performs favorably under several metrics in three different datasets.
http://arxiv.org/abs/1904.12165
We propose a sentiment classification method with a general machine learning framework. For feature representation, n-gram IDF is used to extract software-engineering-related, dataset-specific, positive, neutral, and negative n-gram expressions. For classifiers, an automated machine learning tool is used. In the comparison using publicly available datasets, our method achieved the highest F1 values in positive and negative sentences on all datasets.
http://arxiv.org/abs/1904.12162
The ConditionaL Neural Network (CLNN) exploits the nature of the temporal sequencing of the sound signal represented in a spectrogram, and its variant the Masked ConditionaL Neural Network (MCLNN) induces the network to learn in frequency bands by embedding a filterbank-like sparseness over the network’s links using a binary mask. Additionally, the masking automates the exploration of different feature combinations concurrently analogous to handcrafting the optimum combination of features for a recognition task. We have evaluated the MCLNN performance using the Urbansound8k dataset of environmental sounds. Additionally, we present a collection of manually recorded sounds for rail and road traffic, YorNoise, to investigate the confusion rates among machine generated sounds possessing low-frequency components. MCLNN has achieved competitive results without augmentation and using 12% of the trainable parameters utilized by an equivalent model based on state-of-the-art Convolutional Neural Networks on the Urbansound8k. We extended the Urbansound8k dataset with YorNoise, where experiments have shown that common tonal properties affect the classification performance.
http://arxiv.org/abs/1805.10004
In this paper,we design a formation control systrm for multi-unmanned ground vehicles(UGV) from the prospective of path planning and path tracking.The master-slave control is adopted by electing out a main vehicle to address the problem of possible accumulation,tranmission and amplification of errors.In the process of formation transformation,we first generate an expected path by combing the methods of dynamic window and potential energy field.Then a path tracking algorithm based on Hermite curve is adopted to make the formation transformation process more stable and accurate.Finally,the evaluation system of the formation control system is constructed,which combines the expected position,the actual position,the expected speed, the actual speed and the actual acceleration,giving an evalutaion on the performance of the formation transformation,response of the formation driving process and the performance of the formation stability.
http://arxiv.org/abs/1808.03682
With the rapid development of knowledge bases(KBs),question answering(QA)based on KBs has become a hot research issue. In this paper,we propose two frameworks(i.e.,pipeline framework,an end-to-end framework)to focus answering single-relation factoid question. In both of two frameworks,we study the effect of context information on the quality of QA,such as the entity’s notable type,out-degree. In the end-to-end framework,we combine char-level encoding and self-attention mechanisms,using weight sharing and multi-task strategies to enhance the accuracy of QA. Experimental results show that context information can get better results of simple QA whether it is the pipeline framework or the end-to-end framework. In addition,we find that the end-to-end framework achieves results competitive with state-of-the-art approaches in terms of accuracy and take much shorter time than them.
http://arxiv.org/abs/1905.01995
Understanding the properties exhibited by large scale network probing traffic would improve cyber threat intelligence. In addition, the prediction of probing rates is a key feature for security practitioners in their endeavors for making better operational decisions and for enhancing their defense strategy skills. In this work, we study different aspects of the traffic captured by a /20 network telescope. First, we perform an exploratory data analysis of the collected probing activities. The investigation includes probing rates at the port level, services interesting top network probers and the distribution of probing rates by geolocation. Second, we extract the network probers exploration patterns. We model these behaviors using transition graphs decorated with probabilities of switching from a port to another. Finally, we assess the capacity of Non-stationary Autoregressive and Vector Autoregressive models in predicting port probing rates as a first step towards using more robust models for better forecasting performance.
http://arxiv.org/abs/1812.09790
Acoustic event detection and scene classification are major research tasks in environmental sound analysis, and many methods based on neural networks have been proposed. Conventional methods have addressed these tasks separately; however, acoustic events and scenes are closely related to each other. For example, in the acoustic scene office'', the acoustic eventsmouse clicking’’ and ``keyboard typing’’ are likely to occur. In this paper, we propose multitask learning for joint analysis of acoustic events and scenes, which shares the parts of the networks holding information on acoustic events and scenes in common. By integrating the two networks, we expect that information on acoustic scenes will improve the performance of acoustic event detection. Experimental results obtained using TUT Sound Events 2016/2017 and TUT Acoustic Scenes 2016 datasets indicate that the proposed method improves the performance of acoustic event detection by 10.66 percentage points in terms of the F-score, compared with a conventional method based on a convolutional recurrent neural network.
http://arxiv.org/abs/1904.12146
The majority of the existing methods for non-rigid 3D surface regression from monocular 2D images require an object template or point tracks over multiple frames as an input, and are still far from real-time processing rates. In this work, we present the Isometry-Aware Monocular Generative Adversarial Network (IsMo-GAN) - an approach for direct 3D reconstruction from a single image, trained for the deformation model in an adversarial manner on a light-weight synthetic dataset. IsMo-GAN reconstructs surfaces from real images under varying illumination, camera poses, textures and shading at over 250 Hz. In multiple experiments, it consistently outperforms several approaches in the reconstruction accuracy, runtime, generalisation to unknown surfaces and robustness to occlusions. In comparison to the state-of-the-art, we reduce the reconstruction error by 10-30% including the textureless case and our surfaces evince fewer artefacts qualitatively.
http://arxiv.org/abs/1904.12144
Value iteration is a fundamental algorithm for solving Markov Decision Processes (MDPs). It computes the maximal $n$-step payoff by iterating $n$ times a recurrence equation which is naturally associated to the MDP. At the same time, value iteration provides a policy for the MDP that is optimal on a given finite horizon $n$. In this paper, we settle the computational complexity of value iteration. We show that, given a horizon $n$ in binary and an MDP, computing an optimal policy is EXP-complete, thus resolving an open problem that goes back to the seminal 1987 paper on the complexity of MDPs by Papadimitriou and Tsitsiklis. As a stepping stone, we show that it is EXP-complete to compute the $n$-fold iteration (with $n$ in binary) of a function given by a straight-line program over the integers with $\max$ and $+$ as operators.
http://arxiv.org/abs/1807.04920
The Artificial Intelligence paradigm (hereinafter referred to as “AI”) builds on the analysis of data able, among other things, to snap pictures of the individuals’ behaviors and preferences. Such data represent the most valuable currency in the digital ecosystem, where their value derives from their being a fundamental asset in order to train machines with a view to developing AI applications. In this environment, online providers attract users by offering them services for free and getting in exchange data generated right through the usage of such services. This swap, characterized by an implicit nature, constitutes the focus of the present paper, in the light of the disequilibria, as well as market failures, that it may bring about. We use mobile apps and the related permission system as an ideal environment to explore, via econometric tools, those issues. The results, stemming from a dataset of over one million observations, show that both buyers and sellers are aware that access to digital services implicitly implies an exchange of data, although this does not have a considerable impact neither on the level of downloads (demand), nor on the level of the prices (supply). In other words, the implicit nature of this exchange does not allow market indicators to work efficiently. We conclude that current policies (e.g. transparency rules) may be inherently biased and we put forward suggestions for a new approach.
http://arxiv.org/abs/1904.12134