Image-to-image (I2I) translation is a pixel-level mapping that requires a large number of paired training data and often suffers from the problems of high diversity and strong category bias in image scenes. In order to tackle these problems, we propose a novel BiLevel (BiL) learning paradigm that alternates the learning of two models, respectively at an instance-specific (IS) and a general-purpose (GP) level. In each scene, the IS model learns to maintain the specific scene attributes. It is initialized by the GP model that learns from all the scenes to obtain the generalizable translation knowledge. This GP initialization gives the IS model an efficient starting point, thus enabling its fast adaptation to the new scene with scarce training data. We conduct extensive I2I translation experiments on human face and street view datasets. Quantitative results validate that our approach can significantly boost the performance of classical I2I translation models, such as PG2 and Pix2Pix. Our visualization results show both higher image quality and more appropriate instance-specific details, e.g., the translated image of a person looks more like that person in terms of identity.
http://arxiv.org/abs/1904.09028
The Pointer-Generator architecture has shown to be a big improvement for abstractive summarization seq2seq models. However, the summaries produced by this model are largely extractive as over 30% of the generated sentences are copied from the source text. This work proposes a multihead attention mechanism, pointer dropout, and two new loss functions to promote more abstractive summaries while maintaining similar ROUGE scores. Both the multihead attention and dropout do not improve N-gram novelty, however, the dropout acts as a regularizer which improves the ROUGE score. The new loss function achieves significantly higher novel N-grams and sentences, at the cost of a slightly lower ROUGE score.
http://arxiv.org/abs/1905.01975
Within Reinforcement Learning, there is a growing collection of research which aims to express all of an agent’s knowledge of the world through predictions about sensation, behaviour, and time. This work can be seen not only as a collection of architectural proposals, but also as the beginnings of a theory of machine knowledge in reinforcement learning. Recent work has expanded what can be expressed using predictions, and developed applications which use predictions to inform decision-making on a variety of synthetic and real-world problems. While promising, we here suggest that the notion of predictions as knowledge in reinforcement learning is as yet underdeveloped: some work explicitly refers to predictions as knowledge, what the requirements are for considering a prediction to be knowledge have yet to be well explored. This specification of the necessary and sufficient conditions of knowledge is important; even if claims about the nature of knowledge are left implicit in technical proposals, the underlying assumptions of such claims have consequences for the systems we design. These consequences manifest in both the way we choose to structure predictive knowledge architectures, and how we evaluate them. In this paper, we take a first step to formalizing predictive knowledge by discussing the relationship of predictive knowledge learning methods to existing theories of knowledge in epistemology. Specifically, we explore the relationships between Generalized Value Functions and epistemic notions of Justification and Truth.
http://arxiv.org/abs/1904.09024
Within Reinforcement Learning, there is a fledgling approach to conceptualizing the environment in terms of predictions. Central to this predictive approach is the assertion that it is possible to construct ontologies in terms of predictions about sensation, behaviour, and time—to categorize the world into entities which express all aspects of the world using only predictions. This construction of ontologies is integral to predictive approaches to machine knowledge where objects are described exclusively in terms of how they are perceived. In this paper, we ground the Pericean model of semiotics in terms of Reinforcement Learning Methods, describing Peirce’s Three Categories in the notation of General Value Functions. Using the Peircean model of semiotics, we demonstrate that predictions alone are insufficient to construct an ontology; however, we identify predictions as being integral to the meaning-making process. Moreover, we discuss how predictive knowledge provides a particularly stable foundation for semiosis\textemdash the process of making meaning\textemdash and suggest a possible avenue of research to design algorithmic methods which construct semantics and meaning using predictions.
http://arxiv.org/abs/1904.09023
In this talk we describe our content-preserving attack on object detectors, ShapeShifter, and demonstrate how to evaluate this threat in realistic scenarios. We describe how we use CARLA, a realistic urban driving simulator, to create these scenarios, and how we use ShapeShifter to generate content-preserving attacks against those scenarios.
http://arxiv.org/abs/1904.12622
This paper aims at providing researchers and engineering professionals with a practical and comprehensive deep learning based solution to detect construction equipment from the very first step of its development to the last one which is deployment. This paper focuses on the last step of deployment. The first phase of solution development, involved data preparation, model selection, model training, and model evaluation. The second phase of the study comprises of model optimization, application specific embedded system selection, and economic analysis. Several embedded systems were proposed and compared. The review of the results confirms superior real-time performance of the solutions with a consistent above 90% rate of accuracy. The current study validates the practicality of deep learning based object detection solutions for construction scenarios. Moreover, the detailed knowledge, presented in this study, can be employed for several purposes such as, safety monitoring, productivity assessments, and managerial decisions.
http://arxiv.org/abs/1904.09021
To understand diverse natural language commands, virtual assistants today are trained with numerous labor-intensive, manually annotated sentences. This paper presents a methodology and the Genie toolkit that can handle new compound commands with significantly less manual effort. We advocate formalizing the capability of virtual assistants with a Virtual Assistant Programming Language (VAPL) and using a neural semantic parser to translate natural language into VAPL code. Genie needs only a small realistic set of input sentences for validating the neural model. Developers write templates to synthesize data; Genie uses crowdsourced paraphrases and data augmentation, along with the synthesized data, to train a semantic parser. We also propose design principles that make VAPL languages amenable to natural language translation. We apply these principles to revise ThingTalk, the language used by the Almond virtual assistant. We use Genie to build the first semantic parser that can support compound virtual assistants commands with unquoted free-form parameters. Genie achieves a 62% accuracy on realistic user inputs. We demonstrate Genie’s generality by showing a 19% and 31% improvement over the previous state of the art on a music skill, aggregate functions, and access control.
http://arxiv.org/abs/1904.09020
We explore the use of graph neural networks (GNNs) to model spatial processes in which there is a priori graphical structure. Similar to finite element analysis, we assign nodes of a GNN to spatial locations and use a computational process defined on the graph to model the relationship between an initial function defined over a space and a resulting function in the same space. We use GNNs as a computational substrate, and show that the locations of the nodes in space as well as their connectivity can be optimized to focus on the most complex parts of the space. Moreover, this representational strategy allows the learned input-output relationship to generalize over the size of the underlying space and run the same model at different levels of precision, trading computation for accuracy. We demonstrate this method on a traditional PDE problem, a physical prediction problem from robotics, and a problem of learning to predict scene images from novel viewpoints.
https://arxiv.org/abs/1904.09019
Segmenting objects in images and separating sound sources in audio are challenging tasks, in part because traditional approaches require large amounts of labeled data. In this paper we develop a neural network model for visual object segmentation and sound source separation that learns from natural videos through self-supervision. The model is an extension of recently proposed work that maps image pixels to sounds. Here, we introduce a learning approach to disentangle concepts in the neural networks, and assign semantic categories to network feature channels to enable independent image segmentation and sound source separation after audio-visual training on videos. Our evaluations show that the disentangled model outperforms several baselines in semantic segmentation and sound source separation.
http://arxiv.org/abs/1904.09013
This paper considers the problem of assigning multiple mobile robots to goals on transport networks with uncertain information about travel times. Our aim is to produce optimal assignments, such that the average waiting time at destinations is minimized. Since noisy travel time estimates result in sub-optimal assignments, we propose a method that offers resilience to uncertainty by making use of redundant robots. However, solving the redundant assignment problem optimally is strongly NP-hard. Hence, we exploit structural properties of our mathematical problem formulation to propose a polynomial-time, near-optimal solution. We demonstrate that our problem can be reduced to minimizing a supermodular cost function subject to a matroid constraint. This allows us to develop a greedy algorithm, for which we derive sub-optimality bounds. We demonstrate the effectiveness of our approach with simulations on transport networks, where uncertain edge costs and uncertain node positions lead to noisy travel time estimates. Comparisons to benchmark algorithms show that our method performs near-optimally and significantly better than non-redundant assignment. Finally, our findings include results on the benefit of diversity and complementarity in redundant robot coalitions; these insights contribute towards providing resilience to uncertainty through targeted robot team compositions.
http://arxiv.org/abs/1804.04986
We address the problem of landmark-based vehicle self-localization by relying on multi-modal sensory information. Our goal is to determine the autonomous vehicle’s pose based on landmark measurements and map landmarks. The map is built by extracting landmarks from the vehicle’s field of view in an off-line way, while the measurements are collected in the same way during inference. To map the measurements and map landmarks to the vehicle’s pose, we propose DeepLocalization, a deep neural network that copes with dynamic input. Our network is robust to missing landmarks that occur due to the dynamic environment and handles unordered and adaptive input. In real-world experiments, we evaluate two inference approaches to show that DeepLocalization can be combined with GPS-sensors and is complementary to filtering approaches such as an extended Kalman filter. We show that our approach achieves state-of-the-art accuracy and is about ten times faster than the related work.
http://arxiv.org/abs/1904.09007
This paper explains the math behind a generative adversarial network (GAN) model and why it is hard to be trained. Wasserstein GAN is intended to improve GANs’ training by adopting a smooth metric for measuring the distance between two probability distributions.
https://arxiv.org/abs/1904.08994
Children learn though play. We introduce the analogous idea of learning programs through play. In this approach, a program induction system (the learner) is given a set of tasks and initial background knowledge. Before solving the tasks, the learner enters an unsupervised playing stage where it creates its own tasks to solve, tries to solve them, and saves any solutions (programs) to the background knowledge. After the playing stage is finished, the learner enters the supervised building stage where it tries to solve the user-supplied tasks and can reuse solutions learnt whilst playing. The idea is that playing allows the learner to discover reusable general programs on its own which can then help solve the user-supplied tasks. We claim that playing can improve learning performance. We show that playing can reduce the textual complexity of target concepts which in turn reduces the sample complexity of a learner. We implement our idea in Playgol, a new inductive logic programming system. We experimentally test our claim on two domains: robot planning and real-world string transformations. Our experimental results suggest that playing can substantially improve learning performance. We think that the idea of playing (or, more verbosely, unsupervised bootstrapping for supervised program induction) is an important contribution to the problem of developing program induction approaches that self-discover BK.
http://arxiv.org/abs/1904.08993
In this paper, we present an end-to-end approach for environmental sound classification based on a 1D Convolution Neural Network (CNN) that learns a representation directly from the audio signal. Several convolutional layers are used to capture the signal’s fine time structure and learn diverse filters that are relevant to the classification task. The proposed approach can deal with audio signals of any length as it splits the signal into overlapped frames using a sliding window. Different architectures considering several input sizes are evaluated, including the initialization of the first convolutional layer with a Gammatone filterbank that models the human auditory filter response in the cochlea. The performance of the proposed end-to-end approach in classifying environmental sounds was assessed on the UrbanSound8k dataset and the experimental results have shown that it achieves 89% of mean accuracy. Therefore, the propose approach outperforms most of the state-of-the-art approaches that use handcrafted features or 2D representations as input. Furthermore, the proposed approach has a small number of parameters compared to other architectures found in the literature, which reduces the amount of data required for training.
http://arxiv.org/abs/1904.08990
We present a fully convolutional wav-to-wav network for converting between speakers’ voices, without relying on text. Our network is based on an encoder-decoder architecture, where the encoder is pre-trained for the task of Automatic Speech Recognition (ASR), and a multi-speaker waveform decoder is trained to reconstruct the original signal in an autoregressive manner. We train the network on narrated audiobooks, and demonstrate the ability to perform multi-voice TTS in those voices, by converting the voice of a TTS robot. We observe no degradation in the quality of the generated voices, in comparison to the reference TTS voice. The modularity of our approach, which separates the target voice generation from the TTS module, enables client-side personalized TTS in a privacy-aware manner.
http://arxiv.org/abs/1904.08983
Driving requires reacting to a wide variety of complex environment conditions and agent behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation learning can, in theory, leverage data from large fleets of human-driven cars. Behavior cloning in particular has been successfully used to learn simple visuomotor policies end-to-end, but scaling to the full spectrum of driving behaviors remains an unsolved problem. In this paper, we propose a new benchmark to experimentally investigate the scalability and limitations of behavior cloning. We show that behavior cloning leads to state-of-the-art results, including in unseen environments, executing complex lateral and longitudinal maneuvers without these reactions being explicitly programmed. However, we confirm well-known limitations (due to dataset bias and overfitting), new generalization issues (due to dynamic objects and the lack of a causal model), and training instability requiring further research before behavior cloning can graduate to real-world driving. The code of the studied behavior cloning approaches can be found at https://github.com/felipecode/coiltraine .
http://arxiv.org/abs/1904.08980
In this paper, we address the problem of inferring the layout of complex road scenes given a single camera as input. To achieve that, we first propose a novel parameterized model of road layouts in a top-view representation, which is not only intuitive for human visualization but also provides an interpretable interface for higher-level decision making. Moreover, the design of our top-view scene model allows for efficient sampling and thus generation of large-scale simulated data, which we leverage to train a deep neural network to infer our scene model’s parameters. Specifically, our proposed training procedure uses supervised domain-adaptation techniques to incorporate both simulated as well as manually annotated data. Finally, we design a Conditional Random Field (CRF) that enforces coherent predictions for a single frame and encourages temporal smoothness among video frames. Experiments on two public data sets show that: (1) Our parametric top-view model is representative enough to describe complex road scenes; (2) The proposed method outperforms baselines trained on manually-annotated or simulated data only, thus getting the best of both; (3) Our CRF is able to generate temporally smoothed while semantically meaningful results.
http://arxiv.org/abs/1812.06152
The procedural generation of levels and content in video games is a challenging AI problem. Often such generation relies on an intelligent way of evaluating the content being generated so that constraints are satisfied and/or objectives maximized. In this work, we address the problem of creating levels that are not only playable but also revolve around specific mechanics in the game. We use constrained evolutionary algorithms and quality-diversity algorithms to generate small sections of Super Mario Bros levels called scenes, using three different simulation approaches: Limited Agents, Punishing Model, and Mechanics Dimensions. All three approaches are able to create scenes that give opportunity for a player to encounter or use targeted mechanics with different properties. We conclude by discussing the advantages and disadvantages of each approach and compare them to each other.
http://arxiv.org/abs/1904.08972
Deep learning has revolutionized many computer vision fields in the last few years, including learning-based image compression. In this paper, we propose a deep semantic segmentation-based layered image compression (DSSLIC) framework in which the semantic segmentation map of the input image is obtained and encoded as the base layer of the bit-stream. A compact representation of the input image is also generated and encoded as the first enhancement layer. The segmentation map and the compact version of the image are then employed to obtain a coarse reconstruction of the image. The residual between the input and the coarse reconstruction is additionally encoded as another enhancement layer. Experimental results show that the proposed framework outperforms the H.265/HEVC-based BPG and other codecs in both PSNR and MS-SSIM metrics across a wide range of bit rates in RGB domain. Besides, since semantic segmentation map is included in the bit-stream, the proposed scheme can facilitate many other tasks such as image search and object-based adaptive image compression.
http://arxiv.org/abs/1806.03348
In this work, we describe limitations of the free-field propagation model for designing broadband beamformers for microphone arrays on a rigid surface. Towards this goal, we describe a general framework for quantifying the microphone array performance in a general wave-field by directly solving the acoustic wave equation. The model utilizes Finite-Element-Method (FEM) for evaluating the response of the microphone array surface to background 3D planar and spherical waves. The effectiveness of the framework is established by designing and evaluating a representative broadband beamformer under realistic acoustic conditions.
http://arxiv.org/abs/1904.08971
Deep learning (DL) approaches are state-of-the-art for many medical image segmentation tasks. They offer a number of advantages: they can be trained for specific tasks, computations are fast at test time, and segmentation quality is typically high. In contrast, previously popular multi-atlas segmentation (MAS) methods are relatively slow (as they rely on costly registrations) and even though sophisticated label fusion strategies have been proposed, DL approaches generally outperform MAS. In this work, we propose a DL-based label fusion strategy (VoteNet) which locally selects a set of reliable atlases whose labels are then fused via plurality voting. Experiments on 3D brain MRI data show that by selecting a good initial atlas set MAS with VoteNet significantly outperforms a number of other label fusion strategies as well as a direct DL segmentation approach. We also provide an experimental analysis of the upper performance bound achievable by our method. While unlikely achievable in practice, this bound suggests room for further performance improvements. Lastly, to address the runtime disadvantage of standard MAS, all our results make use of a fast DL registration approach.
http://arxiv.org/abs/1904.08963
Region based object detectors achieve the state-of-the-art performance, but few consider to model the relation of proposals. In this paper, we explore the idea of modeling the relationships among the proposals for object detection from the graph learning perspective. Specifically, we present relational proposal graph network (RepGN) which is defined on object proposals and the semantic and spatial relation modeled as the edge. By integrating our RepGN module into object detectors, the relation and context constraints will be introduced to the feature extraction of regions and bounding boxes regression and classification. Besides, we propose a novel graph-cut based pooling layer for hierarchical coarsening of the graph, which empowers the RepGN module to exploit the inter-regional correlation and scene description in a hierarchical manner. We perform extensive experiments on COCO object detection dataset and show promising results.
http://arxiv.org/abs/1904.08959
Understanding the dynamics of international politics is important yet challenging for civilians. In this work, we explore unsupervised neural models to infer relations between nations from news articles. We extend existing models by incorporating shallow linguistics information and propose a new automatic evaluation metric that aligns relationship dynamics with manually annotated key events. As understanding international relations requires carefully analyzing complex relationships, we conduct in-person human evaluations with three groups of participants. Overall, humans prefer the outputs of our model and give insightful feedback that suggests future directions for human-centered models. Furthermore, our model reveals interesting regional differences in news coverage. For instance, with respect to US-China relations, Singaporean media focus more on “strengthening” and “purchasing”, while US media focus more on “criticizing” and “denouncing”.
http://arxiv.org/abs/1904.08950
Many tasks in graphics and vision demand machinery for converting shapes into representations with sparse sets of parameters; these representations facilitate rendering, editing, and storage. When the source data is noisy or ambiguous, however, artists and engineers often manually construct such representations, a tedious and potentially time-consuming process. While advances in deep learning have been successfully applied to noisy geometric data, the task of generating parametric shapes has so far been difficult for these methods. Hence, we propose a new framework for predicting parametric shape primitives using deep learning. We use distance fields to transition between shape parameters like control points and input data on a raster grid. We demonstrate efficacy on 2D and 3D tasks, including font vectorization and surface abstraction.
http://arxiv.org/abs/1904.08921
Studies have shown that a dominant class of questions asked by visually impaired users on images of their surroundings involves reading text in the image. But today’s VQA models can not read! Our paper takes a first step towards addressing this problem. First, we introduce a new “TextVQA” dataset to facilitate progress on this important problem. Existing datasets either have a small proportion of questions about text (e.g., the VQA dataset) or are too small (e.g., the VizWiz dataset). TextVQA contains 45,336 questions on 28,408 images that require reasoning about text to answer. Second, we introduce a novel model architecture that reads text in the image, reasons about it in the context of the image and the question, and predicts an answer which might be a deduction based on the text and the image or composed of the strings found in the image. Consequently, we call our approach Look, Read, Reason & Answer (LoRRA). We show that LoRRA outperforms existing state-of-the-art VQA models on our TextVQA dataset. We find that the gap between human performance and machine performance is significantly larger on TextVQA than on VQA 2.0, suggesting that TextVQA is well-suited to benchmark progress along directions complementary to VQA 2.0.
http://arxiv.org/abs/1904.08920
In this work we address task interference in universal networks by considering that a network is trained on multiple tasks, but performs one task at a time, an approach we refer to as “single-tasking multiple tasks”. The network thus modifies its behaviour through task-dependent feature adaptation, or task attention. This gives the network the ability to accentuate the features that are adapted to a task, while shunning irrelevant ones. We further reduce task interference by forcing the task gradients to be statistically indistinguishable through adversarial training, ensuring that the common backbone architecture serving all tasks is not dominated by any of the task-specific gradients. Results in three multi-task dense labelling problems consistently show: (i) a large reduction in the number of parameters while preserving, or even improving performance and (ii) a smooth trade-off between computation and multi-task accuracy. We provide our system’s code and pre-trained models at this http URL
http://arxiv.org/abs/1904.08918
We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, masking blocks of frequency channels, and masking blocks of time steps. We apply SpecAugment on Listen, Attend and Spell networks for end-to-end speech recognition tasks. We achieve state-of-the-art performance on the LibriSpeech 960h and Swichboard 300h tasks, outperforming all prior work. On LibriSpeech, we achieve 6.8% WER on test-other without the use of a language model, and 5.8% WER with shallow fusion with a language model. This compares to the previous state-of-the-art hybrid system of 7.5% WER. For Switchboard, we achieve 7.2%/14.6% on the Switchboard/CallHome portion of the Hub5’00 test set without the use of a language model, and 6.8%/14.1% with shallow fusion, which compares to the previous state-of-the-art hybrid system at 8.3%/17.3% WER.
http://arxiv.org/abs/1904.08779
Injuries are a major cost in sports. Teams spend millions of dollars every year on players who are hurt and unable to play, resulting in lost games, decreased fan interest and additional wages for replacement players. Modern convolutional neural networks have been successfully applied to many video recognition tasks. In this paper, we introduce the problem of injury detection/prediction in MLB pitchers and experimentally evaluate the ability of such convolutional models to detect and predict injuries in pitches only from video data. We conduct experiments on a large dataset of TV broadcast MLB videos of 20 different pitchers who were injured during the 2017 season. We experimentally evaluate the model’s performance on each individual pitcher, how well it generalizes to new pitchers, how it performs for various injuries, and how early it can predict or detect an injury.
http://arxiv.org/abs/1904.08916
In this paper we tackle the problem of scene flow estimation in the context of self-driving. We leverage deep learning techniques as well as strong priors as in our application domain the motion of the scene can be composed by the motion of the robot and the 3D motion of the actors in the scene. We formulate the problem as energy minimization in a deep structured model, which can be solved efficiently in the GPU by unrolling a Gaussian-Newton solver. Our experiments in the challenging KITTI scene flow dataset show that we outperform the state-of-the-art by a very large margin, while being 800 times faster.
http://arxiv.org/abs/1904.08913
Watching cartoons can be useful for children’s intellectual, social and emotional development. However, the most popular video sharing platform today provides many videos with Elsagate content. Elsagate is a phenomenon that depicts childhood characters in disturbing circumstances (e.g., gore, toilet humor, drinking urine, stealing). Even with this threat easily available for children, there is no work in the literature addressing the problem. As the first to explore disturbing content in cartoons, we proceed from the most recent pornography detection literature applying deep convolutional neural networks combined with static and motion information of the video. Our solution is compatible with mobile platforms and achieved 92.6% of accuracy. Our goal is not only to introduce the first solution but also to bring up the discussion around Elsagate.
http://arxiv.org/abs/1904.08910
Keypoint-based methods are a relatively new paradigm in object detection, eliminating the need for anchor boxes and offering a simplified detection framework. Keypoint-based CornerNet achieves state of the art accuracy among single-stage detectors. However, this accuracy comes at high processing cost. In this work, we tackle the problem of efficient keypoint-based object detection and introduce CornerNet-Lite. CornerNet-Lite is a combination of two efficient variants of CornerNet: CornerNet-Saccade, which uses an attention mechanism to eliminate the need for exhaustively processing all pixels of the image, and CornerNet-Squeeze, which introduces a new compact backbone architecture. Together these two variants address the two critical use cases in efficient object detection: improving efficiency without sacrificing accuracy, and improving accuracy at real-time efficiency. CornerNet-Saccade is suitable for offline processing, improving the efficiency of CornerNet by 6.0x and the AP by 1.0% on COCO. CornerNet-Squeeze is suitable for real-time detection, improving both the efficiency and accuracy of the popular real-time detector YOLOv3 (34.4% AP at 34ms for CornerNet-Squeeze compared to 33.0% AP at 39ms for YOLOv3 on COCO). Together these contributions for the first time reveal the potential of keypoint-based detection to be useful for applications requiring processing efficiency.
http://arxiv.org/abs/1904.08900
Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate. Although significant efforts have been dedicated to design and improve mobile CNNs on all dimensions, it is very difficult to manually balance these trade-offs when there are so many architectural possibilities to consider. In this paper, we propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency. Unlike previous work, where latency is considered via another, often inaccurate proxy (e.g., FLOPS), our approach directly measures real-world inference latency by executing the model on mobile phones. To further strike the right balance between flexibility and search space size, we propose a novel factorized hierarchical search space that encourages layer diversity throughout the network. Experimental results show that our approach consistently outperforms state-of-the-art mobile CNN models across multiple vision tasks. On the ImageNet classification task, our MnasNet achieves 75.2% top-1 accuracy with 78ms latency on a Pixel phone, which is 1.8x faster than MobileNetV2 [29] with 0.5% higher accuracy and 2.3x faster than NASNet [36] with 1.2% higher accuracy. Our MnasNet also achieves better mAP quality than MobileNets for COCO object detection. Code is at https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet
http://arxiv.org/abs/1807.11626
Deep learning has revolutionized computer vision utilizing the increased availability of big data and the power of parallel computational units such as graphical processing units. The vast majority of deep learning research is conducted using images as training data, however the biomedical domain is rich in physiological signals that are used for diagnosis and prediction problems. It is still an open research question how to best utilize signals to train deep neural networks.
In this paper we define the term Signal2Image (S2Is) as trainable or non-trainable prefix modules that convert signals, such as Electroencephalography (EEG), to image-like representations making them suitable for training image-based deep neural networks defined as base models'. We compare the accuracy and time performance of four S2Is (signal as image’, spectrogram, one and two layer Convolutional Neural Networks (CNNs)) combined with a set of `base models’ (LeNet, AlexNet, VGGnet, ResNet, DenseNet) along with the depth-wise and 1D variations of the latter. We also provide empirical evidence that the one layer CNN S2I performs better in eleven out of fifteen tested models than non-trainable S2Is for classifying EEG signals and we present visual comparisons of the outputs of the S2Is.
http://arxiv.org/abs/1904.13216
We present Kernel Point Convolution (KPConv), a new design of point convolution, i.e. that operates on point clouds without any intermediate representation. The convolution weights of KPConv are located in Euclidean space by kernel points, and applied to the input points close to them. Its capacity to use any number of kernel points gives KPConv more flexibility than fixed grid convolutions. Furthermore, these locations are continuous in space and can be learned by the network. Therefore, KPConv can be extended to deformable convolutions that learn to adapt kernel points to local geometry. Thanks to a regular subsampling strategy, KPConv is also efficient and robust to varying densities. Whether they use deformable KPConv for complex tasks, or rigid KPconv for simpler tasks, our networks outperform state-of-the-art classification and segmentation approaches on several datasets. We also offer ablation studies and visualizations to provide understanding of what has been learned by KPConv and to validate the descriptive power of deformable KPConv.
http://arxiv.org/abs/1904.08889
No-reference image quality assessment (NR-IQA) aims to measure the image quality without reference image. However, contrast distortion has been overlooked in the current research of NR-IQA. In this paper, we propose a very simple but effective metric for predicting quality of contrast-altered images based on the fact that a high-contrast image is often more similar to its contrast enhanced image. Specifically, we first generate an enhanced image through histogram equalization. We then calculate the similarity of the original image and the enhanced one by using structural-similarity index (SSIM) as the first feature. Further, we calculate the histogram based entropy and cross entropy between the original image and the enhanced one respectively, to gain a sum of 4 features. Finally, we learn a regression module to fuse the aforementioned 5 features for inferring the quality score. Experiments on four publicly available databases validate the superiority and efficiency of the proposed technique.
http://arxiv.org/abs/1904.08879
In a recent article, Brette argues that coding as a concept is inappropriate for explanations of neurocognitive phenomena. Here, we argue that Brette’s conceptual analysis mischaracterizes the structure of causal claims in coding and other forms of analysis-by-decomposition. We argue that analyses of this form are permissible, conceptually coherent, and offer essential tools for building and developing models of neurocognitive systems like the brain.
http://arxiv.org/abs/1904.08873
We propose a novel method for salient object detection in different images. Our method integrates spatial features for efficient and robust representation to capture meaningful information about the salient objects. We then train a conditional random field (CRF) using the integrated features. The trained CRF model is then used to detect salient objects during the online testing stage. We perform experiments on two standard datasets and compare the performance of our method with different reference methods. Our experiments show that our method outperforms the compared methods in terms of precision, recall, and F-Measure.
http://arxiv.org/abs/1904.08868
Cell imaging and analysis are fundamental to biomedical research because cells are the basic functional units of life. Among different cell-related analysis, cell counting and detection are widely used. In this paper, we focus on one common step of learning-based cell counting approaches: coding the raw dot labels into more suitable maps for learning. Two criteria of coding raw dot labels are discussed, and a new coding scheme is proposed in this paper. The two criteria measure how easy it is to train the model with a coding scheme, and how robust the recovered raw dot labels are when predicting. The most compelling advantage of the proposed coding scheme is the ability to distinguish neighboring cells in crowded regions. Cell counting and detection experiments are conducted for five coding schemes on four types of cells and two network architectures. The proposed coding scheme improves the counting accuracy versus the widely-used Gaussian and rectangle kernels up to 12%, and also improves the detection accuracy versus the common proximity coding up to 14%.
http://arxiv.org/abs/1904.08864
We present a real-time dense geometric mapping algorithm for large-scale environments. Unlike existing methods which use pinhole cameras, our implementation is based on fisheye cameras which have larger field of view and benefit some other tasks including Visual-Inertial Odometry, localization and object detection around vehicles. Our algorithm runs on in-vehicle PCs at 15 Hz approximately, enabling vision-only 3D scene perception for self-driving vehicles. For each synchronized set of images captured by multiple cameras, we first compute a depth map for a reference camera using plane-sweeping stereo. To maintain both accuracy and efficiency, while accounting for the fact that fisheye images have a rather low resolution, we recover the depths using multiple image resolutions. We adopt the fast object detection framework YOLOv3 to remove potentially dynamic objects. At the end of the pipeline, we fuse the fisheye depth images into the truncated signed distance function (TSDF) volume to obtain a 3D map. We evaluate our method on large-scale urban datasets, and results show that our method works well even in complex environments.
http://arxiv.org/abs/1809.06132
The aim of the present study involves designing a humanoid robot guide as a walking trainer for elderly and rehabilitation patients. The system is based on the humanoid robot Pepper with a compliance approach that allows to match the motion intention of the user to the robot’s pace. This feasibility study is backed up by an experimental evaluation conducted in a rehabilitation centre. We hypothesize that Pepper robot used as an assistive partner, can also benefit elderly users by motivating them to perform physical activity.
http://arxiv.org/abs/1904.08854
A neuroscience method to understanding the brain is to find and study the preferred stimuli that highly activate an individual cell or groups of cells. Recent advances in machine learning enable a family of methods to synthesize preferred stimuli that cause a neuron in an artificial or biological brain to fire strongly. Those methods are known as Activation Maximization (AM) or Feature Visualization via Optimization. In this chapter, we (1) review existing AM techniques in the literature; (2) discuss a probabilistic interpretation for AM; and (3) review the applications of AM in debugging and explaining networks.
http://arxiv.org/abs/1904.08939
Variational Autoencoders(VAEs) have already achieved great results on image generation and recently made promising progress on music generation. However, the generation process is still quite difficult to control in the sense that the learned latent representations lack meaningful music semantics. It would be much more useful if people can modify certain music features, such as rhythm and pitch contour, via latent representations to test different composition ideas. In this paper, we propose a new method to inspect the pitch and rhythm interpretations of the latent representations and we name it disentanglement by augmentation. Based on the interpretable representations, an intuitive graphical user interface is designed for users to better direct the music creation process by manipulating the pitch contours and rhythmic complexity.
http://arxiv.org/abs/1904.08842
Most deep learning approaches for text-to-SQL generation are limited to the WikiSQL dataset, which only supports very simple queries over a single table. We focus on the Spider dataset, a complex and cross-domain text-to-SQL task, which includes complex queries over multiple tables. In this paper, we propose a SQL clause-wise decoding neural architecture with a self-attention based database schema encoder to address Spider task. Each of the clause-specific decoders consists of a set of sub-modules, which is defined by the syntax of each clause. Additionally, our model works recursively to support nested queries. The experimental result shows that our model outperforms the previous state-of-the-art model by 9.8% in the exact matching accuracy on the Spider dev dataset. In addition, we show that our model is significantly more effective to predict complex and nested queries than previous works.
http://arxiv.org/abs/1904.08835
This paper presents an admittance controller based on the passivity theory for a powered upper-limb exoskeleton robot which is governed by the nonlinear equation of motion. Passivity allows us to include a human operator and environmental interaction in the control loop. The robot interacts with the human operator via F/T sensor and interacts with the environment mainly via end-effectors. Although the environmental interaction cannot be detected by any sensors (hence unknown), passivity allows us to have natural interaction. An analysis shows that the behavior of the actual system mimics that of a nominal model as the control gain goes to infinity, which implies that the proposed approach is an admittance controller. However, because the control gain cannot grow infinitely in practice, the performance limitation according to the achievable control gain is also analyzed. The result of this analysis indicates that the performance in the sense of infinite norm increases linearly with the control gain. In the experiments, the proposed properties were verified using 1 degree-of-freedom testbench, and an actual powered upper-limb exoskeleton was used to lift and maneuver the unknown payload.
http://arxiv.org/abs/1904.08833
Image reconstruction techniques such as denoising often need to be applied to the RGB output of cameras and cellphones. Unfortunately, the commonly used additive white noise (AWGN) models do not accurately reproduce the noise and the degradation encountered on these inputs. This is particularly important for learning-based techniques, because the mismatch between training and real world data will hurt their generalization. This paper aims to accurately simulate the degradation and noise transformation performed by camera pipelines. This allows us to generate realistic degradation in RGB images that can be used to train machine learning models. We use our simulation to study the importance of noise modeling for learning-based denoising. Our study shows that a realistic noise model is required for learning to denoise real JPEG images. A neural network trained on realistic noise outperforms the one trained with AWGN by 3 dB. An ablation study of our pipeline shows that simulating denoising and demosaicking is important to this improvement and that realistic demosaicking algorithms, which have been rarely considered, is needed. We believe this simulation will also be useful for other image reconstruction tasks, and we will distribute our code publicly.
http://arxiv.org/abs/1904.08825
Deep neural networks have been widely used in computer vision. There are several well trained deep neural networks for the ImageNet classification challenge, which has played a significant role in image recognition. However, little work has explored pre-trained neural networks for image recognition in domain adaption. In this paper, we are the first to extract better-represented features from a pre-trained Inception ResNet model for domain adaptation. We then present a modified distribution alignment method for classification using the extracted features. We test our model using three benchmark datasets (Office+Caltech-10, Office-31, and Office-Home). Extensive experiments demonstrate significant improvements (4.8%, 5.5%, and 10%) in classification accuracy over the state-of-the-art.
http://arxiv.org/abs/1904.02322
Brette contends that the neural coding metaphor is an invalid basis for theories of what the brain does. Here, we argue that it is an insufficient guide for building an artificial intelligence that learns to accomplish short- and long-term goals in a complex, changing environment.
http://arxiv.org/abs/1904.10396
In this work, we define the task of teaser generation and provide an evaluation benchmark and baseline systems for the process of generating teasers. A teaser is a short reading suggestion for an article that is illustrative and includes curiosity-arousing elements to entice potential readers to read particular news items. Teasers are one of the main vehicles for transmitting news to social media users. We compile a novel dataset of teasers by systematically accumulating tweets and selecting those that conform to the teaser definition. We have compared a number of neural abstractive architectures on the task of teaser generation and the overall best performing system is See et al.(2017)’s seq2seq with pointer network.
http://arxiv.org/abs/1807.11535
Melanoma is the deadliest form of skin cancer. Automated skin lesion analysis plays an important role for early detection. Nowadays, the ISIC Archive and the Atlas of Dermoscopy dataset are the most employed skin lesion sources to benchmark deep-learning based tools. However, all datasets contain biases, often unintentional, due to how they were acquired and annotated. Those biases distort the performance of machine-learning models, creating spurious correlations that the models can unfairly exploit, or, contrarily destroying cogent correlations that the models could learn. In this paper, we propose a set of experiments that reveal both types of biases, positive and negative, in existing skin lesion datasets. Our results show that models can correctly classify skin lesion images without clinically-meaningful information: disturbingly, the machine-learning model learned over images where no information about the lesion remains, presents an accuracy above the AI benchmark curated with dermatologists’ performances. That strongly suggests spurious correlations guiding the models. We fed models with additional clinically meaningful information, which failed to improve the results even slightly, suggesting the destruction of cogent correlations. Our main findings raise awareness of the limitations of models trained and evaluated in small datasets such as the ones we evaluated, and may suggest future guidelines for models intended for real-world deployment.
http://arxiv.org/abs/1904.08818
Signal degradation is ubiquitous and computational restoration of degraded signal has been investigated for many years. Recently, it is reported that the capability of signal restoration is fundamentally limited by the perception-distortion tradeoff, i.e. the distortion and the perceptual difference between the restored signal and the ideal `original’ signal cannot be made both minimal simultaneously. Distortion corresponds to signal fidelity and perceptual difference corresponds to perceptual naturalness, both of which are important metrics in practice. Besides, there is another dimension worthy of consideration, namely the semantic quality or the utility for recognition purpose, of the restored signal. In this paper, we extend the previous perception-distortion tradeoff to the case of classification-distortion-perception (CDP) tradeoff, where we introduced the classification error rate of the restored signal in addition to distortion and perceptual difference. Two versions of the CDP tradeoff are considered, one using a predefined classifier and the other dealing with the optimal classifier for the restored signal. For both versions, we can rigorously prove the existence of the CDP tradeoff, i.e. the distortion, perceptual difference, and classification error rate cannot be made all minimal simultaneously. Our findings can be useful especially for computer vision researches where some low-level vision tasks (signal restoration) serve for high-level vision tasks (visual understanding).
http://arxiv.org/abs/1904.08816