Iris segmentation and localization in non-cooperative environment is challenging due to illumination variations, long distances, moving subjects and limited user cooperation, etc. Traditional methods often suffer from poor performance when confronted with iris images captured in these conditions. Recent studies have shown that deep learning methods could achieve impressive performance on iris segmentation task. In addition, as iris is defined as an annular region between pupil and sclera, geometric constraints could be imposed to help locating the iris more accurately and improve the segmentation results. In this paper, we propose a deep multi-task learning framework, named as IrisParseNet, to exploit the inherent correlations between pupil, iris and sclera to boost up the performance of iris segmentation and localization in a unified model. In particular, IrisParseNet firstly applies a Fully Convolutional Encoder-Decoder Attention Network to simultaneously estimate pupil center, iris segmentation mask and iris inner/outer boundary. Then, an effective post-processing method is adopted for iris inner/outer circle localization.To train and evaluate the proposed method, we manually label three challenging iris datasets, namely CASIA-Iris-Distance, UBIRIS.v2, and MICHE-I, which cover various types of noises. Extensive experiments are conducted on these newly annotated datasets, and results show that our method outperforms state-of-the-art methods on various benchmarks. All the ground-truth annotations, annotation codes and evaluation protocols are publicly available at https://github.com/xiamenwcy/IrisParseNet.
http://arxiv.org/abs/1901.11195
Vulnerability of neural networks under adversarial attacks has raised serious concerns and extensive research. Recent studies suggested that model robustness relies on the use of robust features, i.e., features with strong correlation with labels, and that data dimensionality and distribution affect the learning of robust features. On the other hand, experiments showed that human vision, which is robust against adversarial attacks, is invariant to natural input transformations. Drawing on these findings, this paper investigates whether constraints on transformation invariance, including image cropping, rotation, and zooming, will force image classifiers to learn and use robust features and in turn acquire better robustness. Experiments on MNIST and CIFAR10 show that transformation invariance alone has limited effect. Nonetheless, models adversarially trained on cropping-invariant attacks, in particular, can (1) extract more robust features, (2) have significantly better robustness than the state-of-the-art models from adversarial training, and (3) require less training data.
http://arxiv.org/abs/1901.11188
Several computer algorithms for recognition of visible human emotions are compared at the web camera scenario using CNN/MMOD face detector. The recognition refers to four face expressions: smile, surprise, anger, and neutral. At the feature extraction stage, the following three concepts of face description are confronted: (a) static 2D face geometry represented by its 68 characteristic landmarks (FP68); (b) dynamic 3D geometry defined by motion parameters for eight distinguished face parts (denoted as AU8) of personalized Candide-3 model; (c) static 2D visual description as 2D array of gray scale pixels (known as facial raw image). At the classification stage, the performance of two major models are analyzed: (a) support vector machine (SVM) with kernel options; (b) convolutional neural network (CNN) with variety of relevant tensor processing layers and blocks of them. The models are trained for frontal views of human faces while they are tested for arbitrary head poses. For geometric features, the success rate (accuracy) indicate nearly triple increase of performance of CNN with respect to SVM classifiers. For raw images, CNN outperforms in accuracy its best geometric counterpart (AU/CNN) by about 30 percent while the best SVM solutions are inferior nearly four times. For F-score the high advantage of raw/CNN over geometric/CNN and geometric/SVM is observed, as well. We conclude that contrary to CNN based emotion classifiers, the generalization capability wrt human head pose is for SVM based emotion classifiers poor.
http://arxiv.org/abs/1901.11186
Humans are increasingly coming into contact with artificial intelligence and machine learning systems. Human-centered artificial intelligence is a perspective on AI and ML that algorithms must be designed with awareness that they are part of a larger system consisting of humans. We lay forth an argument that human-centered artificial intelligence can be broken down into two aspects: (1) AI systems that understand humans from a sociocultural perspective, and (2) AI systems that help humans understand them. We further argue that issues of social responsibility such as fairness, accountability, interpretability, and transparency.
http://arxiv.org/abs/1901.11184
Several computer algorithms for recognition of visible human emotions are compared at the web camera scenario using CNN/MMOD face detector. The recognition refers to four face expressions: smile, surprise, anger, and neutral. At the feature extraction stage, the following three concepts of face description are confronted: (a) static 2D face geometry represented by its 68 characteristic landmarks (FP68); (b) dynamic 3D geometry defined by motion parameters for eight distinguished face parts (denoted as AU8) of personalized Candide-3 model; (c) static 2D visual description as 2D array of gray scale pixels (known as facial raw image). At the classification stage, the performance of two major models are analyzed: (a) support vector machine (SVM) with kernel options; (b) convolutional neural network (CNN) with variety of relevant tensor processing layers and blocks of them. The models are trained for frontal views of human faces while they are tested for arbitrary head poses. For geometric features, the success rate (accuracy) indicate nearly triple increase of performance of CNN with respect to SVM classifiers. For raw images, CNN outperforms in accuracy its best geometric counterpart (AU/CNN) by about 30 percent while the best SVM solutions are inferior nearly four times. For F-score the high advantage of raw/CNN over geometric/CNN and geometric/SVM is observed, as well. We conclude that contrary to CNN based emotion classifiers, the generalization capability wrt human head pose is for SVM based emotion classifiers poor.
http://arxiv.org/abs/1901.11179
For a long time, designing neural architectures that exhibit high performance was considered a dark art that required expert hand-tuning. One of the few well-known guidelines for architecture design is the avoidance of exploding gradients, though even this guideline has remained relatively vague and circumstantial. We introduce the nonlinearity coefficient (NLC), a measurement of the complexity of the function computed by a neural network that is based on the magnitude of the gradient. Via an extensive empirical study, we show that the NLC is a powerful predictor of test error and that attaining a right-sized NLC is essential for optimal performance. The NLC exhibits a range of intriguing and important properties. It is closely tied to the amount of information gained from computing a single network gradient. It is tied to the error incurred when replacing the nonlinearity operations in the network with linear operations. It is not susceptible to the confounders of multiplicative scaling, additive bias and layer width. It is stable from layer to layer. Hence, we argue that the NLC is the first robust predictor of overfitting in deep networks.
http://arxiv.org/abs/1806.00179
The emergence of continuous health monitoring and the availability of an enormous amount of time series data has provided a great opportunity for the advancement of personal health tracking. In recent years, unsupervised learning methods have drawn special attention of researchers to tackle the sparse annotation of health data and real-time detection of anomalies has been a central problem of interest. However, one problem that has not been well addressed before is the early prediction of forthcoming negative health events. Early signs of an event can introduce subtle and gradual changes in the health signal prior to its onset, detection of which can be invaluable in effective prevention. In this study, we first demonstrate our observations on the shortcoming of widely adopted anomaly detection methods in uncovering the changes prior to a negative health event. We then propose a framework which relies on online clustering of signal segment representations which are automatically learned by a specially designed LSTM auto-encoder. We show the effectiveness of our approach by predicting Bradycardia events in infants using MIT-PICS dataset 1.3 minutes ahead of time with 68\% AUC score on average, using no label supervision. Results of our study can indicate the viability of our approach in the early detection of health events in other applications as well.
http://arxiv.org/abs/1901.11168
In the literature, tensors have been effectively used for capturing the context information in language models. However, the existing methods usually adopt relatively-low order tensors, which have limited expressive power in modeling language. Developing a higher-order tensor representation is challenging, in terms of deriving an effective solution and showing its generality. In this paper, we propose a language model named Tensor Space Language Model (TSLM), by utilizing tensor networks and tensor decomposition. In TSLM, we build a high-dimensional semantic space constructed by the tensor product of word vectors. Theoretically, we prove that such tensor representation is a generalization of the n-gram language model. We further show that this high-order tensor representation can be decomposed to a recursive calculation of conditional probability for language modeling. The experimental results on Penn Tree Bank (PTB) dataset and WikiText benchmark demonstrate the effectiveness of TSLM.
http://arxiv.org/abs/1901.11167
The recognition of sign language is a challenging task with an important role in society to facilitate the communication of deaf persons. We propose a new approach of Spatial-Temporal Graph Convolutional Network to sign language recognition based on the human skeletal movements. The method uses graphs to capture the signs dynamics in two dimensions, spatial and temporal, considering the complex aspects of the language. Additionally, we present a new dataset of human skeletons for sign language based on ASLLVD to contribute to future related studies.
http://arxiv.org/abs/1901.11164
Building software-driven systems that are easily understood becomes a challenge, with their ever-increasing complexity and autonomy. Accordingly, recent research efforts strive to aid in designing explainable systems. Nevertheless, a common notion of what it takes for a system to be explainable is still missing. To address this problem, we propose a characterization of explainable systems that consolidates existing research. By providing a unified terminology, we lay a basis for the classification of both existing and future research, and the formulation of precise requirements towards such systems.
http://arxiv.org/abs/1902.03096
Recovering the 3D representation of an object from single-view or multi-view RGB images by deep neural networks has attracted increasing attention in the past few years. Several mainstream works (e.g., 3D-R2N2) use recurrent neural networks (RNNs) to fuse multiple feature maps extracted from input images sequentially. However, when given the same set of input images with different orders, RNN-based approaches are unable to produce consistent reconstruction results. Moreover, due to long-term memory loss, RNNs cannot fully exploit input images to refine reconstruction results. To solve these problems, we propose a novel framework for single-view and multi-view 3D reconstruction, named Pix2Vox. By using a well-designed encoder-decoder, it generates a coarse 3D volume from each input image. Then, a context-aware fusion module is introduced to adaptively select high-quality reconstructions for each part (e.g., table legs) from different coarse 3D volumes to obtain a fused 3D volume. Finally, a refiner further refines the fused 3D volume to generate the final output. Experimental results on the ShapeNet and Pascal 3D+ benchmarks indicate that the proposed Pix2Vox outperforms state-of-the-arts by a large margin. Furthermore, the proposed method is 24 times faster than 3D-R2N2 in terms of backward inference time. The experiments on ShapeNet unseen 3D categories have shown the superior generalization abilities of our method.
http://arxiv.org/abs/1901.11153
This work studies the problem of stochastic dynamic filtering and state propagation with complex beliefs. The main contribution is GP-SUM, a filtering algorithm tailored to dynamic systems and observation models expressed as Gaussian Processes (GP), and to states represented as a weighted sum of Gaussians. The key attribute of GP-SUM is that it does not rely on linearizations of the dynamic or observation models, or on unimodal Gaussian approximations of the belief, hence enables tracking complex state distributions. The algorithm can be seen as a combination of a sampling-based filter with a probabilistic Bayes filter. On the one hand, GP-SUM operates by sampling the state distribution and propagating each sample through the dynamic system and observation models. On the other hand, it achieves effective sampling and accurate probabilistic propagation by relying on the GP form of the system, and the sum-of-Gaussian form of the belief. We show that GP-SUM outperforms several GP-Bayes and Particle Filters on a standard benchmark. We also demonstrate its use in a pushing task, predicting with experimental accuracy the naturally occurring non-Gaussian distributions.
http://arxiv.org/abs/1709.08120
Recent progress in autonomous and semi-autonomous driving has been made possible in part through an assortment of sensors that provide the intelligent agent with an enhanced perception of its surroundings. It has been clear for quite some while now that for intelligent vehicles to function effectively in all situations and conditions, a fusion of different sensor technologies is essential. Consequently, the availability of synchronized multi-sensory data streams are necessary to promote the development of fusion based algorithms for low, mid and high level semantic tasks. In this paper, we provide a comprehensive description of LISA-A: our heavily sensorized, full-surround testbed capable of providing high quality data from a slew of synchronized and calibrated sensors such as cameras, LIDARs, radars, and the IMU/GPS. The vehicle has recorded over 100 hours of real world data for a very diverse set of weather, traffic and daylight conditions. All captured data is accurately calibrated and synchronized using timestamps, and stored safely in high performance servers mounted inside the vehicle itself. Details on the testbed instrumentation, sensor layout, sensor outputs, calibration and synchronization are described in this paper.
http://arxiv.org/abs/1709.07502
The concept of beauty has been debated by philosophists and psychologists for centuries, but most definitions are subjective and metaphysical, and deficit in accuracy, generality, and scalability. In this paper, we present a novel study on mining beauty semantics of facial attributes based on big data, with an attempt to objectively construct descriptions of beauty in a quantitative manner. We first deploy a deep convolutional neural network (CNN) to extract facial attributes, and then investigate correlations between these features and attractiveness on two large-scale datasets labelled with beauty scores. Not only do we discover the secrets of beauty verified by statistical significance tests, our findings also align perfectly with existing psychological studies that, e.g., small nose, high cheekbones, and femininity contribute to attractiveness. We further leverage these high-level representations to original images by a generative adversarial network (GAN). Beauty enhancements after synthesis are visually compelling and statistically convincing verified by a user survey of 10,000 data points.
http://arxiv.org/abs/1902.05380
Recent works have highlighted the strengths of the Transformer architecture for dealing with sequence tasks. At the same time, neural architecture search has advanced to the point where it can outperform human-designed models. The goal of this work is to use architecture search to find a better Transformer architecture. We first construct a large search space inspired by the recent advances in feed-forward sequential models and then run evolutionary architecture search, seeding our initial population with the Transformer. To effectively run this search on the computationally expensive WMT 2014 English-German translation task, we develop the progressive dynamic hurdles method, which allows us to dynamically allocate more resources to more promising candidate models. The architecture found in our experiments - the Evolved Transformer - demonstrates consistent improvement over the Transformer on four well-established language tasks: WMT 2014 English-German, WMT 2014 English-French, WMT 2014 English-Czech and LM1B. At big model size, the Evolved Transformer is twice as efficient as the Transformer in FLOPS without loss in quality. At a much smaller - mobile-friendly - model size of ~7M parameters, the Evolved Transformer outperforms the Transformer by 0.7 BLEU on WMT’14 English-German.
http://arxiv.org/abs/1901.11117
The increasing availability of large institutional and public histopathology image datasets is enabling the searching of these datasets for diagnosis, research, and education. Though these datasets typically have associated metadata such as diagnosis or clinical notes, even carefully curated datasets rarely contain annotations of the location of regions of interest on each image. Because pathology images are extremely large (up to 100,000 pixels in each dimension), further laborious visual search of each image may be needed to find the feature of interest. In this paper, we introduce a deep learning based reverse image search tool for histopathology images: Similar Medical Images Like Yours (SMILY). We assessed SMILY’s ability to retrieve search results in two ways: using pathologist-provided annotations, and via prospective studies where pathologists evaluated the quality of SMILY search results. As a negative control in the second evaluation, pathologists were blinded to whether search results were retrieved by SMILY or randomly. In both types of assessments, SMILY was able to retrieve search results with similar histologic features, organ site, and prostate cancer Gleason grade compared with the original query. SMILY may be a useful general-purpose tool in the pathologist’s arsenal, to improve the efficiency of searching large archives of histopathology images, without the need to develop and implement specific tools for each application.
http://arxiv.org/abs/1901.11112
Most superpixel methods are based on spatial and color measures at the pixel level. Therefore, they can highly fail to group pixels with similar local texture properties, and need fine parameter tuning to balance the two measures. In this paper, we address these issues with a new Texture-Aware SuperPixel (TASP) segmentation method. TASP locally adjusts its spatial regularity constraint according to the feature variance to accurately segment both smooth and textured areas. A new pixel to superpixel patch-based distance is also proposed to ensure texture homogeneity within created regions. TASP substantially outperforms the segmentation accuracy of state-of-the-art methods on both natural color and texture images.
http://arxiv.org/abs/1901.11111
In this paper, we propose a novel approach for saliency detection for seismic applications using 3D-FFT local spectra and multi-dimensional plane projections. We develop a projection scheme by dividing a 3D-FFT local spectrum of a data volume into three distinct components, each depicting changes along a different dimension of the data. The saliency detection results obtained using each projected component are then combined to yield a saliency map. To accommodate the directional nature of seismic data, in this work, we modify the center-surround model, proven to be biologically plausible for visual attention, to incorporate directional comparisons around each voxel in a 3D volume. Experimental results on real seismic dataset from the F3 block in Netherlands offshore in the North Sea prove that the proposed algorithm is effective, efficient, and scalable. Furthermore, a subjective comparison of the results shows that it outperforms the state-of-the-art methods for saliency detection.
http://arxiv.org/abs/1901.11095
We report resolution enhancement in scanning electron microscopy (SEM) images using a generative adversarial network. We demonstrate the veracity of this deep learning-based super-resolution technique by inferring unresolved features in low-resolution SEM images and comparing them with the accurately co-registered high-resolution SEM images of the same samples. Through spatial frequency analysis, we also report that our method generates images with frequency spectra matching higher resolution SEM images of the same fields-of-view. By using this technique, higher resolution SEM images can be taken faster, while also reducing both electron charging and damage to the samples.
http://arxiv.org/abs/1901.11094
Tasks related to human hands have long been part of the computer vision community. Hands being the primary actuators for humans, convey a lot about activities and intents, in addition to being an alternative form of communication/interaction with other humans and machines. In this study, we focus on training a single feedforward convolutional neural network (CNN) capable of executing many hand related tasks that may be of use in autonomous and semi-autonomous vehicles of the future. The resulting network, which we refer to as HandyNet, is capable of detecting, segmenting and localizing (in 3D) driver hands inside a vehicle cabin. The network is additionally trained to identify handheld objects that the driver may be interacting with. To meet the data requirements to train such a network, we propose a method for cheap annotation based on chroma-keying, thereby bypassing weeks of human effort required to label such data. This process can generate thousands of labeled training samples in an efficient manner, and may be replicated in new environments with relative ease.
http://arxiv.org/abs/1804.07834
We present a Deep Differentiable Simplex Layer (DDSL) for neural networks for geometric deep learning. The DDSL is a differentiable layer compatible with deep neural networks for bridging simplex mesh-based geometry representations (point clouds, line mesh, triangular mesh, tetrahedral mesh) with raster images (e.g., 2D/3D grids). The DDSL uses Non-Uniform Fourier Transform (NUFT) to perform differentiable, efficient, anti-aliased rasterization of simplex-based signals. We present a complete theoretical framework for the process as well as an efficient backpropagation algorithm. Compared to previous differentiable renderers and rasterizers, the DDSL generalizes to arbitrary simplex degrees and dimensions. In particular, we explore its applications to 2D shapes and illustrate two applications of this method: (1) mesh editing and optimization guided by neural network outputs, and (2) using DDSL for a differentiable rasterization loss to facilitate end-to-end training of polygon generators. We are able to validate the effectiveness of gradient-based shape optimization with the example of airfoil optimization, and using the differentiable rasterization loss to facilitate end-to-end training, we surpass state of the art for polygonal image segmentation given ground-truth bounding boxes.
http://arxiv.org/abs/1901.11082
Research studies have shown that a large proportion of hazards remain unrecognized, which expose construction workers to unanticipated safety risks. Recent studies have also found that a strong correlation exists between viewing patterns of workers, captured using eye-tracking devices, and their hazard recognition performance. Therefore, it is important to analyze the viewing patterns of workers to gain a better understanding of their hazard recognition performance. This paper proposes a method that can automatically map the gaze fixations collected using a wearable eye-tracker to the predefined areas of interests. The proposed method detects these areas or objects (i.e., hazards) of interests through a computer vision-based segmentation technique and transfer learning. The mapped fixation data is then used to analyze the viewing behaviors of workers and compute their attention distribution. The proposed method is implemented on an under construction road as a case study to evaluate the performance of the proposed method.
http://arxiv.org/abs/1901.11078
The development of machine learning systems for the diagnosis of rare diseases is challenging mainly due the lack of data to study them. Despite this challenge, this paper proposes a system for the Computer Aided Diagnosis (CAD) of low-prevalence, congenital muscular dystrophies from confocal microscopy images. The proposed CAD system relies on a Convolutional Neural Network (CNN) which performs an independent classification for non-overlapping patches tiling the input image, and generates an overall decision summarizing the individual decisions for the patches on the query image. This decision scheme points to the possibly problematic areas in the input images and provides a global quantitative evaluation of the state of the patients, which is fundamental for diagnosis and to monitor the efficiency of therapies.
http://arxiv.org/abs/1901.11074
We introduce a new convolutional layer named the Temporal Gaussian Mixture (TGM) layer and present how it can be used to efficiently capture longer-term temporal information in continuous activity videos. The TGM layer is a temporal convolutional layer governed by a much smaller set of parameters (e.g., location/variance of Gaussians) that are fully differentiable. We present our fully convolutional video models with multiple TGM layers for activity detection. The extensive experiments on multiple datasets, including Charades and MultiTHUMOS, confirm the effectiveness of TGM layers, significantly outperforming the state-of-the-arts.
http://arxiv.org/abs/1803.06316
A grand challenge in reinforcement learning is intelligent exploration, especially when rewards are sparse or deceptive. Two Atari games serve as benchmarks for such hard-exploration domains: Montezuma’s Revenge and Pitfall. On both games, current RL algorithms perform poorly, even those with intrinsic motivation, which is the dominant method to improve performance on hard-exploration domains. To address this shortfall, we introduce a new algorithm called Go-Explore. It exploits the following principles: (1) remember previously visited states, (2) first return to a promising state (without exploration), then explore from it, and (3) solve simulated environments through any available means (including by introducing determinism), then robustify via imitation learning. The combined effect of these principles is a dramatic performance improvement on hard-exploration problems. On Montezuma’s Revenge, Go-Explore scores a mean of over 43k points, almost 4 times the previous state of the art. Go-Explore can also harness human-provided domain knowledge and, when augmented with it, scores a mean of over 650k points on Montezuma’s Revenge. Its max performance of nearly 18 million surpasses the human world record, meeting even the strictest definition of “superhuman” performance. On Pitfall, Go-Explore with domain knowledge is the first algorithm to score above zero. Its mean score of almost 60k points exceeds expert human performance. Because Go-Explore produces high-performing demonstrations automatically and cheaply, it also outperforms imitation learning work where humans provide solution demonstrations. Go-Explore opens up many new research directions into improving it and weaving its insights into current RL algorithms. It may also enable progress on previously unsolvable hard-exploration problems in many domains, especially those that harness a simulator during training (e.g. robotics).
http://arxiv.org/abs/1901.10995
Neural text classification models typically treat output labels as categorical variables which lack description and semantics. This forces their parametrization to be dependent on the label set size, and, hence, they are unable to scale to large label sets and generalize to unseen ones. Existing joint input-label text models overcome these issues by exploiting label descriptions, but they are unable to capture complex label relationships, have rigid parametrization, and their gains on unseen labels happen often at the expense of weak performance on the labels seen during training. In this paper, we propose a new input-label model which generalizes over previous such models, addresses their limitations and does not compromise performance on seen labels. The model consists of a joint non-linear input-label embedding with controllable capacity and a joint-space-dependent classification unit which is trained with cross-entropy loss to optimize classification performance. We evaluate models on full-resource and low- or zero-resource text classification of multilingual news and biomedical text with a large label set. Our model outperforms monolingual and multilingual models which do not leverage label semantics and previous joint input-label space models in both scenarios.
http://arxiv.org/abs/1806.06219
We propose a general framework for denoising high-dimensional measurements which requires no prior on the signal, no estimate of the noise, and no clean training data. The only assumption is that the noise exhibits statistical independence across different dimensions of the measurement. Moreover, our framework is not restricted to a particular denoising model. We show how it can be used to calibrate any parameterised denoising algorithm, from the single hyperparameter of a median filter to the millions of weights of a deep neural network. We demonstrate this on natural image and microscopy data, where we exploit noise independence between pixels, and on single-cell gene expression data, where we exploit independence between detections of individual molecules. Finally, we prove a theoretical lower bound on the performance of an optimal denoiser. This framework generalizes recent work on training neural nets from noisy images and on cross-validation for matrix factorization.
http://arxiv.org/abs/1901.11365
Deep reinforcement learning (RL) algorithms have shown an impressive ability to learn complex control policies in high-dimensional environments. However, despite the ever-increasing performance on popular benchmarks such as the Arcade Learning Environment (ALE), policies learned by deep RL algorithms often struggle to generalize when evaluated in remarkably similar environments. In this paper, we assess the generalization capabilities of DQN, one of the most traditional deep RL algorithms in the field. We provide evidence suggesting that DQN overspecializes to the training environment. We comprehensively evaluate the impact of traditional regularization methods, $\ell_2$-regularization and dropout, and of reusing the learned representations to improve the generalization capabilities of DQN. We perform this study using different game modes of Atari 2600 games, a recently introduced modification for the ALE which supports slight variations of the Atari 2600 games traditionally used for benchmarking. Despite regularization being largely underutilized in deep RL, we show that it can, in fact, help DQN learn more general features. These features can then be reused and fine-tuned on similar tasks, considerably improving the sample efficiency of DQN.
http://arxiv.org/abs/1810.00123
To solve its task, a robot needs to have the ability to interpret its perceptions. In vision, this interpretation is particularly difficult and relies on the understanding of the structure of the scene, at least to the extent of its task and sensorimotor abilities. A robot with the ability to build and adapt this interpretation process according to its own tasks and capabilities would push away the limits of what robots can achieve in a non controlled environment. A solution is to provide the robot with processes to build such representations that are not specific to an environment or a situation. A lot of works focus on objects segmentation, recognition and manipulation. Defining an object solely on the basis of its visual appearance is challenging given the wide range of possible objects and environments. Therefore, current works make simplifying assumptions about the structure of a scene. Such assumptions reduce the adaptivity of the object extraction process to the environments in which the assumption holds. To limit such assumptions, we introduce an exploration method aimed at identifying moveable elements in a scene without considering the concept of object. By using the interactive perception framework, we aim at bootstrapping the acquisition process of a representation of the environment with a minimum of context specific assumptions. The robotic system builds a perceptual map called relevance map which indicates the moveable parts of the current scene. A classifier is trained online to predict the category of each region (moveable or non-moveable). It is also used to select a region with which to interact, with the goal of minimizing the uncertainty of the classification. A specific classifier is introduced to fit these needs: the collaborative mixture models classifier. The method is tested on a set of scenarios of increasing complexity, using both simulations and a PR2 robot.
http://arxiv.org/abs/1901.10968
Traditionally, the P3P problem is solved by firstly transforming its 3 quadratic equations into a quartic one, then by locating the roots of the resulting quartic equation and verifying whether a root does really correspond to a true solution of the P3P problem itself. However, a root of the quartic equation does not always correspond to a solution of the P3P problem. In this work, we show that when the optical center is outside of all the 6 toroids defined by the control point triangle, each positive root of the Grunert’s quartic equation must correspond to a true solution of the P3P problem, and the corresponding P3P problem cannot have a unique solution, it must have either 2 positive solutions or 4 positive solutions. In addition, we show that when the optical center passes through any one of the 3 toroids among these 6 toroids ( except possibly for two concentric circles) , the number of the solutions of the corresponding P3P problem always changes by 1, either increased by 1 or decreased by 1.Furthermore we show that such changed solutions always locate in a small neighborhood of control points, hence the 3 toroids are critical surfaces of the P3P problem and the 3 control points are 3 singular points of solutions. A notable example is that when the optical center passes through the outer surface of the union of the 6 toroids from the outside to inside, the number of the solutions must always decrease by 1. Our results are the first to give an explicit and geometrically intuitive relationship between the P3P solutions and the roots of its quartic equation. It could act as some theoretical guidance for P3P practitioners to properly arrange their control points to avoid undesirable solutions.
http://arxiv.org/abs/1901.11464
The ability to transfer skills across tasks has the potential to scale up reinforcement learning (RL) agents to environments currently out of reach. Recently, a framework based on two ideas, successor features (SFs) and generalised policy improvement (GPI), has been introduced as a principled way of transferring skills. In this paper we extend the SFs & GPI framework in two ways. One of the basic assumptions underlying the original formulation of SFs & GPI is that rewards for all tasks of interest can be computed as linear combinations of a fixed set of features. We relax this constraint and show that the theoretical guarantees supporting the framework can be extended to any set of tasks that only differ in the reward function. Our second contribution is to show that one can use the reward functions themselves as features for future tasks, without any loss of expressiveness, thus removing the need to specify a set of features beforehand. This makes it possible to combine SFs & GPI with deep learning in a more stable way. We empirically verify this claim on a complex 3D environment where observations are images from a first-person perspective. We show that the transfer promoted by SFs & GPI leads to very good policies on unseen tasks almost instantaneously. We also describe how to learn policies specialised to the new tasks in a way that allows them to be added to the agent’s set of skills, and thus be reused in the future.
http://arxiv.org/abs/1901.10964
The binary similarity problem consists in determining if two functions are similar by only considering their compiled form. Advanced techniques for binary similarity recently gained momentum as they can be applied in several fields, such as copyright disputes, malware analysis, vulnerability detection, etc., and thus have an immediate practical impact. Current solutions compare functions by first transforming their binary code in multi-dimensional vector representations (embeddings), and then comparing vectors through simple and efficient geometric operations. However, embeddings are usually derived from binary code using manual feature extraction, that may fail in considering important function characteristics, or may consider features that are not important for the binary similarity problem. In this paper we propose SAFE, a novel architecture for the embedding of functions based on a self-attentive neural network. SAFE works directly on disassembled binary functions, does not require manual feature extraction, is computationally more efficient than existing solutions (i.e., it does not incur in the computational overhead of building or manipulating control flow graphs), and is more general as it works on stripped binaries and on multiple architectures. We report the results from a quantitative and qualitative analysis that show how SAFE provides a noticeable performance improvement with respect to previous solutions. Furthermore, we show how clusters of our embedding vectors are closely related to the semantic of the implemented algorithms, paving the way for further interesting applications (e.g. semantic-based binary function search).
https://arxiv.org/abs/1811.05296
In this paper, we present an analysis of recorded eye-fixation data from human subjects viewing video sequences. The purpose is to better understand visual attention for videos. Utilizing the eye-fixation data provided in the CRCNS (Collaborative Research in Computational Neuroscience) dataset, this paper focuses on the relation between the saliency of a pixel and that of its direct neighbors, without making any assumption about the structure of the eye-fixation maps. By employing some basic concepts from information theory, the analysis shows substantial correlation between the saliency of a pixel and the saliency of its neighborhood. The analysis also provides insights into the structure and dynamics of the eye-fixation maps, which can be very useful in understanding video saliency and its applications.
http://arxiv.org/abs/1901.10957
For autonomous vehicles to be able to operate successfully they need to be aware of other vehicles with sufficient time to make safe, stable plans. Given the possible closing speeds between two vehicles, this necessitates the ability to accurately detect distant vehicles. Many current image-based object detectors using convolutional neural networks exhibit excellent performance on existing datasets such as KITTI. However, the performance of these networks falls when detecting small (distant) objects. We demonstrate that incorporating radar data can boost performance in these difficult situations. We also introduce an efficient automated method for training data generation using cameras of different focal lengths.
http://arxiv.org/abs/1901.10951
Navigation research is attracting renewed interest with the advent of learning-based methods. However, this new line of work is largely disconnected from well-established classic navigation approaches. In this paper, we take a step towards coordinating these two directions of research. We set up classic and learning-based navigation systems in common simulated environments and thoroughly evaluate them in indoor spaces of varying complexity, with access to different sensory modalities. Additionally, we measure human performance in the same environments. We find that a classic pipeline, when properly tuned, can perform very well in complex cluttered environments. On the other hand, learned systems can operate more robustly with a limited sensor suite. Both approaches are still far from human-level performance.
http://arxiv.org/abs/1901.10915
In this paper, we examine several typical texture attributes developed in the image processing community in recent years with respect to their capability of characterizing a migrated seismic volume. These attributes are generated in either frequency or space domain, including steerable pyramid, curvelet, local binary pattern, and local radius index. The comparative study is performed within an image retrieval framework. We evaluate these attributes in terms of retrieval accuracy. It is our hope that this comparative study will help acquaint the seismic interpretation community with the many available powerful image texture analysis techniques, providing more alternative attributes for their seismic exploration.
http://arxiv.org/abs/1901.10909
Transportation systems serve the people in essence, in this study we focus in traffic information related to violation events to respond to safety requirements of the cities. Traffic violation events have an important role in city safety awareness and secure travel. In this work, we describe the use of knowledge discovery from traffic violation reports in combination with demographics approach using inductive logic programming to automatically extract knowledge about traffic violation behavior and their impact on the environment.
http://arxiv.org/abs/1902.06670
Redundancy in deep neural network (DNN) models has always been one of their most intriguing and important properties. DNNs have been shown to overparameterize, or extract a lot of redundant features. In this work, we explore the impact of size (both width and depth), activation function, and weight initialization on the susceptibility of deep neural network models to extract redundant features. To estimate the number of redundant features in each layer, all the features of a given layer are hierarchically clustered according to their relative cosine distances in feature space and a set threshold. It is shown that both network size and activation function are the two most important components that foster the tendency of DNNs to extract redundant features. The concept is illustrated using deep multilayer perceptron and convolutional neural networks on MNIST digits recognition and CIFAR-10 dataset, respectively.
http://arxiv.org/abs/1901.10900
In this paper, we propose a span based model combined with syntactic information for n-ary open information extraction. The advantage of span model is that it can leverage span level features, which is difficult in token based BIO tagging methods. We also improve the previous bootstrap method to construct training corpus. Experiments show that our model outperforms previous open information extraction systems. Our code and data are publicly available at https://github.com/zhanjunlang/Span_OIE
http://arxiv.org/abs/1901.10879
Legged robots have the ability to adapt their walking posture to navigate confined spaces due to their high degrees of freedom. However, this has not been exploited in most common multilegged platforms. This paper presents a deformable bounding box abstraction of the robot model, with accompanying mapping and planning strategies, that enable a legged robot to autonomously change its body shape to navigate confined spaces. The mapping is achieved using robot-centric multi-elevation maps generated with distance sensors carried by the robot. The path planning is based on the trajectory optimisation algorithm CHOMP which creates smooth trajectories while avoiding obstacles. The proposed method has been tested in simulation and implemented on the hexapod robot Weaver, which is 33\,cm tall and 82\,cm wide when walking normally. We demonstrate navigating under 25cm overhanging obstacles, through 70cm wide gaps and over 22cm high obstacles in both artificial testing spaces and realistic environments, including a subterranean mining tunnel.
http://arxiv.org/abs/1901.10863
The recent success of deep networks has significantly advanced 3D human pose estimation from 2D images. The diversity of capturing viewpoints and the flexibility of the human poses, however, remain some significant challenges. In this paper, we propose a view invariant 3D human pose estimation module to alleviate the effects of viewpoint diversity. The framework consists of a base network, which provides an initial estimation of a 3D pose, a view-invariant hierarchical correction network (VI-HC) on top of that to learn the 3D pose refinement under consistent views, and a view-invariant discriminative network (VID) to enforce high-level constraints over body configurations. In VI-HC, the initial 3D pose inputs are automatically transformed to consistent views for further refinements at the global body and local body parts level, respectively. For the VID, under consistent viewpoints, we use adversarial learning to differentiate between estimated poses and real poses to avoid implausible 3D poses. Experimental results demonstrate that the consistent viewpoints can dramatically enhance the performance. Our module shows robustness for different 3D pose base networks and achieves a significant improvement (about 9%) over a powerful baseline on the public 3D pose estimation benchmark Human3.6M.
http://arxiv.org/abs/1901.10841
Fair machine learning concerns the analysis and design of learning algorithms that do not exhibit systematic bias with respect to some sensitive feature (e.g., race, gender). This subject has received sustained interest in the past few years, with considerable progress on both devising sensible measures of fairness, and means of achieving them. Typically, the latter involves correcting one’s learning procedure so that there is no bias on the training sample. However, all such work has operated under the assumption that the sensitive feature available in one’s training sample is perfectly reliable. This assumption may be violated in many real-world cases: for example, respondents to a survey may choose to conceal or obfuscate their group identity out of privacy concerns. This poses the question of whether one can still learn fair classifiers in the presence of such noisy sensitive features. In this paper, we answer the question in the affirmative for a widely-used measure of fairness and model of noise. We show that if one measures fairness using the mean-difference score, and sensitive features are subject to noise from the mutually contaminated learning model, then owing to a simple identity we only need to change the desired fairness-tolerance. The requisite tolerance can be estimated by leveraging existing noise-rate estimators. We finally show that our procedure is empirically effective on two case-studies involving sensitive feature censoring.
http://arxiv.org/abs/1901.10837
The two key players in Generative Adversarial Networks (GANs), the discriminator and generator, are usually parameterized as deep neural networks (DNNs). On many generative tasks, GANs achieve state-of-the-art performance but are often unstable to train and sometimes miss modes. A typical failure mode is the collapse of the generator to a single parameter configuration where its outputs are identical. When this collapse occurs, the gradient of the discriminator may point in similar directions for many similar points. We hypothesize that some of these shortcomings are in part due to primitive and redundant features extracted by discriminator and this can easily make the training stuck. We present a novel approach for regularizing adversarial models by enforcing diverse feature learning. In order to do this, both generator and discriminator are regularized by penalizing both negatively and positively correlated features according to their differentiation and based on their relative cosine distances. In addition to the gradient information from the adversarial loss made available by the discriminator, diversity regularization also ensures that a more stable gradient is provided to update both the generator and discriminator. Results indicate our regularizer enforces diverse features, stabilizes training, and improves image synthesis.
http://arxiv.org/abs/1901.10824
This study investigates the effect of a physical robot taking the role of a teacher or exercise partner in a language learning exercise. In order to investigate this, an application was developed enabling a 2:nd language learning vocabulary exercise in three different conditions. In the first condition the learner would receive tutoring from a disembodied voice, in the second condition the tutor would be embodied by an animated avatar on a computer screen, and in the final condition the tutor was a physical robotic head with a 3D animated face mask. A Russian language vocabulary exercise with 15 subjects was conducted. None of the subjects reported any Russian language skills prior to the exercises. Each subject were taught a set of 9 words in each of the three conditions during a practice phase, and were then asked to recall the words in a test phase. Results show that the recall of the words practiced with the physical robot were significantly higher than that of the words practiced with the avatar on the screen or with the disembodied voice.
http://arxiv.org/abs/1901.10461
In this paper, we studied extensively on different deep learning based methods to detect melanoma and skin lesion cancers. Melanoma, a form of malignant skin cancer is very threatening to health. Proper diagnosis of melanoma at an earlier stage is crucial for the success rate of complete cure. Dermoscopic images with Benign and malignant forms of skin cancer can be analyzed by computer vision system to streamline the process of skin cancer detection. In this study, we experimented with various neural networks which employ recent deep learning based models like PNASNet-5-Large, InceptionResNetV2, SENet154, InceptionV4. Dermoscopic images are properly processed and augmented before feeding them into the network. We tested our methods on International Skin Imaging Collaboration (ISIC) 2018 challenge dataset. Our system has achieved best validation score of 0.76 for PNASNet-5-Large model. Further improvement and optimization of the proposed methods with a bigger training dataset and carefully chosen hyper-parameter could improve the performances. The code available for download at https://github.com/miltonbd/ISIC_2018_classification
http://arxiv.org/abs/1901.10802
“Deep Archetypal Analysis” generates latent representations of high-dimensional datasets in terms of fractions of intuitively understandable basic entities called archetypes. The proposed method is an extension of linear “Archetypal Analysis” (AA), an unsupervised method to represent multivariate data points as sparse convex combinations of extremal elements of the dataset. Unlike the original formulation of AA, “Deep AA” can also handle side information and provides the ability for data-driven representation learning which reduces the dependence on expert knowledge. Our method is motivated by studies of evolutionary trade-offs in biology where archetypes are species highly adapted to a single task. Along these lines, we demonstrate that “Deep AA” also lends itself to the supervised exploration of chemical space, marking a distinct starting point for de novo molecular design. In the unsupervised setting we show how “Deep AA” is used on CelebA to identify archetypal faces. These can then be superimposed in order to generate new faces which inherit dominant traits of the archetypes they are based on.
http://arxiv.org/abs/1901.10799
Blurred Images Lead to Bad Local Minima
http://arxiv.org/abs/1901.10788
The embedding layers transforming input words into real vectors are the key components of deep neural networks used in natural language processing. However, when the vocabulary is large (e.g., 800k unique words in the One-Billion-Word dataset), the corresponding weight matrices can be enormous, which precludes their deployment in a limited resource setting. We introduce a novel way of parametrizing embedding layers based on the Tensor Train (TT) decomposition, which allows compressing the model significantly at the cost of a negligible drop or even a slight gain in performance. Importantly, our method does not take the pre-trained model and compress its weights but rather supplants the standard embedding layers with their TT-based counterparts. The resulting model is then trained end-to-end, however, it can capitalize on larger batches due to the reduced memory requirements. We evaluate our method on a wide range of benchmarks in sentiment analysis, neural machine translation, and language modeling, and analyze the trade-off between performance and compression ratios for a wide range of architectures, from MLPs to LSTMs and Transformers.
http://arxiv.org/abs/1901.10787
Although end-to-end neural text-to-speech (TTS) methods (such as Tacotron2) are proposed and achieve state-of-the-art performance, they still suffer from two problems: 1) low efficiency during training and inference; 2) hard to model long dependency using current recurrent neural networks (RNNs). Inspired by the success of Transformer network in neural machine translation (NMT), in this paper, we introduce and adapt the multi-head attention mechanism to replace the RNN structures and also the original attention mechanism in Tacotron2. With the help of multi-head self-attention, the hidden states in the encoder and decoder are constructed in parallel, which improves the training efficiency. Meanwhile, any two inputs at different times are connected directly by self-attention mechanism, which solves the long range dependency problem effectively. Using phoneme sequences as input, our Transformer TTS network generates mel spectrograms, followed by a WaveNet vocoder to output the final audio results. Experiments are conducted to test the efficiency and performance of our new network. For the efficiency, our Transformer TTS network can speed up the training about 4.25 times faster compared with Tacotron2. For the performance, rigorous human tests show that our proposed model achieves state-of-the-art performance (outperforms Tacotron2 with a gap of 0.048) and is very close to human quality (4.39 vs 4.44 in MOS).
http://arxiv.org/abs/1809.08895
Lighting design in indoor environments is of primary importance for at least two reasons: 1) people should perceive an adequate light; 2) an effective lighting design means consistent energy saving. We present the Invisible Light Switch (ILS) to address both aspects. ILS dynamically adjusts the room illumination level to save energy while maintaining constant the light level perception of the users. So the energy saving is invisible to them. Our proposed ILS leverages a radiosity model to estimate the light level which is perceived by a person within an indoor environment, taking into account the person position and her/his viewing frustum (head pose). ILS may therefore dim those luminaires, which are not seen by the user, resulting in an effective energy saving, especially in large open offices (where light may otherwise be ON everywhere for a single person). To quantify the system performance, we have collected a new dataset where people wear luxmeter devices while working in office rooms. The luxmeters measure the amount of light (in Lux) reaching the people gaze, which we consider a proxy to their illumination level perception. Our initial results are promising: in a room with 8 LED luminaires, the energy consumption in a day may be reduced from 18585 to 6206 watts with ILS (currently needing 1560 watts for operations). While doing so, the drop in perceived lighting decreases by just 200 lux, a value considered negligible when the original illumination level is above 1200 lux, as is normally the case in offices.
http://arxiv.org/abs/1901.10772