With the rapid growing of remotely sensed imagery data, there is a high demand for effective and efficient image retrieval tools to manage and exploit such data. In this letter, we present a novel content-based remote sensing image retrieval method based on Triplet deep metric learning convolutional neural network (CNN). By constructing a Triplet network with metric learning objective function, we extract the representative features of the images in a semantic space in which images from the same class are close to each other while those from different classes are far apart. In such a semantic space, simple metric measures such as Euclidean distance can be used directly to compare the similarity of images and effectively retrieve images of the same class. We also investigate a supervised and an unsupervised learning methods for reducing the dimensionality of the learned semantic features. We present comprehensive experimental results on two publicly available remote sensing image retrieval datasets and show that our method significantly outperforms state-of-the-art.
http://arxiv.org/abs/1902.05818
While there are optimal TSP solvers, as well as recent learning-based approaches, the generalization of the TSP to the Multiple Traveling Salesmen Problem is much less studied. Here, we design a neural network solution that treats the salesmen, cities and depot as three different sets of varying cardinalities. We apply a novel technique that combines elements from recent architectures that were developed for sets, as well as elements from graph networks. Coupled with new constraint enforcing output layers, a dedicated loss, and a search method, our solution is shown to outperform all the meta-heuristics of the leading solver in the field.
https://arxiv.org/abs/1803.09621
We perform unsupervised analysis of image-derived shape and motion features extracted from 3822 cardiac 4D MRIs of the UK Biobank. First, with a feature extraction method previously published based on deep learning models, we extract from each case 9 feature values characterizing both the cardiac shape and motion. Second, a feature selection is performed to remove highly correlated feature pairs. Third, clustering is carried out using a Gaussian mixture model on the selected features. After analysis, we identify two small clusters which probably correspond to two pathological categories. Further confirmation using a trained classification model and dimensionality reduction tools is carried out to support this discovery. Moreover, we examine the differences between the other large clusters and compare our measures with the ground-truth.
http://arxiv.org/abs/1902.05811
In real-world scenarios, the observation data for reinforcement learning with continuous control is commonly noisy and part of it may be dynamically missing over time, which violates the assumption of many current methods developed for this. We addressed the issue within the framework of partially observable Markov Decision Process (POMDP) using a model-based method, in which the transition model is estimated from the incomplete and noisy observations using a newly proposed surrogate loss function with local approximation, while the policy and value function is learned with the help of belief imputation. For the latter purpose, a generative model is constructed and is seamlessly incorporated into the belief updating procedure of POMDP, which enables robust execution even under a significant incompleteness and noise. The effectiveness of the proposed method is verified on a collection of benchmark tasks, showing that our approach outperforms several compared methods under various challenging scenarios.
http://arxiv.org/abs/1902.05795
Neural architecture search has been shown to hold great promise towards the automation of deep learning. However in spite of its potential, neural architecture search remains quite costly. To this point, we propose a novel gradient-based framework for efficient architecture search by sharing information across several tasks. We start by training many model architectures on several related (training) tasks. When a new unseen task is presented, the framework performs architecture inference in order to quickly identify a good candidate architecture, before any model is trained on the new task. At the core of our framework lies a deep value network that can predict the performance of input architectures on a task by utilizing task meta-features and the previous model training experiments performed on related tasks. We adopt a continuous parametrization of the model architecture which allows for efficient gradient-based optimization. Given a new task, an effective architecture is quickly identified by maximizing the estimated performance with respect to the model architecture parameters with simple gradient ascent. It is key to point out that our goal is to achieve reasonable performance at the lowest cost. We provide experimental results showing the effectiveness of the framework despite its high computational efficiency.
https://arxiv.org/abs/1902.05781
High-level driving behavior decision-making is an open-challenging problem for connected vehicle technology, especially in heterogeneous traffic scenarios. In this paper, a deep reinforcement learning based high-level driving behavior decision-making approach is proposed for connected vehicle in heterogeneous traffic situations. The model is composed of three main parts: a data preprocessor that maps hybrid data into a data format called hyper-grid matrix, a two-stream deep neural network that extracts the hidden features, and a deep reinforcement learning network that learns the optimal policy. Moreover, a simulation environment, which includes different heterogeneous traffic scenarios, is built to train and test the proposed method. The results demonstrate that the model has the capability to learn the optimal high-level driving policy such as driving fast through heterogeneous traffic without unnecessary lane changes. Furthermore, two separate models are used to compare with the proposed model, and the performances are analyzed in detail.
http://arxiv.org/abs/1902.05772
With the promising progress of deep neural networks, layer aggregation has been used to fuse information across layers in various fields, such as computer vision and machine translation. However, most of the previous methods combine layers in a static fashion in that their aggregation strategy is independent of specific hidden states. Inspired by recent progress on capsule networks, in this paper we propose to use routing-by-agreement strategies to aggregate layers dynamically. Specifically, the algorithm learns the probability of a part (individual layer representations) assigned to a whole (aggregated representations) in an iterative way and combines parts accordingly. We implement our algorithm on top of the state-of-the-art neural machine translation model TRANSFORMER and conduct experiments on the widely-used WMT14 English-German and WMT17 Chinese-English translation datasets. Experimental results across language pairs show that the proposed approach consistently outperforms the strong baseline model and a representative static aggregation model.
http://arxiv.org/abs/1902.05770
Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the contextual information, which have proven useful for modeling dependencies among neural representations in various natural language tasks. In this work, we focus on improving self-attention networks through capturing the richness of context. To maintain the simplicity and flexibility of the self-attention networks, we propose to contextualize the transformations of the query and key layers, which are used to calculates the relevance between elements. Specifically, we leverage the internal representations that embed both global and deep contexts, thus avoid relying on external resources. Experimental results on WMT14 English-German and WMT17 Chinese-English translation tasks demonstrate the effectiveness and universality of the proposed methods. Furthermore, we conducted extensive analyses to quantity how the context vectors participate in the self-attention model.
http://arxiv.org/abs/1902.05766
The performance of automatic speaker recognition systems degrades when facing distorted speech data containing additive noise and/or reverberation. Statistical uncertainty propagation has been introduced as a promising paradigm to address this challenge. So far, different uncertainty propagation methods have been proposed to compensate noise and reverberation in i-vectors in the context of speaker recognition. They have achieved promising results on small datasets such as YOHO and Wall Street Journal, but little or no improvement on the larger, highly variable NIST Speaker Recognition Evaluation (SRE) corpus. In this paper, we propose a complete uncertainty propagation method, whereby we model the effect of uncertainty both in the computation of unbiased Baum-Welch statistics and in the derivation of the posterior expectation of the i-vector. We conduct experiments on the NIST-SRE corpus mixed with real domestic noise and reverberation from the CHiME-2 corpus and preprocessed by multichannel speech enhancement. The proposed method improves the equal error rate (EER) by 4% relative compared to a conventional i-vector based speaker verification baseline. This is to be compared with previous methods which degrade performance.
http://arxiv.org/abs/1902.05761
Legged robots can outperform wheeled machines for most navigation tasks across unknown and rough terrains. For such tasks, visual feedback is a fundamental asset to provide robots with terrain-awareness. However, robust dynamic locomotion on difficult terrains with real-time performance guarantees remains a challenge. We present here a real-time, dynamic foothold adaptation strategy based on visual feedback. Our method adjusts the landing position of the feet in a fully reactive manner, using only on-board computers and sensors. The correction is computed and executed continuously along the swing phase trajectory of each leg. To efficiently adapt the landing position, we implement a self-supervised foothold classifier based on a Convolutional Neural Network (CNN). Our method results in an up to 200 times faster computation with respect to the full-blown heuristics. Our goal is to react to visual stimuli from the environment, bridging the gap between blind reactive locomotion and purely vision-based planning strategies. We assess the performance of our method on the dynamic quadruped robot HyQ, executing static and dynamic gaits (at speeds up to 0.5 m/s) in both simulated and real scenarios; the benefit of safe foothold adaptation is clearly demonstrated by the overall robot behavior.
http://arxiv.org/abs/1809.09759
In this paper we present an end-to-end deep learning framework to turn images that show dynamic content, such as vehicles or pedestrians, into realistic static frames. This objective encounters two main challenges: detecting all the dynamic objects, and inpainting the static occluded background with plausible imagery. The second problem is approached with a conditional generative adversarial model that, taking as input the original dynamic image and its dynamic/static binary mask, is capable of generating the final static image. The former challenge is addressed by the use of a convolutional network that learns a multi-class semantic segmentation of the image. These generated images can be used for applications such as augmented reality or vision-based robot localization purposes. To validate our approach, we show both qualitative and quantitative comparisons against other state-of-the-art inpainting methods by removing the dynamic objects and hallucinating the static structure behind them. Furthermore, to demonstrate the potential of our results, we carry out pilot experiments that show the benefits of our proposal for visual place recognition.
http://arxiv.org/abs/1809.10239
This paper considers large families of Markov chains (MCs) that are defined over a set of parameters with finite discrete domains. Such families occur in software product lines, planning under partial observability, and sketching of probabilistic programs. Simple questions, like `does at least one family member satisfy a property?’, are NP-hard. We tackle two problems: distinguish family members that satisfy a given quantitative property from those that do not, and determine a family member that satisfies the property optimally, i.e., with the highest probability or reward. We show that combining two well-known techniques, MDP model checking and abstraction refinement, mitigates the computational complexity. Experiments on a broad set of benchmarks show that in many situations, our approach is able to handle families of millions of MCs, providing superior scalability compared to existing solutions.
http://arxiv.org/abs/1902.05727
Collaborative robots are becoming more common on factory floors as well as regular environments, however, their safety still is not a fully solved issue. Collision detection does not always perform as expected and collision avoidance is still an active research area. Collision avoidance works well for fixed robot-camera setups, however, if they are shifted around, Eye-to-Hand calibration becomes invalid making it difficult to accurately run many of the existing collision avoidance algorithms. We approach the problem by presenting a stand-alone system capable of detecting the robot and estimating its position, including individual joints, by using a simple 2D colour image as an input, where no Eye-to-Hand calibration is needed. As an extension of previous work, a two-stage transfer learning approach is used to re-train a multi-objective convolutional neural network (CNN) to allow it to be used with heterogeneous robot arms. Our method is capable of detecting the robot in real-time and new robot types can be added by having significantly smaller training datasets compared to the requirements of a fully trained network. We present data collection approach, the structure of the multi-objective CNN, the two-stage transfer learning training and test results by using real robots from Universal Robots, Kuka, and Franka Emika. Eventually, we analyse possible application areas of our method together with the possible improvements.
http://arxiv.org/abs/1902.05718
This work addresses the outlier removal problem in large-scale global structure-from-motion. In such applications, global outlier removal is very useful to mitigate the deterioration caused by mismatches in the feature point matching step. Unlike existing outlier removal methods, we exploit the structure in multiview geometry problems to propose a dimension reduced formulation, based on which two methods have been developed. The first method considers a convex relaxed $\ell_1$ minimization and is solved by a single linear programming (LP), whilst the second one approximately solves the ideal $\ell_0$ minimization by an iteratively reweighted method. The dimension reduction results in a significant speedup of the new algorithms. Further, the iteratively reweighted method can significantly reduce the possibility of removing true inliers. Realistic multiview reconstruction experiments demonstrated that, compared with state-of-the-art algorithms, the new algorithms are much more efficient and meanwhile can give improved solution. Matlab code for reproducing the results is available at \textit{https://github.com/FWen/OUTLR.git}.
http://arxiv.org/abs/1808.03041
In this paper, we present a novel approach for the task of eXplainable Question Answering (XQA), i.e., generating natural language (NL) explanations for the Visual Question Answering (VQA) problem. We generate NL explanations comprising of the evidence to support the answer to a question asked to an image using two sources of information: (a) annotations of entities in an image (e.g., object labels, region descriptions, relation phrases) generated from the scene graph of the image, and (b) the attention map generated by a VQA model when answering the question. We show how combining the visual attention map with the NL representation of relevant scene graph entities, carefully selected using a language model, can give reasonable textual explanations without the need of any additional collected data (explanation captions, etc). We run our algorithms on the Visual Genome (VG) dataset and conduct internal user-studies to demonstrate the efficacy of our approach over a strong baseline. We have also released a live web demo showcasing our VQA and textual explanation generation using scene graphs and visual attention.
http://arxiv.org/abs/1902.05715
Many optimization problems admit a number of local optima, among which there is the global optimum. For these problems, various heuristic optimization methods have been proposed. Comparing the results of these solvers requires the definition of suitable metrics. In the electrical energy systems literature, simple metrics such as best value obtained, the mean value, the median or the standard deviation of the solutions are still used. However, the comparisons carried out with these metrics are rather weak, and on these bases a somehow uncontrolled proliferation of heuristic solvers is taking place. This paper addresses the overall issue of understanding the reasons of this proliferation, showing a conceptual scheme that indicates how the assessment of the best solver may result in the unlimited formulation of new solvers. Moreover, this paper shows how the use of more refined metrics defined to compare the optimization result, associated with the definition of appropriate benchmarks, may make the comparisons among the solvers more robust. The proposed metrics are based on the concept of first-order stochastic dominance and are defined for the cases in which: (i) the globally optimal solution can be found (for testing purposes); and (ii) the number of possible solutions is so large that practically it cannot be guaranteed that the global optimum has been found. Illustrative examples are provided for a typical problem in the electrical energy systems area-distribution network reconfiguration. The conceptual results obtained are generally valid to compare the results of other optimization problems.
http://arxiv.org/abs/1810.02196
Today’s robotic systems are increasingly turning to computationally expensive models such as deep neural networks (DNNs) for tasks like localization, perception, planning, and object detection. However, resource-constrained robots, like low-power drones, often have insufficient on-board compute resources or power reserves to scalably run the most accurate, state-of-the art neural network compute models. Cloud robotics allows mobile robots the benefit of offloading compute to centralized servers if they are uncertain locally or want to run more accurate, compute-intensive models. However, cloud robotics comes with a key, often understated cost: communicating with the cloud over congested wireless networks may result in latency or loss of data. In fact, sending high data-rate video or LIDAR from multiple robots over congested networks can lead to prohibitive delay for real-time applications, which we measure experimentally. In this paper, we formulate a novel Robot Offloading Problem — how and when should robots offload sensing tasks, especially if they are uncertain, to improve accuracy while minimizing the cost of cloud communication? We formulate offloading as a sequential decision making problem for robots, and propose a solution using deep reinforcement learning. In both simulations and hardware experiments using state-of-the art vision DNNs, our offloading strategy improves vision task performance by between 1.3-2.6x of benchmark offloading strategies, allowing robots the potential to significantly transcend their on-board sensing accuracy but with limited cost of cloud communication.
http://arxiv.org/abs/1902.05703
A 3D flexible bin packing problem (3D-FBPP) arises from the process of warehouse packing in e-commerce. An online customer’s order usually contains several items and needs to be packed as a whole before shipping. In particular, 5% of tens of millions of packages are using plastic wrapping as outer packaging every day, which brings pressure on the plastic surface minimization to save traditional logistics costs. Because of the huge practical significance, we focus on the issue of packing cuboid-shaped items orthogonally into a least-surface-area bin. The existing heuristic methods for classic 3D bin packing don’t work well for this particular NP-hard problem and designing a good problem-specific heuristic is non-trivial. In this paper, rather than designing heuristics, we propose a novel multi-task framework based on Selected Learning to learn a heuristic-like policy that generates the sequence and orientations of items to be packed simultaneously. Through comprehensive experiments on a large scale real-world transaction order dataset and online AB tests, we show: 1) our selected learning method trades off the imbalance and correlation among the tasks and significantly outperforms the single task Pointer Network and the multi-task network without selected learning; 2) our method obtains an average 5.47% cost reduction than the well-designed greedy algorithm which is previously used in our online production system.
http://arxiv.org/abs/1804.06896
Decision-making under uncertainty is a crucial ability for autonomous systems. In its most general form, this problem can be formulated as a Partially Observable Markov Decision Process (POMDP). The solution policy of a POMDP can be implicitly encoded as a value function. In partially observable settings, the value function is typically learned via forward simulation of the system evolution. Focusing on accurate and long-range risk assessment, we propose a novel method, where the value function is learned in different phases via a bi-directional search in belief space. A backward value learning process provides a long-range and risk-aware base policy. A forward value learning process ensures local optimality and updates the policy via forward simulations. We consider a class of scalable and continuous-space rover navigation problems (RNP) to assess the safety, scalability, and optimality of the proposed algorithm. The results demonstrate the capabilities of the proposed algorithm in evaluating long-range risk/safety of the planner while addressing continuous problems with long planning horizons.
http://arxiv.org/abs/1902.05698
Single image super-resolution(SISR) has witnessed great progress as convolutional neural network(CNN) gets deeper and wider. However, enormous parameters hinder its application to real world problems. In this letter, We propose a lightweight feature fusion network (LFFN) that can fully explore multi-scale contextual information and greatly reduce network parameters while maximizing SISR results. LFFN is built on spindle blocks and a softmax feature fusion module (SFFM). Specifically, a spindle block is composed of a dimension extension unit, a feature exploration unit and a feature refinement unit. The dimension extension layer expands low dimension to high dimension and implicitly learns the feature maps which is suitable for the next unit. The feature exploration unit performs linear and nonlinear feature exploration aimed at different feature maps. The feature refinement layer is used to fuse and refine features. SFFM fuses the features from different modules in a self-adaptive learning manner with softmax function, making full use of hierarchical information with a small amount of parameter cost. Both qualitative and quantitative experiments on benchmark datasets show that LFFN achieves favorable performance against state-of-the-art methods with similar parameters.
http://arxiv.org/abs/1902.05694
In this paper we study the convergence of generative adversarial networks (GANs) from the perspective of the informativeness of the gradient of the optimal discriminative function. We show that GANs without restriction on the discriminative function space commonly suffer from the problem that the gradient produced by the discriminator is uninformative to guide the generator. By contrast, Wasserstein GAN (WGAN), where the discriminative function is restricted to $1$-Lipschitz, does not suffer from such a gradient uninformativeness problem. We further show in the paper that the model with a compact dual form of Wasserstein distance, where the Lipschitz condition is relaxed, also suffers from this issue. This implies the importance of Lipschitz condition and motivates us to study the general formulation of GANs with Lipschitz constraint, which leads to a new family of GANs that we call Lipschitz GANs (LGANs). We show that LGANs guarantee the existence and uniqueness of the optimal discriminative function as well as the existence of a unique Nash equilibrium. We prove that LGANs are generally capable of eliminating the gradient uninformativeness problem. According to our empirical analysis, LGANs are more stable and generate consistently higher quality samples compared with WGAN.
http://arxiv.org/abs/1902.05687
PRAM puts agent-based models on a sound probabilistic footing as a basis for integrating agent-based and probabilistic models. It extends the themes of probabilistic relational models and lifted inference to incorporate dynamical models and simulation. It can also be much more efficient than agent-based simulation.
http://arxiv.org/abs/1902.05677
Light-field cameras (LFC) have received increasing attention due to their wide-spread applications. However, current LFCs suffer from the well-known spatio-angular trade-off, which is considered as an inherent and fundamental limit for LFC designs. In this paper, by doing a detailed geometrical optical analysis of the sampling process in an LFC, we show that the effective sampling resolution is generally higher than the number of micro-lenses. This contribution makes it theoretically possible to break the resolution trade-off. Our second contribution is an epipolar plane image (EPI) based super-resolution method, which can super-resolve the spatial and angular dimensions simultaneously. We prove that the light field is a 2D series, thus, a specifically designed CNN-LSTM network is proposed to capture the continuity property of the EPI. Rather than leveraging semantic information, our network focuses on extracting geometric continuity in the EPI. This gives our method an improved generalization ability and makes it applicable to a wide range of previously unseen scenes. Experiments on both synthetic and real light fields demonstrate the improvements over state-of-the-art, especially in large disparity areas.
http://arxiv.org/abs/1902.05672
Despite significant progress in Visual Question Answering over the years, robustness of today’s VQA models leave much to be desired. We introduce a new evaluation protocol and associated dataset (VQA-Rephrasings) and show that state-of-the-art VQA models are notoriously brittle to linguistic variations in questions. VQA-Rephrasings contains 3 human-provided rephrasings for 40k questions spanning 40k images from the VQA v2.0 validation dataset. As a step towards improving robustness of VQA models, we propose a model-agnostic framework that exploits cycle consistency. Specifically, we train a model to not only answer a question, but also generate a question conditioned on the answer, such that the answer predicted for the generated question is the same as the ground truth answer to the original question. Without the use of additional annotations, we show that our approach is significantly more robust to linguistic variations than state-of-the-art VQA models, when evaluated on the VQA-Rephrasings dataset. In addition, our approach outperforms state-of-the-art approaches on the standard VQA and Visual Question Generation tasks on the challenging VQA v2.0 dataset.
http://arxiv.org/abs/1902.05660
We tackle the problem of graph partitioning for image segmentation using correlation clustering (CC), which we treat as an integer linear program (ILP). We reformulate optimization in the ILP so as to admit efficient optimization via Benders decomposition, a classic technique from operations research. Our Benders decomposition formulation has many subproblems, each associated with a node in the CC instance’s graph, which are solved in parallel. Each Benders subproblem enforces the cycle inequalities corresponding to the negative weight edges attached to its corresponding node in the CC instance. We generate Magnanti-Wong Benders rows in addition to standard Benders rows, to accelerate optimization. Our Benders decomposition approach provides a promising new avenue to accelerate optimization for CC, and allows for massive parallelization.
http://arxiv.org/abs/1902.05659
Analyzing video for traffic categorization is an important pillar of Intelligent Transport Systems. However, it is difficult to analyze and predict traffic based on image frames because the representation of each frame may vary significantly within a short time period. This also would inaccurately represent the traffic over a longer period of time such as the case of video. We propose a novel bio-inspired methodology that integrates analysis of the previous image frames of the video to represent the analysis of the current image frame, the same way a human being analyzes the current situation based on past experience. In our proposed methodology, called IRON-MAN (Integrated Rational prediction and Motionless textbfANalysis), we utilize Bayesian update on top of the individual image frame analysis in the videos and this has resulted in highly accurate prediction of Temporal Motionless Analysis of the Videos (TMAV) for most of the chosen test cases. The proposed approach could be used for TMAV using Convolutional Neural Network (CNN) for applications where the number of objects in an image is the deciding factor for prediction and results also show that our proposed approach outperforms the state-of-the-art for the chosen test case. We also introduce a new metric named, Energy Consumption per Training Image (ECTI). Since, different CNN based models have different training capability and computing resource utilization, some of the models are more suitable for embedded device implementation than the others, and ECTI metric is useful to assess the suitability of using a CNN model in multi-processor systems-on-chips (MPSoCs) with a focus on energy consumption and reliability in terms of lifespan of the embedded device using these MPSoCs.
http://arxiv.org/abs/1902.05657
Medical Image Analysis is currently experiencing a paradigm shift due to Deep Learning. This technology has recently attracted so much interest of the Medical Imaging community that it led to a specialized conference in Medical Imaging with Deep Learning' in the year 2018. This article surveys the recent developments in this direction, and provides a critical review of the related major aspects. We organize the reviewed literature according to the underlying Pattern Recognition tasks, and further sub-categorize it following a taxonomy based on human anatomy. This article does not assume prior knowledge of Deep Learning and makes a significant contribution in explaining the core Deep Learning concepts to the non-experts in the Medical community. Unique to this study is the Computer Vision/Machine Learning perspective taken on the advances of Deep Learning in Medical Imaging. This enables us to single out lack of appropriately annotated large-scale datasets’ as the core challenge (among other challenges) in this research direction. We draw on the insights from the sister research fields of Computer Vision, Pattern Recognition and Machine Learning etc.; where the techniques of dealing with such challenges have already matured, to provide promising directions for the Medical Imaging community to fully harness Deep Learning in the future.
http://arxiv.org/abs/1902.05655
We pose an active perception problem where an autonomous agent actively interacts with a second agent with potentially adversarial behaviors. Given the uncertainty in the intent of the other agent, the objective is to collect further evidence to help discriminate potential threats. The main technical challenges are the partial observability of the agent intent, the adversary modeling, and the corresponding uncertainty modeling. Note that an adversary agent may act to mislead the autonomous agent by using a deceptive strategy that is learned from past experiences. We propose an approach that combines belief space planning, generative adversary modeling, and maximum entropy reinforcement learning to obtain a stochastic belief space policy. By accounting for various adversarial behaviors in the simulation framework and minimizing the predictability of the autonomous agent’s action, the resulting policy is more robust to unmodeled adversarial strategies. This improved robustness is empirically shown against an adversary that adapts to and exploits the autonomous agent’s policy when compared with a standard Chance-Constraint Partially Observable Markov Decision Process robust approach.
http://arxiv.org/abs/1902.05644
The desire to use reinforcement learning in safety-critical settings has inspired a recent interest in formal methods for learning algorithms. Existing formal methods for learning and optimization primarily consider the problem of constrained learning or constrained optimization. Given a single correct model and associated safety constraint, these approaches guarantee efficient learning while provably avoiding behaviors outside the safety constraint. Acting well given an accurate environmental model is an important pre-requisite for safe learning, but is ultimately insufficient for systems that operate in complex heterogeneous environments. This paper introduces verification-preserving model updates, the first approach toward obtaining formal safety guarantees for reinforcement learning in settings where multiple environmental models must be taken into account. Through a combination of design-time model updates and runtime model falsification, we provide a first approach toward obtaining formal safety proofs for autonomous systems acting in heterogeneous environments.
http://arxiv.org/abs/1902.05632
In the recent years Generative Adversarial Networks (GANs) have demonstrated significant progress in generating authentic looking data. In this work we introduce our simple method to exploit the advancements in well established image-based GANs to synthesise single channel time series data. We implement Wasserstein GANs (WGANs) with gradient penalty due to their stability in training to synthesise three different types of data; sinusoidal data, photoplethysmograph (PPG) data and electrocardiograph (ECG) data. The length of the returned time series data is limited only by the image resolution, we use an image size of 64x64 pixels which yields 4096 data points. We present both visual and quantitative evidence that our novel method can successfully generate time series data using image-based GANs.
https://arxiv.org/abs/1902.05624
Automatically generating maps from satellite images is an important task. There is a body of literature which tries to address this challenge. We created a more expansive survey of the task by experimenting with different models and adding new loss functions to improve results. We created a database of pairs of satellite images and the corresponding map of the area. Our model translates the satellite image to the corresponding standard layer map image using three main model architectures: (i) a conditional Generative Adversarial Network (GAN) which compresses the images down to a learned embedding, (ii) a generator which is trained as a normalizing flow (RealNVP) model, and (iii) a conditional GAN where the generator translates via a series of convolutions to the standard layer of a map and the discriminator input is the concatenation of the real/generated map and the satellite image. Model (iii) was by far the most promising of three models. To improve the results we also added a reconstruction loss and style transfer loss in addition to the GAN losses. The third model architecture produced the best quality of sampled images. In contrast to the other generative model where evaluation of the model is a challenging problem. since we have access to the real map for a given satellite image, we are able to assign a quantitative metric to the quality of the generated images in addition to inspecting them visually. While we are continuing to work on increasing the accuracy of the model, one challenge has been the coarse resolution of the data which upper-bounds the quality of the results of our model. Nevertheless, as will be seen in the results, the generated map is more accurate in the features it produces since the generator architecture demands a pixel-wise image translation/pixel-wise coloring. A video presentation summarizing this paper is available at: https://youtu.be/Ur0flOX-Ji0
http://arxiv.org/abs/1902.05611
Video object segmentation is an essential task in robot manipulation to facilitate grasping and learning affordances. Incremental learning is important for robotics in unstructured environments, since the total number of objects and their variations can be intractable. Inspired by the children learning process, human robot interaction (HRI) can be utilized to teach robots about the world guided by humans similar to how children learn from a parent or a teacher. A human teacher can show potential objects of interest to the robot, which is able to self adapt to the teaching signal without providing manual segmentation labels. We propose a novel teacher-student learning paradigm to teach robots about their surrounding environment. A two-stream motion and appearance teacher network provides pseudo-labels to adapt an appearance student network. The student network is able to segment the newly learned objects in other scenes, whether they are static or in motion. We also introduce a carefully designed dataset that serves the proposed HRI setup, denoted as (I)nteractive (V)ideo (O)bject (S)egmentation. Our IVOS dataset contains teaching videos of different objects, and manipulation tasks. Unlike previous datasets, IVOS provides manipulation tasks sequences with segmentation annotation along with the waypoints for the robot trajectories. It also provides segmentation annotation for the different transformations such as translation, scale, planar rotation, and out-of-plane rotation. Our proposed adaptation method outperforms the state-of-the-art on DAVIS and FBMS with 6.8% and 1.2% in F-measure respectively. It improves over the baseline on IVOS dataset with 46.1% and 25.9% in mIoU.
http://arxiv.org/abs/1810.07733
We draw upon a previously largely untapped literature on human collective intelligence as a source of inspiration for improving deep learning. Implicit in many algorithms that attempt to solve Deep Reinforcement Learning (DRL) tasks is the network of processors along which parameter values are shared. So far, existing approaches have implicitly utilized fully-connected networks, in which all processors are connected. However, the scientific literature on human collective intelligence suggests that complete networks may not always be the most effective information network structures for distributed search through complex spaces. Here we show that alternative topologies can improve deep neural network training: we find that sparser networks learn higher rewards faster, leading to learning improvements at lower communication costs.
http://arxiv.org/abs/1711.11180
Convolutional Neural Networks and Deep Learning classification systems in general have been shown to be vulnerable to attack by specially crafted data samples that appear to belong to one class but are instead classified as another, commonly known as adversarial examples. A variety of attack strategies have been proposed to craft these samples; however, there is no standard model that is used to compare the success of each type of attack. Furthermore, there is no literature currently available that evaluates how common hyperparameters and optimization strategies may impact a model’s ability to resist these samples. This research bridges that lack of awareness and provides a means for the selection of training and model parameters in future research on evasion attacks against convolutional neural networks. The findings of this work indicate that the selection of model hyperparameters does impact the ability of a model to resist attack, although they alone cannot prevent the existence of adversarial examples.
http://arxiv.org/abs/1902.05586
The rapid growth of social media in recent years has fed into some highly undesirable phenomena such as proliferation of abusive and offensive language on the Internet. Previous research suggests that such hateful content tends to come from users who share a set of common stereotypes and form communities around them. The current state-of-the-art approaches to hate speech detection are oblivious to user and community information and rely entirely on textual (i.e., lexical and semantic) cues. In this paper, we propose a novel approach to this problem that incorporates community-based profiling features of Twitter users. Experimenting with a dataset of 16k tweets, we show that our methods significantly outperform the current state of the art in hate speech detection. Further, we conduct a qualitative analysis of model characteristics. We release our code, pre-trained models and all the resources used in the public domain.
http://arxiv.org/abs/1902.06734
Fast and accurate catheter detection in cardiac catheterization using harmless 3D ultrasound (US) can improve the efficiency and outcome of the intervention. However, the low image quality of US requires extra training for sonographers to localize the catheter. In this paper, we propose a catheter detection method based on a pre-trained VGG network, which exploits 3D information through re-organized cross-sections to segment the catheter by a shared fully convolutional network (FCN), which is called a Direction-Fused FCN (DF-FCN). Based on the segmented image of DF-FCN, the catheter can be localized by model fitting. Our experiments show that the proposed method can successfully detect an ablation catheter in a challenging ex-vivo 3D US dataset, which was collected on the porcine heart. Extensive analysis shows that the proposed method achieves a Dice score of 57.7%, which offers at least an 11.8 % improvement when compared to state-of-the-art instrument detection methods. Due to the improved segmentation performance by the DF-FCN, the catheter can be localized with an error of only 1.4 mm.
http://arxiv.org/abs/1902.05582
Regularized autoencoders learn the latent codes, a structure with the regularization under the distribution, which enables them the capability to infer the latent codes given observations and generate new samples given the codes. However, they are sometimes ambiguous as they tend to produce reconstructions that are not necessarily faithful reproduction of the inputs. The main reason is to enforce the learned latent code distribution to match a prior distribution while the true distribution remains unknown. To improve the reconstruction quality and learn the latent space a manifold structure, this work present a novel approach using the adversarially approximated autoencoder (AAAE) to investigate the latent codes with adversarial approximation. Instead of regularizing the latent codes by penalizing on the distance between the distributions of the model and the target, AAAE learns the autoencoder flexibly and approximates the latent space with a simpler generator. The ratio is estimated using generative adversarial network (GAN) to enforce the similarity of the distributions. Additionally, the image space is regularized with an additional adversarial regularizer. The proposed approach unifies two deep generative models for both latent space inference and diverse generation. The learning scheme is realized without regularization on the latent codes, which also encourages faithful reconstruction. Extensive validation experiments on four real-world datasets demonstrate the superior performance of AAAE. In comparison to the state-of-the-art approaches, AAAE generates samples with better quality and shares the properties of regularized autoencoder with a nice latent manifold structure.
http://arxiv.org/abs/1902.05581
Optimal surface segmentation is a state-of-the-art method used for segmentation of multiple globally optimal surfaces in volumetric datasets. The method is widely used in numerous medical image segmentation applications. However, nodes in the graph based optimal surface segmentation method typically encode uniformly distributed orthogonal voxels of the volume. Thus the segmentation cannot attain an accuracy greater than a single unit voxel, i.e. the distance between two adjoining nodes in graph space. Segmentation accuracy higher than a unit voxel is achievable by exploiting partial volume information in the voxels which shall result in non-equidistant spacing between adjoining graph nodes. This paper reports a generalized graph based multiple surface segmentation method with convex priors which can optimally segment the target surfaces in an irregularly sampled space. The proposed method allows non-equidistant spacing between the adjoining graph nodes to achieve subvoxel segmentation accuracy by utilizing the partial volume information in the voxels. The partial volume information in the voxels is exploited by computing a displacement field from the original volume data to identify the subvoxel-accurate centers within each voxel resulting in non-equidistant spacing between the adjoining graph nodes. The smoothness of each surface modeled as a convex constraint governs the connectivity and regularity of the surface. We employ an edge-based graph representation to incorporate the necessary constraints and the globally optimal solution is obtained by computing a minimum s-t cut. The proposed method was validated on 10 intravascular multi-frame ultrasound image datasets for subvoxel segmentation accuracy. In all cases, the approach yielded highly accurate results. Our approach can be readily extended to higher-dimensional segmentations.
http://arxiv.org/abs/1611.03059
The computer vision literature shows that randomly weighted neural networks perform reasonably as feature extractors. Following this idea, we study how non-trained (randomly weighted) convolutional neural networks perform as feature extractors for (music) audio classification tasks. We use features extracted from the embeddings of deep architectures as input to a classifier - with the goal to compare classification accuracies when using different randomly weighted architectures. By following this methodology, we run a comprehensive evaluation of the current deep architectures for audio classification, and provide evidence that the architectures alone are an important piece for resolving (music) audio problems using deep neural networks.
http://arxiv.org/abs/1805.00237
Contemporary sensorimotor learning approaches typically start with an existing complex agent (e.g., a robotic arm), which they learn to control. In contrast, this paper investigates a modular co-evolution strategy: a collection of primitive agents learns to dynamically self-assemble into composite bodies while also learning to coordinate their behavior to control these bodies. Each primitive agent consists of a limb with a motor attached at one end. Limbs may choose to link up to form collectives. When a limb initiates a link-up action and there is another limb nearby, the latter is magnetically connected to the ‘parent’ limb’s motor. This forms a new single agent, which may further link with other agents. In this way, complex morphologies can emerge, controlled by a policy whose architecture is in explicit correspondence with the morphology. We evaluate the performance of these ‘dynamic’ and ‘modular’ agents in simulated environments. We demonstrate better generalization to test-time changes both in the environment, as well as in the agent morphology, compared to static and monolithic baselines. Project videos and code are available at https://pathak22.github.io/modular-assemblies/
http://arxiv.org/abs/1902.05546
While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where aspects of the environment needed to compute progress are not directly accessible. To enable robots to autonomously learn skills, we instead consider the problem of reinforcement learning without access to rewards. We aim to learn an unsupervised embedding space under which the robot can measure progress towards a goal for itself. Our approach explicitly optimizes for a metric space under which action sequences that reach a particular state are optimal when the goal is the final state reached. This enables learning effective and control-centric representations that lead to more autonomous reinforcement learning algorithms. Our experiments on three simulated environments and two real-world manipulation problems show that our method can learn effective goal metrics from unlabeled interaction, and use the learned goal metrics for autonomous reinforcement learning.
http://arxiv.org/abs/1902.05542
Endmember (EM) spectral variability can greatly impact the performance of standard hyperspectral image analysis algorithms. Extended parametric models have been successfully applied to account for the EM spectral variability. However, these models still lack the compromise between flexibility and low-dimensional representation that is necessary to properly explore the fact that spectral variability is often confined to a low-dimensional manifold in real scenes. In this paper we propose to learn a spectral variability model directly form the observed data, instead of imposing it \emph{a priori}. This is achieved through a deep generative EM model, which is estimated using a variational autoencoder (VAE). The encoder and decoder that compose the generative model are trained using pure pixel information extracted directly from the observed image, what allows for an unsupervised formulation. The proposed EM model is applied to the solution of a spectral unmixing problem, which we cast as an alternating nonlinear least-squares problem that is solved iteratively with respect to the abundances and to the low-dimensional representations of the EMs in the latent space of the deep generative model. Simulations using both synthetic and real data indicate that the proposed strategy can outperform the competing state-of-the-art algorithms.
http://arxiv.org/abs/1902.05528
We present a method for storing multiple models within a single set of parameters. Models can coexist in superposition and still be retrieved individually. In experiments with neural networks, we show that a surprisingly large number of models can be effectively stored within a single parameter instance. Furthermore, each of these models can undergo thousands of training steps without significantly interfering with other models within the superposition. This approach may be viewed as the online complement of compression: rather than reducing the size of a network after training, we make use of the unrealized capacity of a network during training.
http://arxiv.org/abs/1902.05522
MultiGrain is a network architecture producing compact vector representations that are suited both for image classification and particular object retrieval. It builds on a standard classification trunk. The top of the network produces an embedding containing coarse and fine-grained information, so that images can be recognized based on the object class, particular object, or if they are distorted copies. Our joint training is simple: we minimize a cross-entropy loss for classification and a ranking loss that determines if two images are identical up to data augmentation, with no need for additional labels. A key component of MultiGrain is a pooling layer that allow us to take advantage of high-resolution images with a network trained at a lower resolution. When fed to a linear classifier, the learned embeddings provide state-of-the-art classification accuracy. For instance, we obtain 79.3% top-1 accuracy with a ResNet-50 learned on Imagenet, which is a +1.7% absolute improvement over the AutoAugment method. When compared with the cosine similarity, the same embeddings perform on par with the state-of-the-art for image retrieval at moderate resolutions.
http://arxiv.org/abs/1902.05509
Zero-shot learning (ZSL) is one of the most extreme forms of learning from scarce labeled data. It enables predicting that images belong to classes for which no labeled training instances are available. In this paper, we present a new ZSL framework that leverages both label attribute side information and a semantic label hierarchy. We present two methods, lifted zero-shot prediction and a custom conditional random field (CRF) model, that integrate both forms of side information. We propose benchmark tasks for this framework that focus on making predictions across a range of semantic levels. We show that lifted zero-shot prediction can dramatically outperform baseline methods when making predictions within specified semantic levels, and that the probability distribution provided by the CRF model can be leveraged to yield further performance improvements when making unconstrained predictions over the hierarchy.
http://arxiv.org/abs/1902.05492
Temporal action localization is an important task of computer vision. Though many methods have been proposed, it still remains an open question how to predict the temporal location of action segments precisely. Most state-of-the-art works train action classifiers on video segments pre-determined by action proposal. However, recent work found that a desirable model should move beyond segment-level and make dense predictions at a fine granularity in time to determine precise temporal boundaries. In this paper, we propose a Frame Segmentation Network (FSN) that places a temporal CNN on top of the 2D spatial CNNs. Spatial CNNs are responsible for abstracting semantics in spatial dimension while temporal CNN is responsible for introducing temporal context information and performing dense predictions. The proposed FSN can make dense predictions at frame-level for a video clip using both spatial and temporal context information. FSN is trained in an end-to-end manner, so the model can be optimized in spatial and temporal domain jointly. We also adapt FSN to use it in weakly supervised scenario (WFSN), where only video level labels are provided when training. Experiment results on public dataset show that FSN achieves superior performance in both frame-level action localization and temporal action localization.
http://arxiv.org/abs/1902.05488
We design and study a Contextual Memory Tree (CMT), a learning memory controller that inserts new memories into an experience store of unbounded size. It is designed to efficiently query for memories from that store, supporting logarithmic time insertion and retrieval operations. Hence CMT can be integrated into existing statistical learning algorithms as an augmented memory unit without substantially increasing training and inference computation. Furthermore CMT operates as a reduction to classification, allowing it to benefit from advances in representation or architecture. We demonstrate the efficacy of CMT by augmenting existing multi-class and multi-label classification algorithms with CMT and observe statistical improvement. We also test CMT learning on several image-captioning tasks to demonstrate that it performs computationally better than a simple nearest neighbors memory system while benefitting from reward learning.
https://arxiv.org/abs/1807.06473
Surveillance videos are able to capture a variety of realistic anomalies. In this paper, we propose to learn anomalies by exploiting both normal and anomalous videos. To avoid annotating the anomalous segments or clips in training videos, which is very time consuming, we propose to learn anomaly through the deep multiple instance ranking framework by leveraging weakly labeled training videos, i.e. the training labels (anomalous or normal) are at video-level instead of clip-level. In our approach, we consider normal and anomalous videos as bags and video segments as instances in multiple instance learning (MIL), and automatically learn a deep anomaly ranking model that predicts high anomaly scores for anomalous video segments. Furthermore, we introduce sparsity and temporal smoothness constraints in the ranking loss function to better localize anomaly during training. We also introduce a new large-scale first of its kind dataset of 128 hours of videos. It consists of 1900 long and untrimmed real-world surveillance videos, with 13 realistic anomalies such as fighting, road accident, burglary, robbery, etc. as well as normal activities. This dataset can be used for two tasks. First, general anomaly detection considering all anomalies in one group and all normal activities in another group. Second, for recognizing each of 13 anomalous activities. Our experimental results show that our MIL method for anomaly detection achieves significant improvement on anomaly detection performance as compared to the state-of-the-art approaches. We provide the results of several recent deep learning baselines on anomalous activity recognition. The low recognition performance of these baselines reveals that our dataset is very challenging and opens more opportunities for future work. The dataset is available at: https://webpages.uncc.edu/cchen62/dataset.html
http://arxiv.org/abs/1801.04264
The development of robotic-assisted extracorporeal ultrasound systems has a long history and a number of projects have been proposed since the 1990s focusing on different technical aspects. These aim to resolve the deficiencies of on-site manual manipulation of hand-held ultrasound probes. This paper presents the recent ongoing developments of a series of bespoke robotic systems, including both single-arm and dual-arm versions, for a project known as intelligent Fetal Imaging and Diagnosis (iFIND). After a brief review of the development history of the extracorporeal ultrasound robotic system used for fetal and abdominal examinations, the specific aim of the iFIND robots, the design evolution, the implementation details of each version, and the initial clinical feedback of the iFIND robot series are presented. Based on the preliminary testing of these newly-proposed robots on 30 volunteers, the successful and re-liable working of the mechatronic systems were validated. Analysis of a participant questionnaire indicates a comfortable scanning experience for the volunteers and a good acceptance rate to being scanned by the robots.
http://arxiv.org/abs/1902.05458
Algorithm configuration methods optimize the performance of a parameterized heuristic algorithm on a given distribution of problem instances. Recent work introduced an algorithm configuration procedure (‘Structured Procrastination’) that provably achieves near optimal performance with high probability and with nearly minimal runtime in the worst case. It also offers an $\textit{anytime}$ property: it keeps tightening its optimality guarantees the longer it is run. Unfortunately, Structured Procrastination is not $\textit{adaptive}$ to characteristics of the parameterized algorithm: it treats every input like the worst case. Follow-up work (‘Leaps and Bounds’) achieves adaptivity but trades away the anytime property. This paper introduces a new algorithm configuration method, ‘Structured Procrastination with Confidence’, that preserves the near-optimality and anytime properties of Structured Procrastination while adding adaptivity. In particular, the new algorithm will perform dramatically faster in settings where many algorithm configurations perform poorly; we show empirically that such settings arise frequently in practice.
http://arxiv.org/abs/1902.05454