April 2, 2020

3294 words 16 mins read

Paper Group ANR 120

Paper Group ANR 120

Transfer Reinforcement Learning under Unobserved Contextual Information. TextCaps: a Dataset for Image Captioning with Reading Comprehension. Computer-Aided Assessment of Catheters and Tubes on Radiographs: How Good is Artificial Intelligence for Assessment?. Instance Segmentation of Visible and Occluded Regions for Finding and Picking Target from …

Transfer Reinforcement Learning under Unobserved Contextual Information

Title Transfer Reinforcement Learning under Unobserved Contextual Information
Authors Yan Zhang, Michael M. Zavlanos
Abstract In this paper, we study a transfer reinforcement learning problem where the state transitions and rewards are affected by the environmental context. Specifically, we consider a demonstrator agent that has access to a context-aware policy and can generate transition and reward data based on that policy. These data constitute the experience of the demonstrator. Then, the goal is to transfer this experience, excluding the underlying contextual information, to a learner agent that does not have access to the environmental context, so that they can learn a control policy using fewer samples. It is well known that, disregarding the causal effect of the contextual information, can introduce bias in the transition and reward models estimated by the learner, resulting in a learned suboptimal policy. To address this challenge, in this paper, we develop a method to obtain causal bounds on the transition and reward functions using the demonstrator’s data, which we then use to obtain causal bounds on the value functions. Using these value function bounds, we propose new Q learning and UCB-Q learning algorithms that converge to the true value function without bias. We provide numerical experiments for robot motion planning problems that validate the proposed value function bounds and demonstrate that the proposed algorithms can effectively make use of the data from the demonstrator to accelerate the learning process of the learner.
Tasks Motion Planning, Q-Learning, Transfer Reinforcement Learning
Published 2020-03-09
URL https://arxiv.org/abs/2003.04427v1
PDF https://arxiv.org/pdf/2003.04427v1.pdf
PWC https://paperswithcode.com/paper/transfer-reinforcement-learning-under

TextCaps: a Dataset for Image Captioning with Reading Comprehension

Title TextCaps: a Dataset for Image Captioning with Reading Comprehension
Authors Oleksii Sidorov, Ronghang Hu, Marcus Rohrbach, Amanpreet Singh
Abstract Image descriptions can help visually impaired people to quickly understand the image content. While we made significant progress in automatically describing images and optical character recognition, current approaches are unable to include written text in their descriptions, although text is omnipresent in human environments and frequently critical to understand our surroundings. To study how to comprehend text in the context of an image we collect a novel dataset, TextCaps, with 145k captions for 28k images. Our dataset challenges a model to recognize text, relate it to its visual context, and decide what part of the text to copy or paraphrase, requiring spatial, semantic, and visual reasoning between multiple text tokens and visual entities, such as objects. We study baselines and adapt existing approaches to this new task, which we refer to as image captioning with reading comprehension. Our analysis with automatic and human studies shows that our new TextCaps dataset provides many new technical challenges over previous datasets.
Tasks Image Captioning, Optical Character Recognition, Reading Comprehension, Visual Reasoning
Published 2020-03-24
URL https://arxiv.org/abs/2003.12462v1
PDF https://arxiv.org/pdf/2003.12462v1.pdf
PWC https://paperswithcode.com/paper/textcaps-a-dataset-for-image-captioning-with

Computer-Aided Assessment of Catheters and Tubes on Radiographs: How Good is Artificial Intelligence for Assessment?

Title Computer-Aided Assessment of Catheters and Tubes on Radiographs: How Good is Artificial Intelligence for Assessment?
Authors Xin Yi, Scott J. Adams, Robert D. E. Henderson, Paul Babyn
Abstract Catheters are the second most common abnormal finding on radiographs. The position of catheters must be assessed on all radiographs, as serious complications can arise if catheters are malpositioned. However, due to the large number of radiographs performed each day, there can be substantial delays between the time a radiograph is performed and when it is interpreted by a radiologist. Computer-aided approaches hold the potential to assist in prioritizing radiographs with potentially malpositioned catheters for interpretation and automatically insert text indicating the placement of catheters in radiology reports, thereby improving radiologists’ efficiency. After 50 years of research in computer-aided diagnosis, there is still a paucity of study in this area. With the development of deep learning approaches, the problem of catheter assessment is far more solvable. Therefore, we have performed a review of current algorithms and identified key challenges in building a reliable computer-aided diagnosis system for assessment of catheters on radiographs. This review may serve to further the development of machine learning approaches for this important use case.
Published 2020-02-09
URL https://arxiv.org/abs/2002.03413v1
PDF https://arxiv.org/pdf/2002.03413v1.pdf
PWC https://paperswithcode.com/paper/computer-aided-assessment-of-catheters-and

Instance Segmentation of Visible and Occluded Regions for Finding and Picking Target from a Pile of Objects

Title Instance Segmentation of Visible and Occluded Regions for Finding and Picking Target from a Pile of Objects
Authors Kentaro Wada, Shingo Kitagawa, Kei Okada, Masayuki Inaba
Abstract We present a robotic system for picking a target from a pile of objects that is capable of finding and grasping the target object by removing obstacles in the appropriate order. The fundamental idea is to segment instances with both visible and occluded masks, which we call instance occlusion segmentation'. To achieve this, we extend an existing instance segmentation model with a novel relook’ architecture, in which the model explicitly learns the inter-instance relationship. Also, by using image synthesis, we make the system capable of handling new objects without human annotations. The experimental results show the effectiveness of the relook architecture when compared with a conventional model and of the image synthesis when compared to a human-annotated dataset. We also demonstrate the capability of our system to achieve picking a target in a cluttered environment with a real robot.
Tasks Image Generation, Instance Segmentation, Semantic Segmentation
Published 2020-01-21
URL https://arxiv.org/abs/2001.07475v1
PDF https://arxiv.org/pdf/2001.07475v1.pdf
PWC https://paperswithcode.com/paper/instance-segmentation-of-visible-and-occluded

SVIRO: Synthetic Vehicle Interior Rear Seat Occupancy Dataset and Benchmark

Title SVIRO: Synthetic Vehicle Interior Rear Seat Occupancy Dataset and Benchmark
Authors Steve Dias Da Cruz, Oliver Wasenmüller, Hans-Peter Beise, Thomas Stifter, Didier Stricker
Abstract We release SVIRO, a synthetic dataset for sceneries in the passenger compartment of ten different vehicles, in order to analyze machine learning-based approaches for their generalization capacities and reliability when trained on a limited number of variations (e.g. identical backgrounds and textures, few instances per class). This is in contrast to the intrinsically high variability of common benchmark datasets, which focus on improving the state-of-the-art of general tasks. Our dataset contains bounding boxes for object detection, instance segmentation masks, keypoints for pose estimation and depth images for each synthetic scenery as well as images for each individual seat for classification. The advantage of our use-case is twofold: The proximity to a realistic application to benchmark new approaches under novel circumstances while reducing the complexity to a more tractable environment, such that applications and theoretical questions can be tested on a more challenging dataset as toy problems. The data and evaluation server are available under https://sviro.kl.dfki.de.
Tasks Instance Segmentation, Object Detection, Pose Estimation, Semantic Segmentation
Published 2020-01-10
URL https://arxiv.org/abs/2001.03483v1
PDF https://arxiv.org/pdf/2001.03483v1.pdf
PWC https://paperswithcode.com/paper/sviro-synthetic-vehicle-interior-rear-seat

DropCluster: A structured dropout for convolutional networks

Title DropCluster: A structured dropout for convolutional networks
Authors Liyan Chen, Philip Gautier, Sergul Aydore
Abstract Dropout as a regularizer in deep neural networks has been less effective in convolutional layers than in fully connected layers. This is due to the fact that dropout drops features randomly. When features are spatially correlated as in the case of convolutional layers, information about the dropped pixels can still propagate to the next layers via neighboring pixels. In order to address this problem, more structured forms of dropout have been proposed. A drawback of these methods is that they do not adapt to the data. In this work, we introduce a novel structured regularization for convolutional layers, which we call DropCluster. Our regularizer relies on data-driven structure. It finds clusters of correlated features in convolutional layer outputs and drops the clusters randomly at each iteration. The clusters are learned and updated during model training so that they adapt both to the data and to the model weights. Our experiments on the ResNet-50 architecture demonstrate that our approach achieves better performance than DropBlock or other existing structured dropout variants. We also demonstrate the robustness of our approach when the size of training data is limited and when there is corruption in the data at test time.
Published 2020-02-07
URL https://arxiv.org/abs/2002.02997v1
PDF https://arxiv.org/pdf/2002.02997v1.pdf
PWC https://paperswithcode.com/paper/dropcluster-a-structured-dropout-for

Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation

Title Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation
Authors Tong He, Dong Gong, Zhi Tian, Chunhua Shen
Abstract 3D point cloud semantic and instance segmentation is crucial and fundamental for 3D scene understanding. Due to the complex structure, point sets are distributed off balance and diversely, which appears as both category imbalance and pattern imbalance. As a result, deep networks can easily forget the non-dominant cases during the learning process, resulting in unsatisfactory performance. Although re-weighting can reduce the influence of the well-classified examples, they cannot handle the non-dominant patterns during the dynamic training. In this paper, we propose a memory-augmented network to learn and memorize the representative prototypes that cover diverse samples universally. Specifically, a memory module is introduced to alleviate the forgetting issue by recording the patterns seen in mini-batch training. The learned memory items consistently reflect the interpretable and meaningful information for both dominant and non-dominant categories and cases. The distorted observations and rare cases can thus be augmented by retrieving the stored prototypes, leading to better performances and generalization. Exhaustive experiments on the benchmarks, i.e. S3DIS and ScanNetV2, reflect the superiority of our method on both effectiveness and efficiency. Not only the overall accuracy but also nondominant classes have improved substantially.
Tasks Instance Segmentation, Scene Understanding, Semantic Segmentation
Published 2020-01-06
URL https://arxiv.org/abs/2001.01349v1
PDF https://arxiv.org/pdf/2001.01349v1.pdf
PWC https://paperswithcode.com/paper/learning-and-memorizing-representative

A Comparative Study of Sequence Classification Models for Privacy Policy Coverage Analysis

Title A Comparative Study of Sequence Classification Models for Privacy Policy Coverage Analysis
Authors Zachary Lindner
Abstract Privacy policies are legal documents that describe how a website will collect, use, and distribute a user’s data. Unfortunately, such documents are often overly complicated and filled with legal jargon; making it difficult for users to fully grasp what exactly is being collected and why. Our solution to this problem is to provide users with a coverage analysis of a given website’s privacy policy using a wide range of classical machine learning and deep learning techniques. Given a website’s privacy policy, the classifier identifies the associated data practice for each logical segment. These data practices/labels are taken directly from the OPP-115 corpus. For example, the data practice “Data Retention” refers to how long a website stores a user’s information. The coverage analysis allows users to determine how many of the ten possible data practices are covered, along with identifying the sections that correspond to the data practices of particular interest.
Published 2020-02-12
URL https://arxiv.org/abs/2003.04972v1
PDF https://arxiv.org/pdf/2003.04972v1.pdf
PWC https://paperswithcode.com/paper/a-comparative-study-of-sequence

The statistical physics of discovering exogenous and endogenous factors in a chain of events

Title The statistical physics of discovering exogenous and endogenous factors in a chain of events
Authors Shinsuke Koyama, Shigeru Shinomoto
Abstract Event occurrence is not only subject to the environmental changes, but is also facilitated by the events that have occurred in a system. Here, we develop a method for estimating such extrinsic and intrinsic factors from a single series of event-occurrence times. The analysis is performed using a model that combines the inhomogeneous Poisson process and the Hawkes process, which represent exogenous fluctuations and endogenous chain-reaction mechanisms, respectively. The model is fit to a given dataset by minimizing the free energy, for which statistical physics and a path-integral method are utilized. Because the process of event occurrence is stochastic, parameter estimation is inevitably accompanied by errors, and it can ultimately occur that exogenous and endogenous factors cannot be captured even with the best estimator. We obtained four regimes categorized according to whether respective factors are detected. By applying the analytical method to real time series of debate in a social-networking service, we have observed that the estimated exogenous and endogenous factors are close to the first comments and the follow-up comments, respectively. This method is general and applicable to a variety of data, and we have provided an application program, by which anyone can analyze any series of event times.
Tasks Time Series
Published 2020-03-02
URL https://arxiv.org/abs/2003.00659v1
PDF https://arxiv.org/pdf/2003.00659v1.pdf
PWC https://paperswithcode.com/paper/the-statistical-physics-of-discovering

Asian Handicap football betting with Rating-based Hybrid Bayesian Networks

Title Asian Handicap football betting with Rating-based Hybrid Bayesian Networks
Authors Anthony Constantinou
Abstract Despite the massive popularity of the Asian Handicap (AH) football betting market, it has not been adequately studied by the relevant literature. This paper combines rating systems with hybrid Bayesian networks and presents the first published model specifically developed for prediction and assessment of the AH betting market. The results are based on 13 English Premier League seasons and are compared to the traditional 1X2 market. Different betting situations have been examined including a) both average and maximum (best available) market odds, b) all possible betting decision thresholds between predicted and published odds, c) optimisations for both return-on-investment and profit, and d) simple stake adjustments to investigate how the variance of returns changes when targeting equivalent profit in both 1X2 and AH markets. While the AH market is found to share the inefficiencies of the traditional 1X2 market, the findings reveal both interesting differences as well as similarities between the two.
Published 2020-03-10
URL https://arxiv.org/abs/2003.09384v1
PDF https://arxiv.org/pdf/2003.09384v1.pdf
PWC https://paperswithcode.com/paper/asian-handicap-football-betting-with-rating

DETECT: Deep Trajectory Clustering for Mobility-Behavior Analysis

Title DETECT: Deep Trajectory Clustering for Mobility-Behavior Analysis
Authors Mingxuan Yue, Yaguang Li, Haoze Yang, Ritesh Ahuja, Yao-Yi Chiang, Cyrus Shahabi
Abstract Identifying mobility behaviors in rich trajectory data is of great economic and social interest to various applications including urban planning, marketing and intelligence. Existing work on trajectory clustering often relies on similarity measurements that utilize raw spatial and/or temporal information of trajectories. These measures are incapable of identifying similar moving behaviors that exhibit varying spatio-temporal scales of movement. In addition, the expense of labeling massive trajectory data is a barrier to supervised learning models. To address these challenges, we propose an unsupervised neural approach for mobility behavior clustering, called the Deep Embedded TrajEctory ClusTering network (DETECT). DETECT operates in three parts: first it transforms the trajectories by summarizing their critical parts and augmenting them with context derived from their geographical locality (e.g., using POIs from gazetteers). In the second part, it learns a powerful representation of trajectories in the latent space of behaviors, thus enabling a clustering function (such as $k$-means) to be applied. Finally, a clustering oriented loss is directly built on the embedded features to jointly perform feature refinement and cluster assignment, thus improving separability between mobility behaviors. Exhaustive quantitative and qualitative experiments on two real-world datasets demonstrate the effectiveness of our approach for mobility behavior analyses.
Published 2020-03-03
URL https://arxiv.org/abs/2003.01351v1
PDF https://arxiv.org/pdf/2003.01351v1.pdf
PWC https://paperswithcode.com/paper/detect-deep-trajectory-clustering-for

Scalable Constrained Bayesian Optimization

Title Scalable Constrained Bayesian Optimization
Authors David Eriksson, Matthias Poloczek
Abstract The global optimization of a high-dimensional black-box function under black-box constraints is a pervasive task in machine learning, control, and engineering. These problems are difficult since the feasible set is typically non-convex and hard to find, in addition to the curses of dimensionality and the heterogeneity of the underlying functions. In particular, these characteristics dramatically impact the performance of Bayesian optimization methods, that otherwise have become the de-facto standard for sample-efficient optimization in unconstrained settings. Due to the lack of sample-efficient methods, practitioners usually fall back to evolutionary strategies or heuristics. We propose the scalable constrained Bayesian optimization (SCBO) algorithm that addresses the above challenges by data-independent transformations of the functions and follows the recent theme of local Bayesian optimization. A comprehensive experimental evaluation demonstrates that SCBO achieves excellent results and outperforms the state-of-the-art methods.
Published 2020-02-20
URL https://arxiv.org/abs/2002.08526v2
PDF https://arxiv.org/pdf/2002.08526v2.pdf
PWC https://paperswithcode.com/paper/scalable-constrained-bayesian-optimization

SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinates

Title SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinates
Authors Zhizhong Han, Guanhui Qiao, Yu-Shen Liu, Matthias Zwicker
Abstract Structure learning for 3D shapes is vital for 3D computer vision. State-of-the-art methods show promising results by representing shapes using implicit functions in 3D that are learned using discriminative neural networks. However, learning implicit functions requires dense and irregular sampling in 3D space, which also makes the sampling methods affect the accuracy of shape reconstruction during test. To avoid dense and irregular sampling in 3D, we propose to represent shapes using 2D functions, where the output of the function at each 2D location is a sequence of line segments inside the shape. Our approach leverages the power of functional representations, but without the disadvantage of 3D sampling. Specifically, we use a voxel tubelization to represent a voxel grid as a set of tubes along any one of the X, Y, or Z axes. Each tube can be indexed by its 2D coordinates on the plane spanned by the other two axes. We further simplify each tube into a sequence of occupancy segments. Each occupancy segment consists of successive voxels occupied by the shape, which leads to a simple representation of its 1D start and end location. Given the 2D coordinates of the tube and a shape feature as condition, this representation enables us to learn 3D shape structures by sequentially predicting the start and end locations of each occupancy segment in the tube. We implement this approach using a Seq2Seq model with attention, called SeqXY2SeqZ, which learns the mapping from a sequence of 2D coordinates along two arbitrary axes to a sequence of 1D locations along the third axis. SeqXY2SeqZ not only benefits from the regularity of voxel grids in training and testing, but also achieves high memory efficiency. Our experiments show that SeqXY2SeqZ outperforms the state-ofthe-art methods under widely used benchmarks.
Published 2020-03-12
URL https://arxiv.org/abs/2003.05559v2
PDF https://arxiv.org/pdf/2003.05559v2.pdf
PWC https://paperswithcode.com/paper/seqxy2seqz-structure-learning-for-3d-shapes

Research on a New Convolutional Neural Network Model Combined with Random Edges Adding

Title Research on a New Convolutional Neural Network Model Combined with Random Edges Adding
Authors Xuanyu Shu, Jin Zhang, Sen Tian, Sheng chen, Lingyu Chen
Abstract It is always a hot and difficult point to improve the accuracy of convolutional neural network model and speed up its convergence. Based on the idea of small world network, a random edge adding algorithm is proposed to improve the performance of convolutional neural network model. This algorithm takes the convolutional neural network model as a benchmark, and randomizes backwards and cross-layer connections with probability p to form a new convolutional neural network model. The proposed idea can optimize the cross layer connectivity by changing the topological structure of convolutional neural network, and provide a new idea for the improvement of the model. The simulation results based on Fashion-MINST and cifar10 data set show that the model recognition accuracy and training convergence speed are greatly improved by random edge adding reconstructed models with aprobability p = 0.1.
Published 2020-03-17
URL https://arxiv.org/abs/2003.07794v1
PDF https://arxiv.org/pdf/2003.07794v1.pdf
PWC https://paperswithcode.com/paper/research-on-a-new-convolutional-neural

The exponentially weighted average forecaster in geodesic spaces of non-positive curvature

Title The exponentially weighted average forecaster in geodesic spaces of non-positive curvature
Authors Quentin Paris
Abstract This paper addresses the problem of prediction with expert advice for outcomes in a geodesic space with non-positive curvature in the sense of Alexandrov. Via geometric considerations, and in particular the notion of barycenters, we extend to this setting the definition and analysis of the classical exponentially weighted average forecaster. We also adapt the principle of online to batch conversion to this setting. We shortly discuss the application of these results in the context of aggregation and for the problem of barycenter estimation.
Published 2020-02-03
URL https://arxiv.org/abs/2002.00852v1
PDF https://arxiv.org/pdf/2002.00852v1.pdf
PWC https://paperswithcode.com/paper/the-exponentially-weighted-average-forecaster
comments powered by Disqus