Paper Group ANR 229
Learning Large-Scale Bayesian Networks with the sparsebn Package. Learning Data Manifolds with a Cutting Plane Method. Survey of Recent Advances in Visual Question Answering. State Space Decomposition and Subgoal Creation for Transfer in Deep Reinforcement Learning. Subdeterminant Maximization via Nonconvex Relaxations and Anti-concentration. L1-no …
Learning Large-Scale Bayesian Networks with the sparsebn Package
| Title | Learning Large-Scale Bayesian Networks with the sparsebn Package |
| Authors | Bryon Aragam, Jiaying Gu, Qing Zhou |
| Abstract | Learning graphical models from data is an important problem with wide applications, ranging from genomics to the social sciences. Nowadays datasets often have upwards of thousands—sometimes tens or hundreds of thousands—of variables and far fewer samples. To meet this challenge, we have developed a new R package called sparsebn for learning the structure of large, sparse graphical models with a focus on Bayesian networks. While there are many existing software packages for this task, this package focuses on the unique setting of learning large networks from high-dimensional data, possibly with interventions. As such, the methods provided place a premium on scalability and consistency in a high-dimensional setting. Furthermore, in the presence of interventions, the methods implemented here achieve the goal of learning a causal network from data. Additionally, the sparsebn package is fully compatible with existing software packages for network analysis. |
| Tasks | |
| Published | 2017-03-11 |
| URL | http://arxiv.org/abs/1703.04025v2 |
| http://arxiv.org/pdf/1703.04025v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-large-scale-bayesian-networks-with |
| Repo | |
| Framework | |
Learning Data Manifolds with a Cutting Plane Method
| Title | Learning Data Manifolds with a Cutting Plane Method |
| Authors | SueYeon Chung, Uri Cohen, Haim Sompolinsky, Daniel D. Lee |
| Abstract | We consider the problem of classifying data manifolds where each manifold represents invariances that are parameterized by continuous degrees of freedom. Conventional data augmentation methods rely upon sampling large numbers of training examples from these manifolds; instead, we propose an iterative algorithm called M_{CP} based upon a cutting-plane approach that efficiently solves a quadratic semi-infinite programming problem to find the maximum margin solution. We provide a proof of convergence as well as a polynomial bound on the number of iterations required for a desired tolerance in the objective function. The efficiency and performance of M_{CP} are demonstrated in high-dimensional simulations and on image manifolds generated from the ImageNet dataset. Our results indicate that M_{CP} is able to rapidly learn good classifiers and shows superior generalization performance compared with conventional maximum margin methods using data augmentation methods. |
| Tasks | Data Augmentation |
| Published | 2017-05-28 |
| URL | http://arxiv.org/abs/1705.09944v1 |
| http://arxiv.org/pdf/1705.09944v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-data-manifolds-with-a-cutting-plane |
| Repo | |
| Framework | |
Survey of Recent Advances in Visual Question Answering
| Title | Survey of Recent Advances in Visual Question Answering |
| Authors | Supriya Pandhre, Shagun Sodhani |
| Abstract | Visual Question Answering (VQA) presents a unique challenge as it requires the ability to understand and encode the multi-modal inputs - in terms of image processing and natural language processing. The algorithm further needs to learn how to perform reasoning over this multi-modal representation so it can answer the questions correctly. This paper presents a survey of different approaches proposed to solve the problem of Visual Question Answering. We also describe the current state of the art model in later part of paper. In particular, the paper describes the approaches taken by various algorithms to extract image features, text features and the way these are employed to predict answers. We also briefly discuss the experiments performed to evaluate the VQA models and report their performances on diverse datasets including newly released VQA2.0[8]. |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2017-09-24 |
| URL | http://arxiv.org/abs/1709.08203v1 |
| http://arxiv.org/pdf/1709.08203v1.pdf | |
| PWC | https://paperswithcode.com/paper/survey-of-recent-advances-in-visual-question |
| Repo | |
| Framework | |
State Space Decomposition and Subgoal Creation for Transfer in Deep Reinforcement Learning
| Title | State Space Decomposition and Subgoal Creation for Transfer in Deep Reinforcement Learning |
| Authors | Himanshu Sahni, Saurabh Kumar, Farhan Tejani, Yannick Schroecker, Charles Isbell |
| Abstract | Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a framework through which a deep RL agent learns to generalize policies from smaller, simpler domains to more complex ones using a recurrent attention mechanism. The task is presented to the agent as an image and an instruction specifying the goal. This meta-controller guides the agent towards its goal by designing a sequence of smaller subtasks on the part of the state space within the attention, effectively decomposing it. As a baseline, we consider a setup without attention as well. Our experiments show that the meta-controller learns to create subgoals within the attention. |
| Tasks | |
| Published | 2017-05-24 |
| URL | http://arxiv.org/abs/1705.08997v1 |
| http://arxiv.org/pdf/1705.08997v1.pdf | |
| PWC | https://paperswithcode.com/paper/state-space-decomposition-and-subgoal |
| Repo | |
| Framework | |
Subdeterminant Maximization via Nonconvex Relaxations and Anti-concentration
| Title | Subdeterminant Maximization via Nonconvex Relaxations and Anti-concentration |
| Authors | Javad B. Ebrahimi, Damian Straszak, Nisheeth K. Vishnoi |
| Abstract | Several fundamental problems that arise in optimization and computer science can be cast as follows: Given vectors $v_1,\ldots,v_m \in \mathbb{R}^d$ and a constraint family ${\cal B}\subseteq 2^{[m]}$, find a set $S \in \cal{B}$ that maximizes the squared volume of the simplex spanned by the vectors in $S$. A motivating example is the data-summarization problem in machine learning where one is given a collection of vectors that represent data such as documents or images. The volume of a set of vectors is used as a measure of their diversity, and partition or matroid constraints over $[m]$ are imposed in order to ensure resource or fairness constraints. Recently, Nikolov and Singh presented a convex program and showed how it can be used to estimate the value of the most diverse set when ${\cal B}$ corresponds to a partition matroid. This result was recently extended to regular matroids in works of Straszak and Vishnoi, and Anari and Oveis Gharan. The question of whether these estimation algorithms can be converted into the more useful approximation algorithms – that also output a set – remained open. The main contribution of this paper is to give the first approximation algorithms for both partition and regular matroids. We present novel formulations for the subdeterminant maximization problem for these matroids; this reduces them to the problem of finding a point that maximizes the absolute value of a nonconvex function over a Cartesian product of probability simplices. The technical core of our results is a new anti-concentration inequality for dependent random variables that allows us to relate the optimal value of these nonconvex functions to their value at a random point. Unlike prior work on the constrained subdeterminant maximization problem, our proofs do not rely on real-stability or convexity and could be of independent interest both in algorithms and complexity. |
| Tasks | Data Summarization |
| Published | 2017-07-10 |
| URL | http://arxiv.org/abs/1707.02757v2 |
| http://arxiv.org/pdf/1707.02757v2.pdf | |
| PWC | https://paperswithcode.com/paper/subdeterminant-maximization-via-nonconvex |
| Repo | |
| Framework | |
L1-norm Error Function Robustness and Outlier Regularization
| Title | L1-norm Error Function Robustness and Outlier Regularization |
| Authors | Chris Ding, Bo Jiang |
| Abstract | In many real-world applications, data come with corruptions, large errors or outliers. One popular approach is to use L1-norm function. However, the robustness of L1-norm function is not well understood so far. In this paper, we present a new outlier regularization framework to understand and analyze the robustness of L1-norm function. There are two main features for the proposed outlier regularization. (1) A key property of outlier regularization is that how far an outlier lies away from its theoretically predicted value does not affect the final regularization and analysis results. (2) Another important feature of outlier regularization is that it has an equivalent continuous representation that closely relates to L1 function. This provides a new way to understand and analyze the robustness of L1 function. We apply our outlier regularization framework to PCA and propose an outlier regularized PCA (ORPCA) model. Comparing to the trace-normbased robust PCA, ORPCA has several benefits: (1) It does not suffer singular value suppression. (2) It can retain small high rank components which help retain fine details of data. (3) ORPCA can be computed more efficiently. |
| Tasks | |
| Published | 2017-05-28 |
| URL | http://arxiv.org/abs/1705.09954v1 |
| http://arxiv.org/pdf/1705.09954v1.pdf | |
| PWC | https://paperswithcode.com/paper/l1-norm-error-function-robustness-and-outlier |
| Repo | |
| Framework | |
A New Representation of Skeleton Sequences for 3D Action Recognition
| Title | A New Representation of Skeleton Sequences for 3D Action Recognition |
| Authors | Qiuhong Ke, Mohammed Bennamoun, Senjian An, Ferdous Sohel, Farid Boussaid |
| Abstract | This paper presents a new method for 3D action recognition with skeleton sequences (i.e., 3D trajectories of human skeleton joints). The proposed method first transforms each skeleton sequence into three clips each consisting of several frames for spatial temporal feature learning using deep neural networks. Each clip is generated from one channel of the cylindrical coordinates of the skeleton sequence. Each frame of the generated clips represents the temporal information of the entire skeleton sequence, and incorporates one particular spatial relationship between the joints. The entire clips include multiple frames with different spatial relationships, which provide useful spatial structural information of the human skeleton. We propose to use deep convolutional neural networks to learn long-term temporal information of the skeleton sequence from the frames of the generated clips, and then use a Multi-Task Learning Network (MTLN) to jointly process all frames of the generated clips in parallel to incorporate spatial structural information for action recognition. Experimental results clearly show the effectiveness of the proposed new representation and feature learning method for 3D action recognition. |
| Tasks | 3D Human Action Recognition, Multi-Task Learning, Skeleton Based Action Recognition, Temporal Action Localization |
| Published | 2017-03-09 |
| URL | http://arxiv.org/abs/1703.03492v3 |
| http://arxiv.org/pdf/1703.03492v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-representation-of-skeleton-sequences |
| Repo | |
| Framework | |
Semantic Technology-Assisted Review (STAR) Document analysis and monitoring using random vectors
| Title | Semantic Technology-Assisted Review (STAR) Document analysis and monitoring using random vectors |
| Authors | Jean-François Delpech |
| Abstract | The review and analysis of large collections of documents and the periodic monitoring of new additions thereto has greatly benefited from new developments in computer software. This paper demonstrates how using random vectors to construct a low-dimensional Euclidean space embedding words and documents enables fast and accurate computation of semantic similarities between them. With this technique of Semantic Technology-Assisted Review (STAR), documents can be selected, compared, classified, summarized and evaluated very quickly with minimal expert involvement and high-quality results. |
| Tasks | |
| Published | 2017-11-28 |
| URL | http://arxiv.org/abs/1711.10307v2 |
| http://arxiv.org/pdf/1711.10307v2.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-technology-assisted-review-star |
| Repo | |
| Framework | |
Performance Characterization of Image Feature Detectors in Relation to the Scene Content Utilizing a Large Image Database
| Title | Performance Characterization of Image Feature Detectors in Relation to the Scene Content Utilizing a Large Image Database |
| Authors | Bruno Ferrarini, Shoaib Ehsan, Ales Leonardis, Naveed Ur Rehman, Klaus D. McDonald-Maier |
| Abstract | Selecting the most suitable local invariant feature detector for a particular application has rendered the task of evaluating feature detectors a critical issue in vision research. Although the literature offers a variety of comparison works focusing on performance evaluation of image feature detectors under several types of image transformations, the influence of the scene content on the performance of local feature detectors has received little attention so far. This paper aims to bridge this gap with a new framework for determining the type of scenes which maximize and minimize the performance of detectors in terms of repeatability rate. The results are presented for several state-of-the-art feature detectors that have been obtained using a large image database of 20482 images under JPEG compression, uniform light and blur changes with 539 different scenes captured from real-world scenarios. These results provide new insights into the behavior of feature detectors. |
| Tasks | |
| Published | 2017-09-24 |
| URL | http://arxiv.org/abs/1709.08202v2 |
| http://arxiv.org/pdf/1709.08202v2.pdf | |
| PWC | https://paperswithcode.com/paper/performance-characterization-of-image-feature |
| Repo | |
| Framework | |
Robust Facial Landmark Detection under Significant Head Poses and Occlusion
| Title | Robust Facial Landmark Detection under Significant Head Poses and Occlusion |
| Authors | Yue Wu, Qiang Ji |
| Abstract | There have been tremendous improvements for facial landmark detection on general “in-the-wild” images. However, it is still challenging to detect the facial landmarks on images with severe occlusion and images with large head poses (e.g. profile face). In fact, the existing algorithms usually can only handle one of them. In this work, we propose a unified robust cascade regression framework that can handle both images with severe occlusion and images with large head poses. Specifically, the method iteratively predicts the landmark occlusions and the landmark locations. For occlusion estimation, instead of directly predicting the binary occlusion vectors, we introduce a supervised regression method that gradually updates the landmark visibility probabilities in each iteration to achieve robustness. In addition, we explicitly add occlusion pattern as a constraint to improve the performance of occlusion prediction. For landmark detection, we combine the landmark visibility probabilities, the local appearances, and the local shapes to iteratively update their positions. The experimental results show that the proposed method is significantly better than state-of-the-art works on images with severe occlusion and images with large head poses. It is also comparable to other methods on general “in-the-wild” images. |
| Tasks | Facial Landmark Detection |
| Published | 2017-09-23 |
| URL | http://arxiv.org/abs/1709.08127v1 |
| http://arxiv.org/pdf/1709.08127v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-facial-landmark-detection-under |
| Repo | |
| Framework | |
Discovery Radiomics via Deep Multi-Column Radiomic Sequencers for Skin Cancer Detection
| Title | Discovery Radiomics via Deep Multi-Column Radiomic Sequencers for Skin Cancer Detection |
| Authors | Mohammad Javad Shafiee, Alexander Wong |
| Abstract | While skin cancer is the most diagnosed form of cancer in men and women, with more cases diagnosed each year than all other cancers combined, sufficiently early diagnosis results in very good prognosis and as such makes early detection crucial. While radiomics have shown considerable promise as a powerful diagnostic tool for significantly improving oncological diagnostic accuracy and efficiency, current radiomics-driven methods have largely rely on pre-defined, hand-crafted quantitative features, which can greatly limit the ability to fully characterize unique cancer phenotype that distinguish it from healthy tissue. Recently, the notion of discovery radiomics was introduced, where a large amount of custom, quantitative radiomic features are directly discovered from the wealth of readily available medical imaging data. In this study, we present a novel discovery radiomics framework for skin cancer detection, where we leverage novel deep multi-column radiomic sequencers for high-throughput discovery and extraction of a large amount of custom radiomic features tailored for characterizing unique skin cancer tissue phenotype. The discovered radiomic sequencer was tested against 9,152 biopsy-proven clinical images comprising of different skin cancers such as melanoma and basal cell carcinoma, and demonstrated sensitivity and specificity of 91% and 75%, respectively, thus achieving dermatologist-level performance and \break hence can be a powerful tool for assisting general practitioners and dermatologists alike in improving the efficiency, consistency, and accuracy of skin cancer diagnosis. |
| Tasks | |
| Published | 2017-09-24 |
| URL | http://arxiv.org/abs/1709.08248v1 |
| http://arxiv.org/pdf/1709.08248v1.pdf | |
| PWC | https://paperswithcode.com/paper/discovery-radiomics-via-deep-multi-column |
| Repo | |
| Framework | |
Survival-Supervised Topic Modeling with Anchor Words: Characterizing Pancreatitis Outcomes
| Title | Survival-Supervised Topic Modeling with Anchor Words: Characterizing Pancreatitis Outcomes |
| Authors | George H. Chen, Jeremy C. Weiss |
| Abstract | We introduce a new approach for topic modeling that is supervised by survival analysis. Specifically, we build on recent work on unsupervised topic modeling with so-called anchor words by providing supervision through an elastic-net regularized Cox proportional hazards model. In short, an anchor word being present in a document provides strong indication that the document is partially about a specific topic. For example, by seeing “gallstones” in a document, we are fairly certain that the document is partially about medicine. Our proposed method alternates between learning a topic model and learning a survival model to find a local minimum of a block convex optimization problem. We apply our proposed approach to predicting how long patients with pancreatitis admitted to an intensive care unit (ICU) will stay in the ICU. Our approach is as accurate as the best of a variety of baselines while being more interpretable than any of the baselines. |
| Tasks | Survival Analysis |
| Published | 2017-12-02 |
| URL | http://arxiv.org/abs/1712.00535v2 |
| http://arxiv.org/pdf/1712.00535v2.pdf | |
| PWC | https://paperswithcode.com/paper/survival-supervised-topic-modeling-with |
| Repo | |
| Framework | |
Computational Results for Extensive-Form Adversarial Team Games
| Title | Computational Results for Extensive-Form Adversarial Team Games |
| Authors | Andrea Celli, Nicola Gatti |
| Abstract | We provide, to the best of our knowledge, the first computational study of extensive-form adversarial team games. These games are sequential, zero-sum games in which a team of players, sharing the same utility function, faces an adversary. We define three different scenarios according to the communication capabilities of the team. In the first, the teammates can communicate and correlate their actions both before and during the play. In the second, they can only communicate before the play. In the third, no communication is possible at all. We define the most suitable solution concepts, and we study the inefficiency caused by partial or null communication, showing that the inefficiency can be arbitrarily large in the size of the game tree. Furthermore, we study the computational complexity of the equilibrium-finding problem in the three scenarios mentioned above, and we provide, for each of the three scenarios, an exact algorithm. Finally, we empirically evaluate the scalability of the algorithms in random games and the inefficiency caused by partial or null communication. |
| Tasks | |
| Published | 2017-11-18 |
| URL | http://arxiv.org/abs/1711.06930v1 |
| http://arxiv.org/pdf/1711.06930v1.pdf | |
| PWC | https://paperswithcode.com/paper/computational-results-for-extensive-form |
| Repo | |
| Framework | |
Extending Automatic Discourse Segmentation for Texts in Spanish to Catalan
| Title | Extending Automatic Discourse Segmentation for Texts in Spanish to Catalan |
| Authors | Iria da Cunha, Eric SanJuan, Juan-Manuel Torres-Moreno, Irene Castellón |
| Abstract | At present, automatic discourse analysis is a relevant research topic in the field of NLP. However, discourse is one of the phenomena most difficult to process. Although discourse parsers have been already developed for several languages, this tool does not exist for Catalan. In order to implement this kind of parser, the first step is to develop a discourse segmenter. In this article we present the first discourse segmenter for texts in Catalan. This segmenter is based on Rhetorical Structure Theory (RST) for Spanish, and uses lexical and syntactic information to translate rules valid for Spanish into rules for Catalan. We have evaluated the system by using a gold standard corpus including manually segmented texts and results are promising. |
| Tasks | |
| Published | 2017-03-11 |
| URL | http://arxiv.org/abs/1703.04718v1 |
| http://arxiv.org/pdf/1703.04718v1.pdf | |
| PWC | https://paperswithcode.com/paper/extending-automatic-discourse-segmentation |
| Repo | |
| Framework | |
Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching
| Title | Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching |
| Authors | Jiahao Pang, Wenxiu Sun, Jimmy SJ. Ren, Chengxi Yang, Qiong Yan |
| Abstract | Leveraging on the recent developments in convolutional neural networks (CNNs), matching dense correspondence from a stereo pair has been cast as a learning problem, with performance exceeding traditional approaches. However, it remains challenging to generate high-quality disparities for the inherently ill-posed regions. To tackle this problem, we propose a novel cascade CNN architecture composing of two stages. The first stage advances the recently proposed DispNet by equipping it with extra up-convolution modules, leading to disparity images with more details. The second stage explicitly rectifies the disparity initialized by the first stage; it couples with the first-stage and generates residual signals across multiple scales. The summation of the outputs from the two stages gives the final disparity. As opposed to directly learning the disparity at the second stage, we show that residual learning provides more effective refinement. Moreover, it also benefits the training of the overall cascade network. Experimentation shows that our cascade residual learning scheme provides state-of-the-art performance for matching stereo correspondence. By the time of the submission of this paper, our method ranks first in the KITTI 2015 stereo benchmark, surpassing the prior works by a noteworthy margin. |
| Tasks | Stereo Matching, Stereo Matching Hand |
| Published | 2017-08-30 |
| URL | http://arxiv.org/abs/1708.09204v2 |
| http://arxiv.org/pdf/1708.09204v2.pdf | |
| PWC | https://paperswithcode.com/paper/cascade-residual-learning-a-two-stage |
| Repo | |
| Framework | |
