Paper Group ANR 310
Amharic Abstractive Text Summarization. Intweetive Text Summarization. Zero-Assignment Constraint for Graph Matching with Outliers. CAT: Customized Adversarial Training for Improved Robustness. High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification. Fast and Robust Comparison of Probability Measures in …
Amharic Abstractive Text Summarization
| Title | Amharic Abstractive Text Summarization |
| Authors | Amr M. Zaki, Mahmoud I. Khalil, Hazem M. Abbas |
| Abstract | Text Summarization is the task of condensing long text into just a handful of sentences. Many approaches have been proposed for this task, some of the very first were building statistical models (Extractive Methods) capable of selecting important words and copying them to the output, however these models lacked the ability to paraphrase sentences, as they simply select important words without actually understanding their contexts nor understanding their meaning, here comes the use of Deep Learning based architectures (Abstractive Methods), which effectively tries to understand the meaning of sentences to build meaningful summaries. In this work we discuss one of these new novel approaches which combines curriculum learning with Deep Learning, this model is called Scheduled Sampling. We apply this work to one of the most widely spoken African languages which is the Amharic Language, as we try to enrich the African NLP community with top-notch Deep Learning architectures. |
| Tasks | Abstractive Text Summarization, Text Summarization |
| Published | 2020-03-30 |
| URL | https://arxiv.org/abs/2003.13721v1 |
| https://arxiv.org/pdf/2003.13721v1.pdf | |
| PWC | https://paperswithcode.com/paper/amharic-abstractive-text-summarization |
| Repo | |
| Framework | |
Intweetive Text Summarization
| Title | Intweetive Text Summarization |
| Authors | Jean Valère Cossu, Juan-Manuel Torres-Moreno, Eric SanJuan, Marc El-Bèze |
| Abstract | The amount of user generated contents from various social medias allows analyst to handle a wide view of conversations on several topics related to their business. Nevertheless keeping up-to-date with this amount of information is not humanly feasible. Automatic Summarization then provides an interesting mean to digest the dynamics and the mass volume of contents. In this paper, we address the issue of tweets summarization which remains scarcely explored. We propose to automatically generated summaries of Micro-Blogs conversations dealing with public figures E-Reputation. These summaries are generated using key-word queries or sample tweet and offer a focused view of the whole Micro-Blog network. Since state-of-the-art is lacking on this point we conduct and evaluate our experiments over the multilingual CLEF RepLab Topic-Detection dataset according to an experimental evaluation process. |
| Tasks | Text Summarization |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.11382v1 |
| https://arxiv.org/pdf/2001.11382v1.pdf | |
| PWC | https://paperswithcode.com/paper/intweetive-text-summarization |
| Repo | |
| Framework | |
Zero-Assignment Constraint for Graph Matching with Outliers
| Title | Zero-Assignment Constraint for Graph Matching with Outliers |
| Authors | Fudong Wang, Nan Xue, Jin-Gang Yu, Gui-Song Xia |
| Abstract | Graph matching (GM), as a longstanding problem in computer vision and pattern recognition, still suffers from numerous cluttered outliers in practical applications. To address this issue, we present the zero-assignment constraint (ZAC) for approaching the graph matching problem in the presence of outliers. The underlying idea is to suppress the matchings of outliers by assigning zero-valued vectors to the potential outliers in the obtained optimal correspondence matrix. We provide elaborate theoretical analysis to the problem, i.e., GM with ZAC, and figure out that the GM problem with and without outliers are intrinsically different, which enables us to put forward a sufficient condition to construct valid and reasonable objective function. Consequently, we design an efficient outlier-robust algorithm to significantly reduce the incorrect or redundant matchings caused by numerous outliers. Extensive experiments demonstrate that our method can achieve the state-of-the-art performance in terms of accuracy and efficiency, especially in the presence of numerous outliers. |
| Tasks | Graph Matching |
| Published | 2020-03-26 |
| URL | https://arxiv.org/abs/2003.11928v1 |
| https://arxiv.org/pdf/2003.11928v1.pdf | |
| PWC | https://paperswithcode.com/paper/zero-assignment-constraint-for-graph-matching |
| Repo | |
| Framework | |
CAT: Customized Adversarial Training for Improved Robustness
| Title | CAT: Customized Adversarial Training for Improved Robustness |
| Authors | Minhao Cheng, Qi Lei, Pin-Yu Chen, Inderjit Dhillon, Cho-Jui Hsieh |
| Abstract | Adversarial training has become one of the most effective methods for improving robustness of neural networks. However, it often suffers from poor generalization on both clean and perturbed data. In this paper, we propose a new algorithm, named Customized Adversarial Training (CAT), which adaptively customizes the perturbation level and the corresponding label for each training sample in adversarial training. We show that the proposed algorithm achieves better clean and robust accuracy than previous adversarial training methods through extensive experiments. |
| Tasks | |
| Published | 2020-02-17 |
| URL | https://arxiv.org/abs/2002.06789v1 |
| https://arxiv.org/pdf/2002.06789v1.pdf | |
| PWC | https://paperswithcode.com/paper/cat-customized-adversarial-training-for |
| Repo | |
| Framework | |
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
| Title | High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification |
| Authors | Guan’an Wang, Shuo Yang, Huanyu Liu, Zhicheng Wang, Yang Yang, Shuliang Wang, Gang Yu, Erjin Zhou, Jian Sun |
| Abstract | Occluded person re-identification (ReID) aims to match occluded person images to holistic ones across dis-joint cameras. In this paper, we propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. At first, we use a CNN backbone and a key-points estimation model to extract semantic local features. Even so, occluded images still suffer from occlusion and outliers. Then, we view the local features of an image as nodes of a graph and propose an adaptive direction graph convolutional (ADGC)layer to pass relation information between nodes. The proposed ADGC layer can automatically suppress the message-passing of meaningless features by dynamically learning di-rection and degree of linkage. When aligning two groups of local features from two images, we view it as a graph matching problem and propose a cross-graph embedded-alignment (CGEA) layer to jointly learn and embed topology information to local features, and straightly predict similarity score. The proposed CGEA layer not only take full use of alignment learned by graph matching but also re-place sensitive one-to-one matching with a robust soft one. Finally, extensive experiments on occluded, partial, and holistic ReID tasks show the effectiveness of our proposed method. Specifically, our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset. |
| Tasks | Graph Matching, Person Re-Identification |
| Published | 2020-03-18 |
| URL | https://arxiv.org/abs/2003.08177v3 |
| https://arxiv.org/pdf/2003.08177v3.pdf | |
| PWC | https://paperswithcode.com/paper/high-order-information-matters-learning |
| Repo | |
| Framework | |
Fast and Robust Comparison of Probability Measures in Heterogeneous Spaces
| Title | Fast and Robust Comparison of Probability Measures in Heterogeneous Spaces |
| Authors | Ryoma Sato, Marco Cuturi, Makoto Yamada, Hisashi Kashima |
| Abstract | The problem of comparing distributions endowed with their own geometry appears in various settings, e.g., when comparing graphs, high-dimensional point clouds, shapes, and generative models. Although the Gromov Wasserstein (GW) distance is usually presented as the natural geometry to handle such comparisons, computing it involves solving a NP-hard problem. In this paper, we propose the Anchor Energy (AE) and Anchor Wasserstein (AW) distances, simpler alternatives to GW built upon the representation of each point in each distribution as the 1D distribution of its distances to all other points. We propose a sweep line algorithm to compute AE \emph{exactly} in $O(n^2 \log n)$ time, where $n$ is the size of each measure, compared to a naive implementation of AE requires $O(n^3)$ efforts. This is quasi-linear w.r.t. the description of the problem itself. AW can be pending a single $O(n^3)$ effort, in addition to the $O(n^2)$ cost of running the Sinkhorn algorithm. We also propose robust versions of AE and AW using rank-based criteria rather than cost values. We show in our experiments that the AE and AW distances perform well in 3D shape comparison and graph matching, at a fraction of the computational cost of popular GW approximations. |
| Tasks | Graph Matching |
| Published | 2020-02-05 |
| URL | https://arxiv.org/abs/2002.01615v2 |
| https://arxiv.org/pdf/2002.01615v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-robust-comparison-of-probability |
| Repo | |
| Framework | |
Learning representations in Bayesian Confidence Propagation neural networks
| Title | Learning representations in Bayesian Confidence Propagation neural networks |
| Authors | Naresh Balaji Ravichandran, Anders Lansner, Pawel Herman |
| Abstract | Unsupervised learning of hierarchical representations has been one of the most vibrant research directions in deep learning during recent years. In this work we study biologically inspired unsupervised strategies in neural networks based on local Hebbian learning. We propose new mechanisms to extend the Bayesian Confidence Propagating Neural Network (BCPNN) architecture, and demonstrate their capability for unsupervised learning of salient hidden representations when tested on the MNIST dataset. |
| Tasks | |
| Published | 2020-03-27 |
| URL | https://arxiv.org/abs/2003.12415v1 |
| https://arxiv.org/pdf/2003.12415v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-representations-in-bayesian |
| Repo | |
| Framework | |
Fabricated Pictures Detection with Graph Matching
| Title | Fabricated Pictures Detection with Graph Matching |
| Authors | Binrui Shen, Qiang Niu, Shengxin Zhu |
| Abstract | Fabricating experimental pictures in research work is a serious academic misconduct, which should better be detected in the reviewing process. However, due to large number of submissions, the detection whether a picture is fabricated or reused is laborious for reviewers, and sometimes is indistinct with human eyes. A tool for detecting similarity between images may help to alleviate this problem. Some methods based on local feature points matching work for most of the time, while these methods may result in mess of matchings due to ignorance of global relationship between features. We present a framework to detect similar, or perhaps fabricated, pictures with the graph matching techniques. A new iterative method is proposed, and experiments show that such a graph matching technique is better than the methods based only on local features for some cases. |
| Tasks | Graph Matching |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2002.03720v1 |
| https://arxiv.org/pdf/2002.03720v1.pdf | |
| PWC | https://paperswithcode.com/paper/fabricated-pictures-detection-with-graph |
| Repo | |
| Framework | |
MLIR: A Compiler Infrastructure for the End of Moore’s Law
| Title | MLIR: A Compiler Infrastructure for the End of Moore’s Law |
| Authors | Chris Lattner, Mehdi Amini, Uday Bondhugula, Albert Cohen, Andy Davis, Jacques Pienaar, River Riddle, Tatiana Shpeisman, Nicolas Vasilache, Oleksandr Zinenko |
| Abstract | This work presents MLIR, a novel approach to building reusable and extensible compiler infrastructure. MLIR aims to address software fragmentation, improve compilation for heterogeneous hardware, significantly reduce the cost of building domain specific compilers, and aid in connecting existing compilers together. MLIR facilitates the design and implementation of code generators, translators and optimizers at different levels of abstraction and also across application domains, hardware targets and execution environments. The contribution of this work includes (1) discussion of MLIR as a research artifact, built for extension and evolution, and identifying the challenges and opportunities posed by this novel design point in design, semantics, optimization specification, system, and engineering. (2) evaluation of MLIR as a generalized infrastructure that reduces the cost of building compilers-describing diverse use-cases to show research and educational opportunities for future programming languages, compilers, execution environments, and computer architecture. The paper also presents the rationale for MLIR, its original design principles, structures and semantics. |
| Tasks | |
| Published | 2020-02-25 |
| URL | https://arxiv.org/abs/2002.11054v2 |
| https://arxiv.org/pdf/2002.11054v2.pdf | |
| PWC | https://paperswithcode.com/paper/mlir-a-compiler-infrastructure-for-the-end-of |
| Repo | |
| Framework | |
Robust Multimodal Brain Tumor Segmentation via Feature Disentanglement and Gated Fusion
| Title | Robust Multimodal Brain Tumor Segmentation via Feature Disentanglement and Gated Fusion |
| Authors | Cheng Chen, Qi Dou, Yueming Jin, Hao Chen, Jing Qin, Pheng-Ann Heng |
| Abstract | Accurate medical image segmentation commonly requires effective learning of the complementary information from multimodal data. However, in clinical practice, we often encounter the problem of missing imaging modalities. We tackle this challenge and propose a novel multimodal segmentation framework which is robust to the absence of imaging modalities. Our network uses feature disentanglement to decompose the input modalities into the modality-specific appearance code, which uniquely sticks to each modality, and the modality-invariant content code, which absorbs multimodal information for the segmentation task. With enhanced modality-invariance, the disentangled content code from each modality is fused into a shared representation which gains robustness to missing data. The fusion is achieved via a learning-based strategy to gate the contribution of different modalities at different locations. We validate our method on the important yet challenging multimodal brain tumor segmentation task with the BRATS challenge dataset. With competitive performance to the state-of-the-art approaches for full modality, our method achieves outstanding robustness under various missing modality(ies) situations, significantly exceeding the state-of-the-art method by over 16% in average for Dice on whole tumor segmentation. |
| Tasks | Brain Tumor Segmentation, Medical Image Segmentation, Semantic Segmentation |
| Published | 2020-02-22 |
| URL | https://arxiv.org/abs/2002.09708v1 |
| https://arxiv.org/pdf/2002.09708v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-multimodal-brain-tumor-segmentation |
| Repo | |
| Framework | |
Extended Target Tracking and Classification Using Neural Networks
| Title | Extended Target Tracking and Classification Using Neural Networks |
| Authors | Barkın Tuncer, Murat Kumru, Emre Özkan |
| Abstract | Extended target/object tracking (ETT) problem involves tracking objects which potentially generate multiple measurements at a single sensor scan. State-of-the-art ETT algorithms can efficiently exploit the available information in these measurements such that they can track the dynamic behaviour of objects and learn their shapes simultaneously. Once the shape estimate of an object is formed, it can naturally be utilized by high-level tasks such as classification of the object type. In this work, we propose to use a naively deep neural network, which consists of one input, two hidden and one output layers, to classify dynamic objects regarding their shape estimates. The proposed method shows superior performance in comparison to a Bayesian classifier for simulation experiments. |
| Tasks | Object Tracking |
| Published | 2020-02-13 |
| URL | https://arxiv.org/abs/2002.05462v1 |
| https://arxiv.org/pdf/2002.05462v1.pdf | |
| PWC | https://paperswithcode.com/paper/extended-target-tracking-and-classification |
| Repo | |
| Framework | |
Monocular Direct Sparse Localization in a Prior 3D Surfel Map
| Title | Monocular Direct Sparse Localization in a Prior 3D Surfel Map |
| Authors | Haoyang Ye, Huaiyang Huang, Ming Liu |
| Abstract | In this paper, we introduce an approach to tracking the pose of a monocular camera in a prior surfel map. By rendering vertex and normal maps from the prior surfel map, the global planar information for the sparse tracked points in the image frame is obtained. The tracked points with and without the global planar information involve both global and local constraints of frames to the system. Our approach formulates all constraints in the form of direct photometric errors within a local window of the frames. The final optimization utilizes these constraints to provide the accurate estimation of global 6-DoF camera poses with the absolute scale. The extensive simulation and real-world experiments demonstrate that our monocular method can provide accurate camera localization results under various conditions. |
| Tasks | Camera Localization |
| Published | 2020-02-23 |
| URL | https://arxiv.org/abs/2002.09923v1 |
| https://arxiv.org/pdf/2002.09923v1.pdf | |
| PWC | https://paperswithcode.com/paper/monocular-direct-sparse-localization-in-a |
| Repo | |
| Framework | |
Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes
| Title | Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes |
| Authors | Qi Lei, Sai Ganesh Nagarajan, Ioannis Panageas, Xiao Wang |
| Abstract | In a recent series of papers it has been established that variants of Gradient Descent/Ascent and Mirror Descent exhibit last iterate convergence in convex-concave zero-sum games. Specifically, \cite{DISZ17, LiangS18} show last iterate convergence of the so called “Optimistic Gradient Descent/Ascent” for the case of \textit{unconstrained} min-max optimization. Moreover, in \cite{Metal} the authors show that Mirror Descent with an extra gradient step displays last iterate convergence for convex-concave problems (both constrained and unconstrained), though their algorithm does not follow the online learning framework; it uses extra information rather than \textit{only} the history to compute the next iteration. In this work, we show that “Optimistic Multiplicative-Weights Update (OMWU)” which follows the no-regret online learning framework, exhibits last iterate convergence locally for convex-concave games, generalizing the results of \cite{DP19} where last iterate convergence of OMWU was shown only for the \textit{bilinear case}. We complement our results with experiments that indicate fast convergence of the method. |
| Tasks | |
| Published | 2020-02-17 |
| URL | https://arxiv.org/abs/2002.06768v2 |
| https://arxiv.org/pdf/2002.06768v2.pdf | |
| PWC | https://paperswithcode.com/paper/last-iterate-convergence-in-no-regret |
| Repo | |
| Framework | |
Gradient tracking and variance reduction for decentralized optimization and machine learning
| Title | Gradient tracking and variance reduction for decentralized optimization and machine learning |
| Authors | Ran Xin, Soummya Kar, Usman A. Khan |
| Abstract | Decentralized methods to solve finite-sum minimization problems are important in many signal processing and machine learning tasks where the data is distributed over a network of nodes and raw data sharing is not permitted due to privacy and/or resource constraints. In this article, we review decentralized stochastic first-order methods and provide a unified algorithmic framework that combines variance-reduction with gradient tracking to achieve both robust performance and fast convergence. We provide explicit theoretical guarantees of the corresponding methods when the objective functions are smooth and strongly-convex, and show their applicability to non-convex problems via numerical experiments. Throughout the article, we provide intuitive illustrations of the main technical ideas by casting appropriate tradeoffs and comparisons among the methods of interest and by highlighting applications to decentralized training of machine learning models. |
| Tasks | |
| Published | 2020-02-13 |
| URL | https://arxiv.org/abs/2002.05373v1 |
| https://arxiv.org/pdf/2002.05373v1.pdf | |
| PWC | https://paperswithcode.com/paper/gradient-tracking-and-variance-reduction-for |
| Repo | |
| Framework | |
A Hierarchy of Limitations in Machine Learning
| Title | A Hierarchy of Limitations in Machine Learning |
| Authors | Momin M. Malik |
| Abstract | “All models are wrong, but some are useful”, wrote George E. P. Box (1979). Machine learning has focused on the usefulness of probability models for prediction in social systems, but is only now coming to grips with the ways in which these models are wrong—and the consequences of those shortcomings. This paper attempts a comprehensive, structured overview of the specific conceptual, procedural, and statistical limitations of models in machine learning when applied to society. Machine learning modelers themselves can use the described hierarchy to identify possible failure points and think through how to address them, and consumers of machine learning models can know what to question when confronted with the decision about if, where, and how to apply machine learning. The limitations go from commitments inherent in quantification itself, through to showing how unmodeled dependencies can lead to cross-validation being overly optimistic as a way of assessing model performance. |
| Tasks | |
| Published | 2020-02-12 |
| URL | https://arxiv.org/abs/2002.05193v2 |
| https://arxiv.org/pdf/2002.05193v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-hierarchy-of-limitations-in-machine |
| Repo | |
| Framework | |
