January 29, 2020

3110 words 15 mins read

Paper Group ANR 509

Sum-of-square-of-rational-function based representations of positive semidefinite polynomial matrices. BusyHands: A Hand-Tool Interaction Database for Assembly Tasks Semantic Segmentation. Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach. Spurious Vanishing Problem in Approximate Vanishing Ideal. Fast Convol …

Sum-of-square-of-rational-function based representations of positive semidefinite polynomial matrices


Title	Sum-of-square-of-rational-function based representations of positive semidefinite polynomial matrices
Authors	Thanh-Hieu Le, Nhat-Thien Pham
Abstract	The paper proves sum-of-square-of-rational-function based representations (shortly, sosrf-based representations) of polynomial matrices that are positive semidefinite on some special sets: $\mathbb{R}^n;$ $\mathbb{R}$ and its intervals $[a,b]$, $[0,\infty)$; and the strips $[a,b] \times \mathbb{R} \subset \mathbb{R}^2.$ A method for numerically computing such representations is also presented. The methodology is divided into two stages: (S1) diagonalizing the initial polynomial matrix based on the Schm"{u}dgen’s procedure \cite{Schmudgen09}; (S2) for each diagonal element of the resulting matrix, find its low rank sosrf-representation satisfying the Artin’s theorem solving the Hilbert’s 17th problem. Some numerical tests and illustrations with \textsf{OCTAVE} are also presented for each type of polynomial matrices.
Tasks
Published	2019-01-05
URL	http://arxiv.org/abs/1901.02360v2
PDF	http://arxiv.org/pdf/1901.02360v2.pdf
PWC	https://paperswithcode.com/paper/sum-of-square-of-rational-function-based
Repo
Framework

BusyHands: A Hand-Tool Interaction Database for Assembly Tasks Semantic Segmentation


Title	BusyHands: A Hand-Tool Interaction Database for Assembly Tasks Semantic Segmentation
Authors	Roy Shilkrot, Zhi Chai, Minh Hoai
Abstract	Visual segmentation has seen tremendous advancement recently with ready solutions for a wide variety of scene types, including human hands and other body parts. However, focus on segmentation of human hands while performing complex tasks, such as manual assembly, is still severely lacking. Segmenting hands from tools, work pieces, background and other body parts is extremely difficult because of self-occlusions and intricate hand grips and poses. In this paper we introduce BusyHands, a large open dataset of pixel-level annotated images of hands performing 13 different tool-based assembly tasks, from both real-world captures and virtual-world renderings. A total of 7906 samples are included in our first-in-kind dataset, with both RGB and depth images as obtained from a Kinect V2 camera and Blender. We evaluate several state-of-the-art semantic segmentation methods on our dataset as a proposed performance benchmark.
Tasks	Semantic Segmentation
Published	2019-02-19
URL	http://arxiv.org/abs/1902.07262v1
PDF	http://arxiv.org/pdf/1902.07262v1.pdf
PWC	https://paperswithcode.com/paper/busyhands-a-hand-tool-interaction-database
Repo
Framework

Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach


Title	Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach
Authors	He He, Dongrui Wu
Abstract	A brain-computer interface (BCI) system usually needs a long calibration session for each new subject/task to adjust its parameters, which impedes its transition from the laboratory to real-world applications. Domain adaptation, which leverages labeled data from auxiliary subjects/tasks (source domains), has demonstrated its effectiveness in reducing such calibration effort. Currently, most domain adaptation approaches require the source domains to have the same feature space and label space as the target domain, which limits their applications, as the auxiliary data may have different feature spaces and/or different label spaces. This paper considers different set domain adaptation for BCIs, i.e., the source and target domains have different label spaces. We introduce a practical setting of different label sets for BCIs, and propose a novel label alignment (LA) approach to align the source label space with the target label space. It has three desirable properties: 1) LA only needs as few as one labeled sample from each class of the target subject; 2) LA can be used as a preprocessing step before different feature extraction and classification algorithms; and, 3) LA can be integrated with other domain adaptation approaches to achieve even better performance. Experiments on two motor imagery datasets demonstrated the effectiveness of LA.
Tasks	Calibration, Domain Adaptation, Transfer Learning
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01166v4
PDF	https://arxiv.org/pdf/1912.01166v4.pdf
PWC	https://paperswithcode.com/paper/heterogeneous-label-space-transfer-learning
Repo
Framework

Spurious Vanishing Problem in Approximate Vanishing Ideal


Title	Spurious Vanishing Problem in Approximate Vanishing Ideal
Authors	Hiroshi Kera, Yoshihiko Hasegawa
Abstract	Approximate vanishing ideal is a concept from computer algebra that studies the algebraic varieties behind perturbed data points. To capture the nonlinear structure of perturbed points, the introduction of approximation to exact vanishing ideals plays a critical role. However, such an approximation also gives rise to a theoretical problem—the spurious vanishing problem—in the basis construction of approximate vanishing ideals; namely, obtained basis polynomials can be approximately vanishing simply because of the small coefficients. In this paper, we propose a first general method that enables various basis construction algorithms to overcome the spurious vanishing problem. In particular, we integrate coefficient normalization with polynomial-based basis constructions, which do not need the proper ordering of monomials to process for basis constructions. We further propose a method that takes advantage of the iterative nature of basis construction so that computationally costly operations for coefficient normalization can be circumvented. Moreover, a coefficient truncation method is proposed for further accelerations. From the experiments, it can be shown that the proposed method overcomes the spurious vanishing problem, resulting in shorter feature vectors while sustaining comparable or even lower classification error.
Tasks
Published	2019-01-25
URL	https://arxiv.org/abs/1901.08798v3
PDF	https://arxiv.org/pdf/1901.08798v3.pdf
PWC	https://paperswithcode.com/paper/spurious-vanishing-problem-in-approximate
Repo
Framework

Fast Convolutive Nonnegative Matrix Factorization Through Coordinate and Block Coordinate Updates


Title	Fast Convolutive Nonnegative Matrix Factorization Through Coordinate and Block Coordinate Updates
Authors	Anthony Degleris, Ben Antin, Surya Ganguli, Alex H Williams
Abstract	Identifying recurring patterns in high-dimensional time series data is an important problem in many scientific domains. A popular model to achieve this is convolutive nonnegative matrix factorization (CNMF), which extends classic nonnegative matrix factorization (NMF) to extract short-lived temporal motifs from a long time series. Prior work has typically fit this model by multiplicative parameter updates—an approach widely considered to be suboptimal for NMF, especially in large-scale data applications. Here, we describe how to extend two popular and computationally scalable NMF algorithms—Hierarchical Alternating Least Squares (HALS) and Alternatining Nonnegative Least Squares (ANLS)—for the CNMF model. Both methods demonstrate performance advantages over multiplicative updates on large-scale synthetic and real world data.
Tasks	Time Series
Published	2019-06-29
URL	https://arxiv.org/abs/1907.00139v1
PDF	https://arxiv.org/pdf/1907.00139v1.pdf
PWC	https://paperswithcode.com/paper/fast-convolutive-nonnegative-matrix
Repo
Framework

Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up


Title	Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up
Authors	Weifeng Ge, Xiangru Lin, Yizhou Yu
Abstract	Given a training dataset composed of images and corresponding category labels, deep convolutional neural networks show a strong ability in mining discriminative parts for image classification. However, deep convolutional neural networks trained with image level labels only tend to focus on the most discriminative parts while missing other object parts, which could provide complementary information. In this paper, we approach this problem from a different perspective. We build complementary parts models in a weakly supervised manner to retrieve information suppressed by dominant object parts detected by convolutional neural networks. Given image level labels only, we first extract rough object instances by performing weakly supervised object detection and instance segmentation using Mask R-CNN and CRF-based segmentation. Then we estimate and search for the best parts model for each object instance under the principle of preserving as much diversity as possible. In the last stage, we build a bi-directional long short-term memory (LSTM) network to fuze and encode the partial information of these complementary parts into a comprehensive feature for image classification. Experimental results indicate that the proposed method not only achieves significant improvement over our baseline models, but also outperforms state-of-the-art algorithms by a large margin (6.7%, 2.8%, 5.2% respectively) on Stanford Dogs 120, Caltech-UCSD Birds 2011-200 and Caltech 256.
Tasks	Fine-Grained Image Classification, Image Classification, Instance Segmentation, Object Detection, Semantic Segmentation, Weakly Supervised Object Detection
Published	2019-03-07
URL	http://arxiv.org/abs/1903.02827v1
PDF	http://arxiv.org/pdf/1903.02827v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-complementary-parts-models
Repo
Framework

Communication-Efficient Accurate Statistical Estimation


Title	Communication-Efficient Accurate Statistical Estimation
Authors	Jianqing Fan, Yongyi Guo, Kaizheng Wang
Abstract	When the data are stored in a distributed manner, direct application of traditional statistical inference procedures is often prohibitive due to communication cost and privacy concerns. This paper develops and investigates two Communication-Efficient Accurate Statistical Estimators (CEASE), implemented through iterative algorithms for distributed optimization. In each iteration, node machines carry out computation in parallel and communicate with the central processor, which then broadcasts aggregated information to node machines for new updates. The algorithms adapt to the similarity among loss functions on node machines, and converge rapidly when each node machine has large enough sample size. Moreover, they do not require good initialization and enjoy linear converge guarantees under general conditions. The contraction rate of optimization errors is presented explicitly, with dependence on the local sample size unveiled. In addition, the improved statistical accuracy per iteration is derived. By regarding the proposed method as a multi-step statistical estimator, we show that statistical efficiency can be achieved in finite steps in typical statistical applications. In addition, we give the conditions under which the one-step CEASE estimator is statistically efficient. Extensive numerical experiments on both synthetic and real data validate the theoretical results and demonstrate the superior performance of our algorithms.
Tasks	Distributed Optimization
Published	2019-06-12
URL	https://arxiv.org/abs/1906.04870v1
PDF	https://arxiv.org/pdf/1906.04870v1.pdf
PWC	https://paperswithcode.com/paper/communication-efficient-accurate-statistical
Repo
Framework

Distance-Based Learning from Errors for Confidence Calibration


Title	Distance-Based Learning from Errors for Confidence Calibration
Authors	Chen Xing, Sercan Arik, Zizhao Zhang, Tomas Pfister
Abstract	Deep neural networks (DNNs) are poorly calibrated when trained in conventional ways. To improve confidence calibration of DNNs, we propose a novel training method, distance-based learning from errors (DBLE). DBLE bases its confidence estimation on distances in the representation space. In DBLE, we first adapt prototypical learning to train classification models. It yields a representation space where the distance between a test sample and its ground truth class center can calibrate the model’s classification performance. At inference, however, these distances are not available due to the lack of ground truth labels. To circumvent this by inferring the distance for every test sample, we propose to train a confidence model jointly with the classification model. We integrate this into training by merely learning from mis-classified training samples, which we show to be highly beneficial for effective learning. On multiple datasets and DNN architectures, we demonstrate that DBLE outperforms alternative single-model confidence calibration approaches. DBLE also achieves comparable performance with computationally-expensive ensemble approaches with lower computational cost and lower number of parameters.
Tasks	Calibration
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01730v2
PDF	https://arxiv.org/pdf/1912.01730v2.pdf
PWC	https://paperswithcode.com/paper/distance-based-learning-from-errors-for-1
Repo
Framework

Optimizing for Interpretability in Deep Neural Networks with Tree Regularization


Title	Optimizing for Interpretability in Deep Neural Networks with Tree Regularization
Authors	Mike Wu, Sonali Parbhoo, Michael C. Hughes, Volker Roth, Finale Doshi-Velez
Abstract	Deep models have advanced prediction in many domains, but their lack of interpretability remains a key barrier to the adoption in many real world applications. There exists a large body of work aiming to help humans understand these black box functions to varying levels of granularity – for example, through distillation, gradients, or adversarial examples. These methods however, all tackle interpretability as a separate process after training. In this work, we take a different approach and explicitly regularize deep models so that they are well-approximated by processes that humans can step-through in little time. Specifically, we train several families of deep neural networks to resemble compact, axis-aligned decision trees without significant compromises in accuracy. The resulting axis-aligned decision functions uniquely make tree regularized models easy for humans to interpret. Moreover, for situations in which a single, global tree is a poor estimator, we introduce a regional tree regularizer that encourages the deep model to resemble a compact, axis-aligned decision tree in predefined, human-interpretable contexts. Using intuitive toy examples as well as medical tasks for patients in critical care and with HIV, we demonstrate that this new family of tree regularizers yield models that are easier for humans to simulate than simpler L1 or L2 penalties without sacrificing predictive power.
Tasks
Published	2019-08-14
URL	https://arxiv.org/abs/1908.05254v1
PDF	https://arxiv.org/pdf/1908.05254v1.pdf
PWC	https://paperswithcode.com/paper/optimizing-for-interpretability-in-deep
Repo
Framework

A Bug or a Suggestion? An Automatic Way to Label Issues


Title	A Bug or a Suggestion? An Automatic Way to Label Issues
Authors	Yuxiang Zhu, Minxue Pan, Yu Pei, Tian Zhang
Abstract	More and more users and developers are using Issue Tracking Systems (ITSs) to report issues, including bugs, feature requests, enhancement suggestions, etc. Different information, however, is gathered from users when issues are reported on different ITSs, which presents considerable challenges for issue classification tools to work effectively across the ITSs. Besides, bugs often take higher priority when it comes to classifying the issues, while existing approaches to issue classification seldom focus on distinguishing bugs and the other non-bug issues, leading to suboptimal accuracy in bug identification. In this paper, we propose a deep learning-based approach to automatically identify bug-reporting issues across various ITSs. The approach implements the k-NN algorithm to detect and correct misclassifications in data extracted from the ITSs, and trains an attention-based bi-directional long short-term memory (ABLSTM) network using a dataset of over 1.2 million labelled issues to identify bug reports. Experimental evaluation shows that our approach achieved an F-measure of 85.6% in distinguishing bugs and other issues, significantly outperforming the other benchmark and state-of-the-art approaches examined in the experiment.
Tasks
Published	2019-09-03
URL	https://arxiv.org/abs/1909.00934v1
PDF	https://arxiv.org/pdf/1909.00934v1.pdf
PWC	https://paperswithcode.com/paper/a-bug-or-a-suggestion-an-automatic-way-to
Repo
Framework

Automatic classification of geologic units in seismic images using partially interpreted examples


Title	Automatic classification of geologic units in seismic images using partially interpreted examples
Authors	Bas Peters, Justin Granek, Eldad Haber
Abstract	Geologic interpretation of large seismic stacked or migrated seismic images can be a time-consuming task for seismic interpreters. Neural network based semantic segmentation provides fast and automatic interpretations, provided a sufficient number of example interpretations are available. Networks that map from image-to-image emerged recently as powerful tools for automatic segmentation, but standard implementations require fully interpreted examples. Generating training labels for large images manually is time consuming. We introduce a partial loss-function and labeling strategies such that networks can learn from partially interpreted seismic images. This strategy requires only a small number of annotated pixels per seismic image. Tests on seismic images and interpretation information from the Sea of Ireland show that we obtain high-quality predicted interpretations from a small number of large seismic images. The combination of a partial-loss function, a multi-resolution network that explicitly takes small and large-scale geological features into account, and new labeling strategies make neural networks a more practical tool for automatic seismic interpretation.
Tasks	Seismic Interpretation, Semantic Segmentation
Published	2019-01-12
URL	http://arxiv.org/abs/1901.03786v1
PDF	http://arxiv.org/pdf/1901.03786v1.pdf
PWC	https://paperswithcode.com/paper/automatic-classification-of-geologic-units-in
Repo
Framework

Fine-tune Bert for DocRED with Two-step Process


Title	Fine-tune Bert for DocRED with Two-step Process
Authors	Hong Wang, Christfried Focke, Rob Sylvester, Nilesh Mishra, William Wang
Abstract	Modelling relations between multiple entities has attracted increasing attention recently, and a new dataset called DocRED has been collected in order to accelerate the research on the document-level relation extraction. Current baselines for this task uses BiLSTM to encode the whole document and are trained from scratch. We argue that such simple baselines are not strong enough to model to complex interaction between entities. In this paper, we further apply a pre-trained language model (BERT) to provide a stronger baseline for this task. We also find that solving this task in phases can further improve the performance. The first step is to predict whether or not two entities have a relation, the second step is to predict the specific relation.
Tasks	Language Modelling, Relation Extraction
Published	2019-09-26
URL	https://arxiv.org/abs/1909.11898v1
PDF	https://arxiv.org/pdf/1909.11898v1.pdf
PWC	https://paperswithcode.com/paper/fine-tune-bert-for-docred-with-two-step
Repo
Framework

A Review of Semi Supervised Learning Theories and Recent Advances


Title	A Review of Semi Supervised Learning Theories and Recent Advances
Authors	Enmei Tu, Jie Yang
Abstract	Semi-supervised learning, which has emerged from the beginning of this century, is a new type of learning method between traditional supervised learning and unsupervised learning. The main idea of semi-supervised learning is to introduce unlabeled samples into the model training process to avoid performance (or model) degeneration due to insufficiency of labeled samples. Semi-supervised learning has been applied successfully in many fields. This paper reviews the development process and main theories of semi-supervised learning, as well as its recent advances and importance in solving real-world problems demonstrated by typical application examples.
Tasks
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11590v1
PDF	https://arxiv.org/pdf/1905.11590v1.pdf
PWC	https://paperswithcode.com/paper/a-review-of-semi-supervised-learning-theories
Repo
Framework

SE-SLAM: Semi-Dense Structured Edge-Based Monocular SLAM


Title	SE-SLAM: Semi-Dense Structured Edge-Based Monocular SLAM
Authors	Juan Jose Tarrio, Claus Smitt, Sol Pedre
Abstract	Vision-based Simultaneous Localization And Mapping (VSLAM) is a mature problem in Robotics. Most VSLAM systems are feature based methods, which are robust and present high accuracy, but yield sparse maps with limited application for further navigation tasks. Most recently, direct methods which operate directly on image intensity have been introduced, capable of reconstructing richer maps at the cost of higher processing power. In this work, an edge-based monocular SLAM system (SE-SLAM) is proposed as a middle point: edges present good localization as point features, while enabling a structural semidense map reconstruction. However, edges are not easy to associate, track and optimize over time, as they lack descriptors and biunivocal correspondence, unlike point features. To tackle these issues, this paper presents a method to match edges between frames in a consistent manner; a feasible strategy to solve the optimization problem, since its size rapidly increases when working with edges; and the use of non-linear optimization techniques. The resulting system achieves comparable precision to state of the art feature-based and dense/semi-dense systems, while inherently building a structural semi-dense reconstruction of the environment, providing relevant structure data for further navigation algorithms. To achieve such accuracy, state of the art non-linear optimization is needed, over a continuous feed of 10000 edgepoints per frame, to optimize the full semi-dense output. Despite its heavy processing requirements, the system achieves near to real-time operation, thanks to a custom built solver and parallelization of its key stages. In order to encourage further development of edge-based SLAM systems, SE-SLAM source code will be released as open source.
Tasks	Simultaneous Localization and Mapping
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03917v1
PDF	https://arxiv.org/pdf/1909.03917v1.pdf
PWC	https://paperswithcode.com/paper/se-slam-semi-dense-structured-edge-based
Repo
Framework

Recurrent Hierarchical Topic-Guided Neural Language Models


Title	Recurrent Hierarchical Topic-Guided Neural Language Models
Authors	Dandan Guo, Bo Chen, Ruiying Lu, Mingyuan Zhou
Abstract	To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation. Moving beyond a conventional RNN based language model that ignores long-range word dependencies and sentence order, the proposed model captures not only intra-sentence word dependencies, but also temporal transitions between sentences and inter-sentence topic dependences. For inference, we develop a hybrid of stochastic-gradient MCMC and recurrent autoencoding variational Bayes. Experimental results on a variety of real-world text corpora demonstrate that the proposed model not only outperforms state-of-the-art larger-context RNN-based language models, but also learns interpretable recurrent multilayer topics and generates diverse sentences and paragraphs that are syntactically correct and semantically coherent.
Tasks	Language Modelling, Text Generation
Published	2019-12-21
URL	https://arxiv.org/abs/1912.10337v1
PDF	https://arxiv.org/pdf/1912.10337v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-hierarchical-topic-guided-neural-1
Repo
Framework