January 29, 2020

3444 words 17 mins read

Paper Group ANR 599

Quantifying consensus of rankings based on q-support patterns. DCMN+: Dual Co-Matching Network for Multi-choice Reading Comprehension. An Arm-Wise Randomization Approach to Combinatorial Linear Semi-Bandits. WildMix Dataset and Spectro-Temporal Transformer Model for Monoaural Audio Source Separation. MURS: Practical and Robust Privacy Amplification …

Quantifying consensus of rankings based on q-support patterns


Title	Quantifying consensus of rankings based on q-support patterns
Authors	Zhengui Xue, Zhiwei Lin, Hui Wang, Sally McClean
Abstract	Rankings, representing preferences over a set of candidates, are widely used in many information systems, e.g., group decision making and information retrieval. It is of great importance to evaluate the consensus of the obtained rankings from multiple agents. An overall measure of the consensus degree provides an insight into the ranking data. Moreover, it could provide a quantitative indicator for consensus comparison between groups and further improvement of a ranking system. Existing studies are insufficient in assessing the overall consensus of a ranking set. They did not provide an evaluation of the consensus degree of preference patterns in most rankings. In this paper, a novel consensus quantifying approach, without the need for any correlation or distance functions as in existing studies of consensus, is proposed based on a concept of q-support patterns of rankings. The q-support patterns represent the commonality embedded in a set of rankings. A method for detecting outliers in a set of rankings is naturally derived from the proposed consensus quantifying approach. Experimental studies are conducted to demonstrate the effectiveness of the proposed approach.
Tasks	Decision Making, Information Retrieval
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12966v2
PDF	https://arxiv.org/pdf/1905.12966v2.pdf
PWC	https://paperswithcode.com/paper/quantifying-consensus-of-rankings-based-on-q
Repo
Framework

DCMN+: Dual Co-Matching Network for Multi-choice Reading Comprehension


Title	DCMN+: Dual Co-Matching Network for Multi-choice Reading Comprehension
Authors	Shuailiang Zhang, Hai Zhao, Yuwei Wu, Zhuosheng Zhang, Xi Zhou, Xiang Zhou
Abstract	Multi-choice reading comprehension is a challenging task to select an answer from a set of candidate options when given passage and question. Previous approaches usually only calculate question-aware passage representation and ignore passage-aware question representation when modeling the relationship between passage and question, which obviously cannot take the best of information between passage and question. In this work, we propose dual co-matching network (DCMN) which models the relationship among passage, question and answer options bidirectionally. Besides, inspired by how human solve multi-choice questions, we integrate two reading strategies into our model: (i) passage sentence selection that finds the most salient supporting sentences to answer the question, (ii) answer option interaction that encodes the comparison information between answer options. DCMN integrated with the two strategies (DCMN+) obtains state-of-the-art results on five multi-choice reading comprehension datasets which are from different domains: RACE, SemEval-2018 Task 11, ROCStories, COIN, MCTest.
Tasks	Reading Comprehension
Published	2019-08-30
URL	https://arxiv.org/abs/1908.11511v4
PDF	https://arxiv.org/pdf/1908.11511v4.pdf
PWC	https://paperswithcode.com/paper/dcmn-dual-co-matching-network-for-multi
Repo
Framework

An Arm-Wise Randomization Approach to Combinatorial Linear Semi-Bandits


Title	An Arm-Wise Randomization Approach to Combinatorial Linear Semi-Bandits
Authors	Kei Takemura, Shinji Ito
Abstract	Combinatorial linear semi-bandits (CLS) are widely applicable frameworks of sequential decision-making, in which a learner chooses a subset of arms from a given set of arms associated with feature vectors. Existing algorithms work poorly for the clustered case, in which the feature vectors form several large clusters. This shortcoming is critical in practice because it can be found in many applications, including recommender systems. In this paper, we clarify why such a shortcoming occurs, and we introduce a key technique of arm-wise randomization to overcome it. We propose two algorithms with this technique: the perturbed C${}^2$UCB (PC${}^2$UCB) and the Thompson sampling (TS). Our empirical evaluation with artificial and real-world datasets demonstrates that the proposed algorithms with the arm-wise randomization technique outperform the existing algorithms without this technique, especially for the clustered case. Our contributions also include theoretical analyses that provide high probability asymptotic regret bounds for our algorithms.
Tasks	Decision Making, Recommendation Systems
Published	2019-09-05
URL	https://arxiv.org/abs/1909.02251v2
PDF	https://arxiv.org/pdf/1909.02251v2.pdf
PWC	https://paperswithcode.com/paper/an-arm-wise-randomization-approach-to
Repo
Framework

WildMix Dataset and Spectro-Temporal Transformer Model for Monoaural Audio Source Separation


Title	WildMix Dataset and Spectro-Temporal Transformer Model for Monoaural Audio Source Separation
Authors	Amir Zadeh, Tianjun Ma, Soujanya Poria, Louis-Philippe Morency
Abstract	Monoaural audio source separation is a challenging research area in machine learning. In this area, a mixture containing multiple audio sources is given, and a model is expected to disentangle the mixture into isolated atomic sources. In this paper, we first introduce a challenging new dataset for monoaural source separation called WildMix. WildMix is designed with the goal of extending the boundaries of source separation beyond what previous datasets in this area would allow. It contains diverse in-the-wild recordings from 25 different sound classes, combined with each other using arbitrary composition policies. Source separation often requires modeling long-range dependencies in both temporal and spectral domains. To this end, we introduce a novel trasnformer-based model called Spectro-Temporal Transformer (STT). STT utilizes a specialized encoder, called Spectro-Temporal Encoder (STE). STE highlights temporal and spectral components of sources within a mixture, using a self-attention mechanism. It subsequently disentangles them in a hierarchical manner. In our experiments, STT swiftly outperforms various previous baselines for monoaural source separation on the challenging WildMix dataset.
Tasks
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09783v1
PDF	https://arxiv.org/pdf/1911.09783v1.pdf
PWC	https://paperswithcode.com/paper/wildmix-dataset-and-spectro-temporal
Repo
Framework

MURS: Practical and Robust Privacy Amplification with Multi-Party Differential Privacy


Title	MURS: Practical and Robust Privacy Amplification with Multi-Party Differential Privacy
Authors	Tianhao Wang, Min Xu, Bolin Ding, Jingren Zhou, Cheng Hong, Zhicong Huang, Ninghui Li, Somesh Jha
Abstract	When collecting information, local differential privacy (LDP) alleviates privacy concerns of users because their private information is randomized before being sent to the central aggregator. However, LDP results in loss of utility due to the amount of noise that is added to each individual data item. To address this issue, recent work introduced an intermediate server with the assumption that this intermediate server did not collude with the aggregator. Using this trust model, one can add less noise to achieve the same privacy guarantee; thus improving the utility. In this paper, we investigate this multiple-party setting of LDP. We first analyze the threat model and identify potential adversaries. We then make observations about existing approaches and propose new techniques that achieve a better privacy-utility tradeoff than existing ones. Finally, we perform experiments to compare different methods and demonstrate the benefits of using our proposed method.
Tasks
Published	2019-08-30
URL	https://arxiv.org/abs/1908.11515v2
PDF	https://arxiv.org/pdf/1908.11515v2.pdf
PWC	https://paperswithcode.com/paper/practical-and-robust-privacy-amplification
Repo
Framework

Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation


Title	Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation
Authors	Alireza Mehrtash, William M. Wells III, Clare M. Tempany, Purang Abolmaesumi, Tina Kapur
Abstract	Fully convolutional neural networks (FCNs), and in particular U-Nets, have achieved state-of-the-art results in semantic segmentation for numerous medical imaging applications. Moreover, batch normalization and Dice loss have been used successfully to stabilize and accelerate training. However, these networks are poorly calibrated i.e. they tend to produce overconfident predictions both in correct and erroneous classifications, making them unreliable and hard to interpret. In this paper, we study predictive uncertainty estimation in FCNs for medical image segmentation. We make the following contributions: 1) We systematically compare cross entropy loss with Dice loss in terms of segmentation quality and uncertainty estimation of FCNs; 2) We propose model ensembling for confidence calibration of the FCNs trained with batch normalization and Dice loss; 3) We assess the ability of calibrated FCNs to predict segmentation quality of structures and detect out-of-distribution test examples. We conduct extensive experiments across three medical image segmentation applications of the brain, the heart, and the prostate to evaluate our contributions. The results of this study offer considerable insight into the predictive uncertainty estimation and out-of-distribution detection in medical image segmentation and provide practical recipes for confidence calibration. Moreover, we consistently demonstrate that model ensembling improves confidence calibration.
Tasks	Calibration, Medical Image Segmentation, Out-of-Distribution Detection, Semantic Segmentation
Published	2019-11-29
URL	https://arxiv.org/abs/1911.13273v1
PDF	https://arxiv.org/pdf/1911.13273v1.pdf
PWC	https://paperswithcode.com/paper/confidence-calibration-and-predictive
Repo
Framework

Hierarchical Attention Networks for Medical Image Segmentation


Title	Hierarchical Attention Networks for Medical Image Segmentation
Authors	Fei Ding, Gang Yang, Jinlu Liu, Jun Wu, Dayong Ding, Jie Xv, Gangwei Cheng, Xirong Li
Abstract	The medical image is characterized by the inter-class indistinction, high variability, and noise, where the recognition of pixels is challenging. Unlike previous self-attention based methods that capture context information from one level, we reformulate the self-attention mechanism from the view of the high-order graph and propose a novel method, namely Hierarchical Attention Network (HANet), to address the problem of medical image segmentation. Concretely, an HA module embedded in the HANet captures context information from neighbors of multiple levels, where these neighbors are extracted from the high-order graph. In the high-order graph, there will be an edge between two nodes only if the correlation between them is high enough, which naturally reduces the noisy attention information caused by the inter-class indistinction. The proposed HA module is robust to the variance of input and can be flexibly inserted into the existing convolution neural networks. We conduct experiments on three medical image segmentation tasks including optic disc/cup segmentation, blood vessel segmentation, and lung segmentation. Extensive results show our method is more effective and robust than the existing state-of-the-art methods.
Tasks	Medical Image Segmentation, Semantic Segmentation
Published	2019-11-20
URL	https://arxiv.org/abs/1911.08777v2
PDF	https://arxiv.org/pdf/1911.08777v2.pdf
PWC	https://paperswithcode.com/paper/hierarchical-attention-networks-for-medical
Repo
Framework

Computing Estimators of Dantzig Selector type via Column and Constraint Generation


Title	Computing Estimators of Dantzig Selector type via Column and Constraint Generation
Authors	Rahul Mazumder, Stephen Wright, Andrew Zheng
Abstract	We consider a class of linear-programming based estimators in reconstructing a sparse signal from linear measurements. Specific formulations of the reconstruction problem considered here include Dantzig selector, basis pursuit (for the case in which the measurements contain no errors), and the fused Dantzig selector (for the case in which the underlying signal is piecewise constant). In spite of being estimators central to sparse signal processing and machine learning, solving these linear programming problems for large scale instances remains a challenging task, thereby limiting their usage in practice. We show that classic constraint- and column-generation techniques from large scale linear programming, when used in conjunction with a commercial implementation of the simplex method, and initialized with the solution from a closely-related Lasso formulation, yields solutions with high efficiency in many settings.
Tasks
Published	2019-08-18
URL	https://arxiv.org/abs/1908.06515v1
PDF	https://arxiv.org/pdf/1908.06515v1.pdf
PWC	https://paperswithcode.com/paper/computing-estimators-of-dantzig-selector-type
Repo
Framework

Target-Aware Deep Tracking


Title	Target-Aware Deep Tracking
Authors	Xin Li, Chao Ma, Baoyuan Wu, Zhenyu He, Ming-Hsuan Yang
Abstract	Existing deep trackers mainly use convolutional neural networks pre-trained for generic object recognition task for representations. Despite demonstrated successes for numerous vision tasks, the contributions of using pre-trained deep features for visual tracking are not as significant as that for object recognition. The key issue is that in visual tracking the targets of interest can be arbitrary object class with arbitrary forms. As such, pre-trained deep features are less effective in modeling these targets of arbitrary forms for distinguishing them from the background. In this paper, we propose a novel scheme to learn target-aware features, which can better recognize the targets undergoing significant appearance variations than pre-trained deep features. To this end, we develop a regression loss and a ranking loss to guide the generation of target-active and scale-sensitive features. We identify the importance of each convolutional filter according to the back-propagated gradients and select the target-aware features based on activations for representing the targets. The target-aware features are integrated with a Siamese matching network for visual tracking. Extensive experimental results show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of accuracy and speed.
Tasks	Object Recognition, Visual Tracking
Published	2019-04-03
URL	http://arxiv.org/abs/1904.01772v1
PDF	http://arxiv.org/pdf/1904.01772v1.pdf
PWC	https://paperswithcode.com/paper/target-aware-deep-tracking
Repo
Framework

Semi-Supervised Multi-Organ Segmentation through Quality Assurance Supervision


Title	Semi-Supervised Multi-Organ Segmentation through Quality Assurance Supervision
Authors	Ho Hin Lee, Yucheng Tang, Olivia Tang, Yuchen Xu, Yunqiang Chen, Dashan Gao, Shizhong Han, Riqiang Gao, Michael R. Savona, Richard G. Abramson, Yuankai Huo, Bennett A. Landman
Abstract	Human in-the-loop quality assurance (QA) is typically performed after medical image segmentation to ensure that the systems are performing as intended, as well as identifying and excluding outliers. By performing QA on large-scale, previously unlabeled testing data, categorical QA scores can be generatedIn this paper, we propose a semi-supervised multi-organ segmentation deep neural network consisting of a traditional segmentation model generator and a QA involved discriminator. A large-scale dataset of 2027 volumes are used to train the generator, whose 2-D montage images and segmentation mask with QA scores are used to train the discriminator. To generate the QA scores, the 2-D montage images were reviewed manually and coded 0 (success), 1 (errors consistent with published performance), and 2 (gross failure). Then, the ResNet-18 network was trained with 1623 montage images in equal distribution of all three code labels and achieved an accuracy 94% for classification predictions with 404 montage images withheld for the test cohort. To assess the performance of using the QA supervision, the discriminator was used as a loss function in a multi-organ segmentation pipeline. The inclusion of QA-loss function boosted performance on the unlabeled test dataset from 714 patients to 951 patients over the baseline model. Additionally, the number of failures decreased from 606 (29.90%) to 402 (19.83%). The contributions of the proposed method are threefold: We show that (1) the QA scores can be used as a loss function to perform semi-supervised learning for unlabeled data, (2) the well trained discriminator is learnt by QA score rather than traditional true/false, and (3) the performance of multi-organ segmentation on unlabeled datasets can be fine-tuned with more robust and higher accuracy than the original baseline method.
Tasks	Medical Image Segmentation, Semantic Segmentation
Published	2019-11-12
URL	https://arxiv.org/abs/1911.05113v1
PDF	https://arxiv.org/pdf/1911.05113v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-multi-organ-segmentation
Repo
Framework

Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory & Practice


Title	Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory & Practice
Authors	Jeroen Bertels, Tom Eelbode, Maxim Berman, Dirk Vandermeulen, Frederik Maes, Raf Bisschops, Matthew Blaschko
Abstract	The Dice score and Jaccard index are commonly used metrics for the evaluation of segmentation tasks in medical imaging. Convolutional neural networks trained for image segmentation tasks are usually optimized for (weighted) cross-entropy. This introduces an adverse discrepancy between the learning optimization objective (the loss) and the end target metric. Recent works in computer vision have proposed soft surrogates to alleviate this discrepancy and directly optimize the desired metric, either through relaxations (soft-Dice, soft-Jaccard) or submodular optimization (Lov'asz-softmax). The aim of this study is two-fold. First, we investigate the theoretical differences in a risk minimization framework and question the existence of a weighted cross-entropy loss with weights theoretically optimized to surrogate Dice or Jaccard. Second, we empirically investigate the behavior of the aforementioned loss functions w.r.t. evaluation with Dice score and Jaccard index on five medical segmentation tasks. Through the application of relative approximation bounds, we show that all surrogates are equivalent up to a multiplicative factor, and that no optimal weighting of cross-entropy exists to approximate Dice or Jaccard measures. We validate these findings empirically and show that, while it is important to opt for one of the target metric surrogates rather than a cross-entropy-based loss, the choice of the surrogate does not make a statistical difference on a wide range of medical segmentation tasks.
Tasks	Medical Image Segmentation, Semantic Segmentation
Published	2019-11-05
URL	https://arxiv.org/abs/1911.01685v1
PDF	https://arxiv.org/pdf/1911.01685v1.pdf
PWC	https://paperswithcode.com/paper/optimizing-the-dice-score-and-jaccard-index
Repo
Framework

Automated Prototype for Asteroids Detection


Title	Automated Prototype for Asteroids Detection
Authors	D. Copandean, O. Vaduvescu, D. Gorgan
Abstract	Near Earth Asteroids (NEAs) are discovered daily, mainly by few major surveys, nevertheless many of them remain unobserved for years, even decades. Even so, there is room for new discoveries, including those submitted by smaller projects and amateur astronomers. Besides the well-known surveys that have their own automated system of asteroid detection, there are only a few software solutions designed to help amateurs and mini-surveys in NEAs discovery. Some of these obtain their results based on the blink method in which a set of reduced images are shown one after another and the astronomer has to visually detect real moving objects in a series of images. This technique becomes harder with the increase in size of the CCD cameras. Aiming to replace manual detection we propose an automated pipeline prototype for asteroids detection, written in Python under Linux, which calls some 3rd party astrophysics libraries.
Tasks
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10469v1
PDF	http://arxiv.org/pdf/1901.10469v1.pdf
PWC	https://paperswithcode.com/paper/automated-prototype-for-asteroids-detection
Repo
Framework

Characterizing the Exact Behaviors of Temporal Difference Learning Algorithms Using Markov Jump Linear System Theory


Title	Characterizing the Exact Behaviors of Temporal Difference Learning Algorithms Using Markov Jump Linear System Theory
Authors	Bin Hu, Usman Ahmed Syed
Abstract	In this paper, we provide a unified analysis of temporal difference learning algorithms with linear function approximators by exploiting their connections to Markov jump linear systems (MJLS). We tailor the MJLS theory developed in the control community to characterize the exact behaviors of the first and second order moments of a large family of temporal difference learning algorithms. For both the IID and Markov noise cases, we show that the evolution of some augmented versions of the mean and covariance matrix of the TD estimation error exactly follows the trajectory of a deterministic linear time-invariant (LTI) dynamical system. Applying the well-known LTI system theory, we obtain closed-form expressions for the mean and covariance matrix of the TD estimation error at any time step. We provide a tight matrix spectral radius condition to guarantee the convergence of the covariance matrix of the TD estimation error, and perform a perturbation analysis to characterize the dependence of the TD behaviors on learning rate. For the IID case, we provide an exact formula characterizing how the mean and covariance matrix of the TD estimation error converge to the steady state values. For the Markov case, we use our formulas to explain how the behaviors of TD learning algorithms are affected by learning rate and the underlying Markov chain. For both cases, upper and lower bounds for the mean square TD error are provided. The mean square TD error is shown to converge linearly to an exact limit.
Tasks
Published	2019-06-16
URL	https://arxiv.org/abs/1906.06781v3
PDF	https://arxiv.org/pdf/1906.06781v3.pdf
PWC	https://paperswithcode.com/paper/characterizing-the-exact-behaviors-of
Repo
Framework

Alternating Between Spectral and Spatial Estimation for Speech Separation and Enhancement


Title	Alternating Between Spectral and Spatial Estimation for Speech Separation and Enhancement
Authors	Zhong-Qiu Wang, Scott Wisdom, Kevin Wilson, John R. Hershey
Abstract	This work investigates alternation between spectral separation using masking-based networks and spatial separation using multichannel beamforming. In this framework, the spectral separation is performed using a mask-based deep network. The result of mask-based separation is used, in turn, to estimate a spatial beamformer. The output of the beamformer is fed back into another mask-based separation network. We explore multiple ways of computing time-varying covariance matrices to improve beamforming, including factorizing the spatial covariance into a time-varying amplitude component and time-invariant spatial component. For the subsequent mask-based filtering, we consider different modes, including masking the noisy input, masking the beamformer output, and a hybrid approach combining both. Our best method first uses spectral separation, then spatial beamforming, and finally a spectral post-filter, and demonstrates an average improvement of 2.8 dB over baseline mask-based separation, across four different reverberant speech enhancement and separation tasks.
Tasks	Speech Enhancement, Speech Separation
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07953v1
PDF	https://arxiv.org/pdf/1911.07953v1.pdf
PWC	https://paperswithcode.com/paper/alternating-between-spectral-and-spatial
Repo
Framework

PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition


Title	PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition
Authors	Kun Su, Xiulong Liu, Eli Shlizerman
Abstract	We propose a novel system for unsupervised skeleton-based action recognition. Given inputs of body keypoints sequences obtained during various movements, our system associates the sequences with actions. Our system is based on an encoder-decoder recurrent neural network, where the encoder learns a separable feature representation within its hidden states formed by training the model to perform prediction task. We show that according to such unsupervised training the decoder and the encoder self-organize their hidden states into a feature space which clusters similar movements into the same cluster and distinct movements into distant clusters. Current state-of-the-art methods for action recognition are strongly supervised, i.e., rely on providing labels for training. Unsupervised methods have been proposed, however, they require camera and depth inputs (RGB+D) at each time step. In contrast, our system is fully unsupervised, does not require labels of actions at any stage, and can operate with body keypoints input only. Furthermore, the method can perform on various dimensions of body keypoints (2D or 3D) and include additional cues describing movements. We evaluate our system on three extensive action recognition benchmarks with different number of actions and examples. Our results outperform prior unsupervised skeleton-based methods, unsupervised RGB+D based methods on cross-view tests and while being unsupervised have similar performance to supervised skeleton-based action recognition.
Tasks	Skeleton Based Action Recognition
Published	2019-11-27
URL	https://arxiv.org/abs/1911.12409v1
PDF	https://arxiv.org/pdf/1911.12409v1.pdf
PWC	https://paperswithcode.com/paper/predict-cluster-unsupervised-skeleton-based
Repo
Framework