January 27, 2020

3203 words 16 mins read

Paper Group ANR 1269

The FACTS of Technology-Assisted Sensitivity Review. k-GANs: Ensemble of Generative Models with Semi-Discrete Optimal Transport. Anytime Lane-Level Intersection Estimation Based on Trajectories of Other Traffic Participants. Data Priming Network for Automatic Check-Out. I-vector Based Features Embedding for Heart Sound Classification. Complicated T …

The FACTS of Technology-Assisted Sensitivity Review


Title	The FACTS of Technology-Assisted Sensitivity Review
Authors	Graham McDonald, Craig Macdonald, Iadh Ounis
Abstract	At least ninety countries implement Freedom of Information laws that state that government documents must be made freely available, or opened, to the public. However, many government documents contain sensitive information, such as personal or confidential information. Therefore, all government documents that are opened to the public must first be reviewed to identify, and protect, any sensitive information. Historically, sensitivity review has been a completely manual process. However, with the adoption of born-digital documents, such as e-mail, human-only sensitivity review is not practical and there is a need for new technologies to assist human sensitivity reviewers. In this paper, we discuss how issues of fairness, accountability, confidentiality, transparency and safety (FACTS) impact technology-assisted sensitivity review. Moreover, we outline some important areas of future FACTS research that will need to be addressed within technology-assisted sensitivity review.
Tasks
Published	2019-07-05
URL	https://arxiv.org/abs/1907.02956v1
PDF	https://arxiv.org/pdf/1907.02956v1.pdf
PWC	https://paperswithcode.com/paper/the-facts-of-technology-assisted-sensitivity
Repo
Framework

k-GANs: Ensemble of Generative Models with Semi-Discrete Optimal Transport


Title	k-GANs: Ensemble of Generative Models with Semi-Discrete Optimal Transport
Authors	Luca Ambrogioni, Umut Güçlü, Marcel van Gerven
Abstract	Generative adversarial networks (GANs) are the state of the art in generative modeling. Unfortunately, most GAN methods are susceptible to mode collapse, meaning that they tend to capture only a subset of the modes of the true distribution. A possible way of dealing with this problem is to use an ensemble of GANs, where (ideally) each network models a single mode. In this paper, we introduce a principled method for training an ensemble of GANs using semi-discrete optimal transport theory. In our approach, each generative network models the transportation map between a point mass (Dirac measure) and the restriction of the data distribution on a tile of a Voronoi tessellation that is defined by the location of the point masses. We iteratively train the generative networks and the point masses until convergence. The resulting k-GANs algorithm has strong theoretical connection with the k-medoids algorithm. In our experiments, we show that our ensemble method consistently outperforms baseline GANs.
Tasks
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04050v1
PDF	https://arxiv.org/pdf/1907.04050v1.pdf
PWC	https://paperswithcode.com/paper/k-gans-ensemble-of-generative-models-with
Repo
Framework

Anytime Lane-Level Intersection Estimation Based on Trajectories of Other Traffic Participants


Title	Anytime Lane-Level Intersection Estimation Based on Trajectories of Other Traffic Participants
Authors	Annika Meyer, Jonas Walter, Martin Lauer, Christoph Stiller
Abstract	Estimating and understanding the current scene is an inevitable capability of automated vehicles. Usually, maps are used as prior for interpreting sensor measurements in order to drive safely and comfortably. Only few approaches take into account that maps might be outdated and lead to wrong assumptions on the environment. This work estimates a lane-level intersection topology without any map prior by observing the trajectories of other traffic participants. We are able to deliver both a coarse lane-level topology as well as the lane course inside and outside of the intersection using Markov chain Monte Carlo sampling. The model is neither limited to a number of lanes or arms nor to the topology of the intersection. We present our results on an evaluation set of 1000 simulated intersections and achieve 99.9% accuracy on the topology estimation that takes only 36ms, when utilizing tracked object detections. The precise lane course on these intersections is estimated with an error of 15cm on average after 140ms. Our approach shows a similar level of precision on 14 real-world intersections with 18cm average deviation on simple intersections and 27cm for more complex scenarios. Here the estimation takes only 113ms in total.
Tasks
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02495v2
PDF	https://arxiv.org/pdf/1906.02495v2.pdf
PWC	https://paperswithcode.com/paper/anytime-lane-level-intersection-estimation
Repo
Framework

Data Priming Network for Automatic Check-Out


Title	Data Priming Network for Automatic Check-Out
Authors	Congcong Li, Dawei Du, Libo Zhang, Tiejian Luo, Yanjun Wu, Qi Tian, Longyin Wen, Siwei Lyu
Abstract	Automatic Check-Out (ACO) receives increased interests in recent years. An important component of the ACO system is the visual item counting, which recognizes the categories and counts of the items chosen by the customers. However, the training of such a system is challenged by the domain adaptation problem, in which the training data are images from isolated items while the testing images are for collections of items. Existing methods solve this problem with data augmentation using synthesized images, but the image synthesis leads to unreal images that affect the training process. In this paper, we propose a new data priming method to solve the domain adaptation problem. Specifically, we first use pre-augmentation data priming, in which we remove distracting background from the training images using the coarse-to-fine strategy and select images with realistic view angles by the pose pruning method. In the post-augmentation step, we train a data priming network using detection and counting collaborative learning, and select more reliable images from testing data to fine-tune the final visual item tallying network. Experiments on the large scale Retail Product Checkout (RPC) dataset demonstrate the superiority of the proposed method, i.e., we achieve 80.51% checkout accuracy compared with 56.68% of the baseline methods. The source codes can be found in https://isrc.iscas.ac.cn/gitlab/research/acm-mm-2019-ACO.
Tasks	Data Augmentation, Domain Adaptation, Image Generation
Published	2019-04-10
URL	https://arxiv.org/abs/1904.04978v3
PDF	https://arxiv.org/pdf/1904.04978v3.pdf
PWC	https://paperswithcode.com/paper/data-priming-network-for-automatic-check-out
Repo
Framework

I-vector Based Features Embedding for Heart Sound Classification


Title	I-vector Based Features Embedding for Heart Sound Classification
Authors	Mohammad Adiban, Bagher BabaAli, Saeedreza Shehnepoor
Abstract	Cardiovascular Disease (CVD) is considered as one of the principal causes of death in the world. Over recent years, this field of study has attracted researchers’ attention to investigate heart sounds’ patterns for disease diagnostics. In this study, an approach is proposed for normal/abnormal heart sound classification on the Physionet challenge 2016 dataset. For the first time, a fixed length feature vector; called i-vector; is extracted from each heart sound using Mel Frequency Cepstral Coefficient (MFCC) features. Afterwards, Principal Component Analysis (PCA) transform and Variational Autoencoder (VAE) are applied on the i-vector to achieve dimension reduction. Eventually, the reduced size vector is fed to Gaussian Mixture Models (GMMs) and Support Vector Machine (SVM) for classification purpose. Experimental results demonstrate the proposed method could achieve a performance improvement of 16% based on Modified Accuracy (MAcc) compared with the baseline system on the Physionet2016 dataset.
Tasks	Dimensionality Reduction
Published	2019-04-26
URL	https://arxiv.org/abs/1904.11914v2
PDF	https://arxiv.org/pdf/1904.11914v2.pdf
PWC	https://paperswithcode.com/paper/i-vector-based-features-embedding-for-heart
Repo
Framework

Complicated Table Structure Recognition


Title	Complicated Table Structure Recognition
Authors	Zewen Chi, Heyan Huang, Heng-Da Xu, Houjin Yu, Wanxuan Yin, Xian-Ling Mao
Abstract	The task of table structure recognition aims to recognize the internal structure of a table, which is a key step to make machines understand tables. Currently, there are lots of studies on this task for different file formats such as ASCII text and HTML. It also attracts lots of attention to recognize the table structures in PDF files. However, it is hard for the existing methods to accurately recognize the structure of complicated tables in PDF files. The complicated tables contain spanning cells which occupy at least two columns or rows. To address the issue, we propose a novel graph neural network for recognizing the table structure in PDF files, named GraphTSR. Specifically, it takes table cells as input, and then recognizes the table structures by predicting relations among cells. Moreover, to evaluate the task better, we construct a large-scale table structure recognition dataset from scientific papers, named SciTSR, which contains 15,000 tables from PDF files and their corresponding structure labels. Extensive experiments demonstrate that our proposed model is highly effective for complicated tables and outperforms state-of-the-art baselines over a benchmark dataset and our new constructed dataset.
Tasks
Published	2019-08-13
URL	https://arxiv.org/abs/1908.04729v2
PDF	https://arxiv.org/pdf/1908.04729v2.pdf
PWC	https://paperswithcode.com/paper/complicated-table-structure-recognition
Repo
Framework

Low-Variance and Zero-Variance Baselines for Extensive-Form Games


Title	Low-Variance and Zero-Variance Baselines for Extensive-Form Games
Authors	Trevor Davis, Martin Schmid, Michael Bowling
Abstract	Extensive-form games (EFGs) are a common model of multi-agent interactions with imperfect information. State-of-the-art algorithms for solving these games typically perform full walks of the game tree that can prove prohibitively slow in large games. Alternatively, sampling-based methods such as Monte Carlo Counterfactual Regret Minimization walk one or more trajectories through the tree, touching only a fraction of the nodes on each iteration, at the expense of requiring more iterations to converge due to the variance of sampled values. In this paper, we extend recent work that uses baseline estimates to reduce this variance. We introduce a framework of baseline-corrected values in EFGs that generalizes the previous work. Within our framework, we propose new baseline functions that result in significantly reduced variance compared to existing techniques. We show that one particular choice of such a function — predictive baseline — is provably optimal under certain sampling schemes. This allows for efficient computation of zero-variance value estimates even along sampled trajectories.
Tasks
Published	2019-07-22
URL	https://arxiv.org/abs/1907.09633v1
PDF	https://arxiv.org/pdf/1907.09633v1.pdf
PWC	https://paperswithcode.com/paper/low-variance-and-zero-variance-baselines-for
Repo
Framework

Hypothesis Set Stability and Generalization


Title	Hypothesis Set Stability and Generalization
Authors	Dylan J. Foster, Spencer Greenberg, Satyen Kale, Haipeng Luo, Mehryar Mohri, Karthik Sridharan
Abstract	We present an extensive study of generalization for data-dependent hypothesis sets. We give a general learning guarantee for data-dependent hypothesis sets based on a notion of transductive Rademacher complexity. Our main results are two generalization bounds for data-dependent hypothesis sets expressed in terms of a notion of hypothesis set stability and a notion of Rademacher complexity for data-dependent hypothesis sets that we introduce. These bounds admit as special cases both standard Rademacher complexity bounds and algorithm-dependent uniform stability bounds. We also illustrate the use of these learning bounds in the analysis of several scenarios.
Tasks
Published	2019-04-09
URL	http://arxiv.org/abs/1904.04755v2
PDF	http://arxiv.org/pdf/1904.04755v2.pdf
PWC	https://paperswithcode.com/paper/hypothesis-set-stability-and-generalization
Repo
Framework

Classification of Resting-State fMRI using Evolutionary Algorithms: Towards a Brain Imaging Biomarker for Parkinson’s Disease


Title	Classification of Resting-State fMRI using Evolutionary Algorithms: Towards a Brain Imaging Biomarker for Parkinson’s Disease
Authors	Amir Dehsarvi, Stephen L. Smith
Abstract	Accurate early diagnosis and monitoring of neurodegenerative conditions is essential for effective disease management and delivery of medication and treatment. This research develops automatic methods for detecting brain imaging preclinical biomarkers for Parkinson’s disease (PD) by considering the novel application of evolutionary algorithms. A fundamental novel element of this work is the use of evolutionary algorithms to both map and predict the functional connectivity in patients using resting state functional MRI data taken from the PPMI to identify PD progression biomarkers. Specifically, Cartesian Genetic Programming was used to classify DCM data as well as time-series data. The findings were validated using two other commonly used classification methods (Artificial Neural Networks and Support Vector Machines) and by employing k-fold cross-validation. Across DCM and time-series analyses, findings revealed maximum accuracies of 75.21% for early stage (prodromal) PD patients versus healthy controls, 85.87% for PD patients versus prodromal PD patients, and 92.09% for PD patients versus healthy controls. Prodromal PD patients were classified from healthy controls with high accuracy - this is notable and represents the key finding of this research since current methods of diagnosing prodromal PD have both low reliability and low accuracy. Furthermore, Cartesian Genetic Programming provided comparable performance accuracy relative to ANN and SVM. Evolutionary algorithms enable us to decode the classifier in terms of understanding the data inputs that are used, more easily than in ANN and SVM. Hence, these findings underscore the relevance of both DCM analyses for classification and CGP as a novel classification tool for brain imaging data with medical implications for disease diagnosis, particularly in early and asymptomatic stages.
Tasks	Time Series
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05378v1
PDF	https://arxiv.org/pdf/1910.05378v1.pdf
PWC	https://paperswithcode.com/paper/classification-of-resting-state-fmri-using
Repo
Framework

LANTERN: learn analysis transform network for dynamic magnetic resonance imaging with small dataset


Title	LANTERN: learn analysis transform network for dynamic magnetic resonance imaging with small dataset
Authors	Shanshan Wang, Yanxia Chen, Taohui Xiao, Ziwen Ke, Qiegen Liu, Hairong Zheng
Abstract	This paper proposes to learn analysis transform network for dynamic magnetic resonance imaging (LANTERN) with small dataset. Integrating the strength of CS-MRI and deep learning, the proposed framework is highlighted in three components: (i) The spatial and temporal domains are sparsely constrained by using adaptively trained CNN. (ii) We introduce an end-to-end framework to learn the parameters in LANTERN to solve the difficulty of parameter selection in traditional methods. (iii) Compared to existing deep learning reconstruction methods, our reconstruction accuracy is better when the amount of data is limited. Our model is able to fully exploit the redundancy in spatial and temporal of dynamic MR images. We performed quantitative and qualitative analysis of cardiac datasets at different acceleration factors (2x-11x) and different undersampling modes. In comparison with state-of-the-art methods, extensive experiments show that our method achieves consistent better reconstruction performance on the MRI reconstruction in terms of three quantitative metrics (PSNR, SSIM and HFEN) under different undersamling patterns and acceleration factors.
Tasks
Published	2019-08-24
URL	https://arxiv.org/abs/1908.09140v1
PDF	https://arxiv.org/pdf/1908.09140v1.pdf
PWC	https://paperswithcode.com/paper/lantern-learn-analysis-transform-network-for
Repo
Framework

Embedding Projection for Targeted Cross-Lingual Sentiment: Model Comparisons and a Real-World Study


Title	Embedding Projection for Targeted Cross-Lingual Sentiment: Model Comparisons and a Real-World Study
Authors	Jeremy Barnes, Roman Klinger
Abstract	Sentiment analysis benefits from large, hand-annotated resources in order to train and test machine learning models, which are often data hungry. While some languages, e.g., English, have a vast array of these resources, most under-resourced languages do not, especially for fine-grained sentiment tasks, such as aspect-level or targeted sentiment analysis. To improve this situation, we propose a cross-lingual approach to sentiment analysis that is applicable to under-resourced languages and takes into account target-level information. This model incorporates sentiment information into bilingual distributional representations, by jointly optimizing them for semantics and sentiment, showing state-of-the-art performance at sentence-level when combined with machine translation. The adaptation to targeted sentiment analysis on multiple domains shows that our model outperforms other projection-based bilingual embedding methods on binary targeted sentiment tasks. Our analysis on ten languages demonstrates that the amount of unlabeled monolingual data has surprisingly little effect on the sentiment results. As expected, the choice of annotated source language for projection to a target leads to better results for source-target language pairs which are similar. Therefore, our results suggest that more efforts should be spent on the creation of resources for less similar languages to those which are resource-rich already. Finally, a domain mismatch leads to a decreased performance. This suggests resources in any language should ideally cover varieties of domains.
Tasks	Machine Translation, Sentiment Analysis
Published	2019-06-24
URL	https://arxiv.org/abs/1906.10519v1
PDF	https://arxiv.org/pdf/1906.10519v1.pdf
PWC	https://paperswithcode.com/paper/embedding-projection-for-targeted-cross
Repo
Framework

Ensemble Decision Systems for General Video Game Playing


Title	Ensemble Decision Systems for General Video Game Playing
Authors	Damien Anderson, Cristina Guerrero-Romero, Diego Perez-Liebana, Philip Rodgers, John Levine
Abstract	Ensemble Decision Systems offer a unique form of decision making that allows a collection of algorithms to reason together about a problem. Each individual algorithm has its own inherent strengths and weaknesses, and often it is difficult to overcome the weaknesses while retaining the strengths. Instead of altering the properties of the algorithm, the Ensemble Decision System augments the performance with other algorithms that have complementing strengths. This work outlines different options for building an Ensemble Decision System as well as providing analysis on its performance compared to the individual components of the system with interesting results, showing an increase in the generality of the algorithms without significantly impeding performance.
Tasks	Decision Making
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10792v1
PDF	https://arxiv.org/pdf/1905.10792v1.pdf
PWC	https://paperswithcode.com/paper/ensemble-decision-systems-for-general-video
Repo
Framework

Data description and retrieval using periods represented by uncertain time intervals


Title	Data description and retrieval using periods represented by uncertain time intervals
Authors	Tatsuki Sekino
Abstract	Time periods are frequently used to specify time in metadata and retrieval. However, it is not easy to describe and retrieve information about periods, because the temporal ranges represented by periods are often ambiguous. This is because these temporal ranges do not have fixed beginning and end points. To solve this problem, basic logics to describe and process uncertain time intervals were developed in this study. An uncertain time interval is represented as a set of time intervals that indicate states when the uncertain time interval is determined. Based on this concept, a logic to retrieve uncertain time intervals satisfying a given condition was established, and it was revealed that retrieval results belong to three states: reliable, impossible, and possible matches. Additionally, to describe data about uncertain periods, an ontology (the HuTime Ontology) was constructed based on the logic. This ontology is characterized by the fact that uncertain time intervals can be defined recursively. It is expected that more data about time periods will be created and released using the result of this study.
Tasks
Published	2019-05-11
URL	https://arxiv.org/abs/1905.04611v2
PDF	https://arxiv.org/pdf/1905.04611v2.pdf
PWC	https://paperswithcode.com/paper/data-description-and-retrieval-using-periods
Repo
Framework

Generating Natural Language Explanations for Visual Question Answering using Scene Graphs and Visual Attention


Title	Generating Natural Language Explanations for Visual Question Answering using Scene Graphs and Visual Attention
Authors	Shalini Ghosh, Giedrius Burachas, Arijit Ray, Avi Ziskind
Abstract	In this paper, we present a novel approach for the task of eXplainable Question Answering (XQA), i.e., generating natural language (NL) explanations for the Visual Question Answering (VQA) problem. We generate NL explanations comprising of the evidence to support the answer to a question asked to an image using two sources of information: (a) annotations of entities in an image (e.g., object labels, region descriptions, relation phrases) generated from the scene graph of the image, and (b) the attention map generated by a VQA model when answering the question. We show how combining the visual attention map with the NL representation of relevant scene graph entities, carefully selected using a language model, can give reasonable textual explanations without the need of any additional collected data (explanation captions, etc). We run our algorithms on the Visual Genome (VG) dataset and conduct internal user-studies to demonstrate the efficacy of our approach over a strong baseline. We have also released a live web demo showcasing our VQA and textual explanation generation using scene graphs and visual attention.
Tasks	Language Modelling, Question Answering, Visual Question Answering
Published	2019-02-15
URL	http://arxiv.org/abs/1902.05715v1
PDF	http://arxiv.org/pdf/1902.05715v1.pdf
PWC	https://paperswithcode.com/paper/generating-natural-language-explanations-for
Repo
Framework

On the Benefits of Attributional Robustness


Title	On the Benefits of Attributional Robustness
Authors	Mayank Singh, Nupur Kumari, Puneet Mangla, Abhishek Sinha, Vineeth N Balasubramanian, Balaji Krishnamurthy
Abstract	Interpretability is an emerging area of research in trustworthy machine learning. Safe deployment of machine learning system mandates that the prediction and its explanation be reliable and robust. Recently, it was shown that one could craft perturbations that produce perceptually indistinguishable inputs having the same prediction, yet very different interpretations. We tackle the problem of attributional robustness (i.e. models having robust explanations) by maximizing the alignment between the input image and its saliency map using soft-margin triplet loss. We propose a robust attribution training methodology that beats the state-of-the-art attributional robustness measure by a margin of approximately 6-18% on several standard datasets, ie. SVHN, CIFAR-10 and GTSRB. We further show the utility of the proposed robust model in the domain of weakly supervised object localization and segmentation. Our proposed robust model also achieves a new state-of-the-art object localization accuracy on the CUB-200 dataset.
Tasks	Object Localization, Weakly-Supervised Object Localization
Published	2019-11-29
URL	https://arxiv.org/abs/1911.13073v3
PDF	https://arxiv.org/pdf/1911.13073v3.pdf
PWC	https://paperswithcode.com/paper/on-the-benefits-of-attributional-robustness
Repo
Framework