January 29, 2020

3069 words 15 mins read

Paper Group ANR 612

TimeCaps: Learning From Time Series Data with Capsule Networks. Analyzing Utility of Visual Context in Multimodal Speech Recognition Under Noisy Conditions. Weak Supervision Enhanced Generative Network for Question Generation. Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signals. Detecting Radical Text over Online Media …

TimeCaps: Learning From Time Series Data with Capsule Networks


Title	TimeCaps: Learning From Time Series Data with Capsule Networks
Authors	Hirunima Jayasekara, Vinoj Jayasundara, Jathushan Rajasegaran, Sandaru Jayasekara, Suranga Seneviratne, Ranga Rodrigo
Abstract	Capsule networks excel in understanding spatial relationships in 2D data for vision related tasks. Even though they are not designed to capture 1D temporal relationships, with TimeCaps we demonstrate that given the ability, capsule networks excel in understanding temporal relationships. To this end, we generate capsules along the temporal and channel dimensions creating two temporal feature detectors which learn contrasting relationships. TimeCaps surpasses the state-of-the-art results by achieving 96.21% accuracy on identifying 13 Electrocardiogram (ECG) signal beat categories, while achieving on-par results on identifying 30 classes of short audio commands. Further, the instantiation parameters inherently learnt by the capsule networks allow us to completely parameterize 1D signals which opens various possibilities in signal processing.
Tasks	Time Series
Published	2019-11-26
URL	https://arxiv.org/abs/1911.11800v3
PDF	https://arxiv.org/pdf/1911.11800v3.pdf
PWC	https://paperswithcode.com/paper/timecaps-capturing-time-series-data-with
Repo
Framework

Analyzing Utility of Visual Context in Multimodal Speech Recognition Under Noisy Conditions


Title	Analyzing Utility of Visual Context in Multimodal Speech Recognition Under Noisy Conditions
Authors	Tejas Srinivasan, Ramon Sanabria, Florian Metze
Abstract	Multimodal learning allows us to leverage information from multiple sources (visual, acoustic and text), similar to our experience of the real world. However, it is currently unclear to what extent auxiliary modalities improve performance over unimodal models, and under what circumstances the auxiliary modalities are useful. We examine the utility of the auxiliary visual context in Multimodal Automatic Speech Recognition in adversarial settings, where we deprive the models from partial audio signal during inference time. Our experiments show that while MMASR models show significant gains over traditional speech-to-text architectures (upto 4.2% WER improvements), they do not incorporate visual information when the audio signal has been corrupted. This shows that current methods of integrating the visual modality do not improve model robustness to noise, and we need better visually grounded adaptation techniques.
Tasks	Speech Recognition
Published	2019-06-30
URL	https://arxiv.org/abs/1907.00477v2
PDF	https://arxiv.org/pdf/1907.00477v2.pdf
PWC	https://paperswithcode.com/paper/analyzing-utility-of-visual-context-in
Repo
Framework

Weak Supervision Enhanced Generative Network for Question Generation


Title	Weak Supervision Enhanced Generative Network for Question Generation
Authors	Yutong Wang, Jiyuan Zheng, Qijiong Liu, Zhou Zhao, Jun Xiao, Yueting Zhuang
Abstract	Automatic question generation according to an answer within the given passage is useful for many applications, such as question answering system, dialogue system, etc. Current neural-based methods mostly take two steps which extract several important sentences based on the candidate answer through manual rules or supervised neural networks and then use an encoder-decoder framework to generate questions about these sentences. These approaches neglect the semantic relations between the answer and the context of the whole passage which is sometimes necessary for answering the question. To address this problem, we propose the Weak Supervision Enhanced Generative Network (WeGen) which automatically discovers relevant features of the passage given the answer span in a weakly supervised manner to improve the quality of generated questions. More specifically, we devise a discriminator, Relation Guider, to capture the relations between the whole passage and the associated answer and then the Multi-Interaction mechanism is deployed to transfer the knowledge dynamically for our question generation system. Experiments show the effectiveness of our method in both automatic evaluations and human evaluations.
Tasks	Question Answering, Question Generation
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00607v1
PDF	https://arxiv.org/pdf/1907.00607v1.pdf
PWC	https://paperswithcode.com/paper/weak-supervision-enhanced-generative-network
Repo
Framework

Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signals


Title	Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signals
Authors	Yunhan Huang, Quanyan Zhu
Abstract	This paper studies reinforcement learning (RL) under malicious falsification on cost signals and introduces a quantitative framework of attack models to understand the vulnerabilities of RL. Focusing on $Q$-learning, we show that $Q$-learning algorithms converge under stealthy attacks and bounded falsifications on cost signals. We characterize the relation between the falsified cost and the $Q$-factors as well as the policy learned by the learning agent which provides fundamental limits for feasible offensive and defensive moves. We propose a robust region in terms of the cost within which the adversary can never achieve the targeted policy. We provide conditions on the falsified cost which can mislead the agent to learn an adversary’s favored policy. A numerical case study of water reservoir control is provided to show the potential hazards of RL in learning-based control systems and corroborate the results.
Tasks	Q-Learning
Published	2019-06-24
URL	https://arxiv.org/abs/1906.10571v3
PDF	https://arxiv.org/pdf/1906.10571v3.pdf
PWC	https://paperswithcode.com/paper/deceptive-reinforcement-learning-under
Repo
Framework

Detecting Radical Text over Online Media using Deep Learning


Title	Detecting Radical Text over Online Media using Deep Learning
Authors	Armaan Kaur, Jaspal Kaur Saini, Divya Bansal
Abstract	Social Media has influenced the way people socially connect, interact and opinionize. The growth in technology has enhanced communication and dissemination of information. Unfortunately,many terror groups like jihadist communities have started consolidating a virtual community online for various purposes such as recruitment, online donations, targeting youth online and spread of extremist ideologies. Everyday a large number of articles, tweets, posts, posters, blogs, comments, views and news are posted online without a check which in turn imposes a threat to the security of any nation. However, different agencies are working on getting down this radical content from various online social media platforms. The aim of our paper is to utilise deep learning algorithm in detection of radicalization contrary to the existing works based on machine learning algorithms. An LSTM based feed forward neural network is employed to detect radical content. We collected total 61601 records from various online sources constituting news, articles and blogs. These records are annotated by domain experts into three categories: Radical(R), Non-Radical (NR) and Irrelevant(I) which are further applied to LSTM based network to classify radical content. A precision of 85.9% has been achieved with the proposed approach
Tasks
Published	2019-07-22
URL	https://arxiv.org/abs/1907.12368v2
PDF	https://arxiv.org/pdf/1907.12368v2.pdf
PWC	https://paperswithcode.com/paper/detecting-radical-text-over-online-media
Repo
Framework

A Note on Posterior Probability Estimation for Classifiers


Title	A Note on Posterior Probability Estimation for Classifiers
Authors	Georgi Nalbantov, Svetoslav Ivanov
Abstract	One of the central themes in the classification task is the estimation of class posterior probability at a new point $\bf{x}$. The vast majority of classifiers output a score for $\bf{x}$, which is monotonically related to the posterior probability via an unknown relationship. There are many attempts in the literature to estimate this latter relationship. Here, we provide a way to estimate the posterior probability without resorting to using classification scores. Instead, we vary the prior probabilities of classes in order to derive the ratio of pdf’s at point $\bf{x}$, which is directly used to determine class posterior probabilities. We consider here the binary classification problem.
Tasks
Published	2019-09-12
URL	https://arxiv.org/abs/1909.05894v1
PDF	https://arxiv.org/pdf/1909.05894v1.pdf
PWC	https://paperswithcode.com/paper/a-note-on-posterior-probability-estimation
Repo
Framework

A Latent Feelings-aware RNN Model for User Churn Prediction with Behavioral Data


Title	A Latent Feelings-aware RNN Model for User Churn Prediction with Behavioral Data
Authors	Meng Xi, Zhiling Luo, Naibo Wang, Jianwei Yin
Abstract	Predicting user churn and taking personalized measures to retain users is a set of common and effective practices for online game operators. However, different from the traditional user churn relevant researches that can involve demographic, economic, and behavioral data, most online games can only obtain logs of user behavior and have no access to users’ latent feelings. There are mainly two challenges in this work: 1. The latent feelings, which cannot be directly observed in this work, need to be estimated and verified; 2. User churn needs to be predicted with only behavioral data. In this work, a Recurrent Neural Network(RNN) called LaFee (Latent Feeling) is proposed, which can get the users’ latent feelings while predicting user churn. Besides, we proposed a method named BMM-UCP (Behavior-based Modeling Method for User Churn Prediction) to help models predict user churn with only behavioral data. The latent feelings are names as satisfaction and aspiration in this work. We designed experiments on a real dataset and the results show that our methods outperform baselines and are more suitable for long-term sequential learning. The latent feelings learned are fully discussed and proven meaningful.
Tasks
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02224v1
PDF	https://arxiv.org/pdf/1911.02224v1.pdf
PWC	https://paperswithcode.com/paper/a-latent-feelings-aware-rnn-model-for-user
Repo
Framework

Strong Equivalence for LPMLN Programs


Title	Strong Equivalence for LPMLN Programs
Authors	Joohyung Lee, Man Luo
Abstract	LPMLN is a probabilistic extension of answer set programs with the weight scheme adapted from Markov Logic. We study the concept of strong equivalence in LPMLN, which is a useful mathematical tool for simplifying a part of an LPMLN program without looking at the rest of it. We show that the verification of strong equivalence in LPMLN can be reduced to equivalence checking in classical logic via a reduct and choice rules as well as to equivalence checking under the “soft” logic of here-and-there. The result allows us to leverage an answer set solver for LPMLN strong equivalence checking. The study also suggests us a few reformulations of the LPMLN semantics using choice rules, the logic of here-and-there, and classical logic.
Tasks
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08998v1
PDF	https://arxiv.org/pdf/1909.08998v1.pdf
PWC	https://paperswithcode.com/paper/strong-equivalence-for-lpmln-programs
Repo
Framework

Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis


Title	Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis
Authors	Wen Liu, Zhixin Piao, Jie Min, Wenhan Luo, Lin Ma, Shenghua Gao
Abstract	We tackle the human motion imitation, appearance transfer, and novel view synthesis within a unified framework, which means that the model once being trained can be used to handle all these tasks. The existing task-specific methods mainly use 2D keypoints (pose) to estimate the human body structure. However, they only expresses the position information with no abilities to characterize the personalized shape of the individual person and model the limbs rotations. In this paper, we propose to use a 3D body mesh recovery module to disentangle the pose and shape, which can not only model the joint location and rotation but also characterize the personalized body shape. To preserve the source information, such as texture, style, color, and face identity, we propose a Liquid Warping GAN with Liquid Warping Block (LWB) that propagates the source information in both image and feature spaces, and synthesizes an image with respect to the reference. Specifically, the source features are extracted by a denoising convolutional auto-encoder for characterizing the source identity well. Furthermore, our proposed method is able to support a more flexible warping from multiple sources. In addition, we build a new dataset, namely Impersonator (iPER) dataset, for the evaluation of human motion imitation, appearance transfer, and novel view synthesis. Extensive experiments demonstrate the effectiveness of our method in several aspects, such as robustness in occlusion case and preserving face identity, shape consistency and clothes details. All codes and datasets are available on https://svip-lab.github.io/project/impersonator.html
Tasks	Denoising, Novel View Synthesis
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12224v3
PDF	https://arxiv.org/pdf/1909.12224v3.pdf
PWC	https://paperswithcode.com/paper/liquid-warping-gan-a-unified-framework-for
Repo
Framework

Exploit fully automatic low-level segmented PET data for training high-level deep learning algorithms for the corresponding CT data


Title	Exploit fully automatic low-level segmented PET data for training high-level deep learning algorithms for the corresponding CT data
Authors	Christina Gsaxner, Peter M. Roth, Jürgen Wallner, Jan Egger
Abstract	We present an approach for fully automatic urinary bladder segmentation in CT images with artificial neural networks in this study. Automatic medical image analysis has become an invaluable tool in the different treatment stages of diseases. Especially medical image segmentation plays a vital role, since segmentation is often the initial step in an image analysis pipeline. Since deep neural networks have made a large impact on the field of image processing in the past years, we use two different deep learning architectures to segment the urinary bladder. Both of these architectures are based on pre-trained classification networks that are adapted to perform semantic segmentation. Since deep neural networks require a large amount of training data, specifically images and corresponding ground truth labels, we furthermore propose a method to generate such a suitable training data set from Positron Emission Tomography/Computed Tomography image data. This is done by applying thresholding to the Positron Emission Tomography data for obtaining a ground truth and by utilizing data augmentation to enlarge the dataset. In this study, we discuss the influence of data augmentation on the segmentation results, and compare and evaluate the proposed architectures in terms of qualitative and quantitative segmentation performance. The results presented in this study allow concluding that deep neural networks can be considered a promising approach to segment the urinary bladder in CT images.
Tasks	Data Augmentation, Medical Image Segmentation, Semantic Segmentation
Published	2019-03-07
URL	http://arxiv.org/abs/1903.02871v1
PDF	http://arxiv.org/pdf/1903.02871v1.pdf
PWC	https://paperswithcode.com/paper/exploit-fully-automatic-low-level-segmented
Repo
Framework

Probing Multilingual Sentence Representations With X-Probe


Title	Probing Multilingual Sentence Representations With X-Probe
Authors	Vinit Ravishankar, Lilja Øvrelid, Erik Velldal
Abstract	This paper extends the task of probing sentence representations for linguistic insight in a multilingual domain. In doing so, we make two contributions: first, we provide datasets for multilingual probing, derived from Wikipedia, in five languages, viz. English, French, German, Spanish and Russian. Second, we evaluate six sentence encoders for each language, each trained by mapping sentence representations to English sentence representations, using sentences in a parallel corpus. We discover that cross-lingually mapped representations are often better at retaining certain linguistic information than representations derived from English encoders trained on natural language inference (NLI) as a downstream task.
Tasks	Natural Language Inference
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05061v1
PDF	https://arxiv.org/pdf/1906.05061v1.pdf
PWC	https://paperswithcode.com/paper/probing-multilingual-sentence-representations
Repo
Framework


Title	Deep Learning of Preconditioners for Conjugate Gradient Solvers in Urban Water Related Problems
Authors	Johannes Sappl, Laurent Seiler, Matthias Harders, Wolfgang Rauch
Abstract	Solving systems of linear equations is a problem occuring frequently in water engineering applications. Usually the size of the problem is too large to be solved via direct factorization. One can resort to iterative approaches, in particular the conjugate gradients method if the matrix is symmetric positive definite. Preconditioners further enhance the rate of convergence but hitherto only handcrafted ones requiring expert knowledge have been used. We propose an innovative approach employing Machine Learning, in particular a Convolutional Neural Network, to unassistedly design preconditioning matrices specifically for the problem at hand. Based on an in-depth case study in fluid simulation we are able to show that our learned preconditioner is able to improve the convergence rate even beyond well established methods like incomplete Cholesky factorization or Algebraic MultiGrid.
Tasks
Published	2019-06-17
URL	https://arxiv.org/abs/1906.06925v1
PDF	https://arxiv.org/pdf/1906.06925v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-of-preconditioners-for
Repo
Framework

Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning


Title	Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning
Authors	Xugong Qin, Yu Zhou, Dongbao Yang, Weiping Wang
Abstract	Detecting curved text in the wild is very challenging. Recently, most state-of-the-art methods are segmentation based and require pixel-level annotations. We propose a novel scheme to train an accurate text detector using only a small amount of pixel-level annotated data and a large amount of data annotated with rectangles or even unlabeled data. A baseline model is first obtained by training with the pixel-level annotated data and then used to annotate unlabeled or weakly labeled data. A novel strategy which utilizes ground-truth bounding boxes to generate pseudo mask annotations is proposed in weakly-supervised learning. Experimental results on CTW1500 and Total-Text demonstrate that our method can substantially reduce the requirement of pixel-level annotated data. Our method can also generalize well across two datasets. The performance of the proposed method is comparable with the state-of-the-art methods with only 10% pixel-level annotated data and 90% rectangle-level weakly annotated data.
Tasks	Curved Text Detection
Published	2019-08-27
URL	https://arxiv.org/abs/1908.09990v1
PDF	https://arxiv.org/pdf/1908.09990v1.pdf
PWC	https://paperswithcode.com/paper/curved-text-detection-in-natural-scene-images
Repo
Framework

Machine learning in APOGEE: Identification of stellar populations through chemical abundances


Title	Machine learning in APOGEE: Identification of stellar populations through chemical abundances
Authors	Rafael Garcia-Dias, Carlos Allende Prieto, Jorge Sánchez Almeida, Pedro Alonso Palicio
Abstract	The vast volume of data generated by modern astronomical surveys offers test beds for the application of machine-learning. It is important to evaluate potential existing tools and determine those that are optimal for extracting scientific knowledge from the available observations. We explore the possibility of using clustering algorithms to separate stellar populations with distinct chemical patterns. Star clusters are likely the most chemically homogeneous populations in the Galaxy, and therefore any practical approach to identifying distinct stellar populations should at least be able to separate clusters from each other. We applied eight clustering algorithms combined with four dimensionality reduction strategies to automatically distinguish stellar clusters using chemical abundances of 13 elements. Our sample includes 18 stellar clusters with a total of 453 stars. We use statistical tests showing that some pairs of clusters are indistinguishable from each other when chemical abundances from the Apache Point Galactic Evolution Experiment (APOGEE) are used. However, for most clusters we are able to automatically assign membership with metric scores similar to previous works. The confusion level of the automatically selected clusters is consistent with statistical tests that demonstrate the impossibility of perfectly distinguishing all the clusters from each other. These statistical tests and confusion levels establish a limit for the prospect of blindly identifying stars born in the same cluster based solely on chemical abundances. We find that some of the algorithms we explored are capable of blindly identify stellar populations with similar ages and chemical distributions in the APOGEE data. Because some stellar clusters are chemically indistinguishable, our study supports the notion of extending weak chemical tagging that involves families of clusters instead of individual clusters
Tasks	Dimensionality Reduction
Published	2019-07-30
URL	https://arxiv.org/abs/1907.12796v1
PDF	https://arxiv.org/pdf/1907.12796v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-in-apogee-identification-of
Repo
Framework

General Regression Neural Networks, Radial Basis Function Neural Networks, Support Vector Machines, and Feedforward Neural Networks


Title	General Regression Neural Networks, Radial Basis Function Neural Networks, Support Vector Machines, and Feedforward Neural Networks
Authors	Alison Jenkins, Vinika Gupta, Mary Lenoir
Abstract	The aim of this project is to develop a code to discover the optimal sigma value that maximum the F1 score and the optimal sigma value that maximizes the accuracy and to find out if they are the same. Four algorithms which can be used to solve this problem are: Genetic Regression Neural Networks (GRNNs), Radial Based Function (RBF) Neural Networks (RBFNNs), Support Vector Machines (SVMs) and Feedforward Neural Network (FFNNs).
Tasks
Published	2019-11-16
URL	https://arxiv.org/abs/1911.07115v1
PDF	https://arxiv.org/pdf/1911.07115v1.pdf
PWC	https://paperswithcode.com/paper/general-regression-neural-networks-radial
Repo
Framework