October 17, 2019

3368 words 16 mins read

Paper Group ANR 746

Text to brain: predicting the spatial distribution of neuroimaging observations from text reports. Actor-Critic based Training Framework for Abstractive Summarization. A Spatial and Temporal Features Mixture Model with Body Parts for Video-based Person Re-Identification. Distribution Assertive Regression. Deep Learning in the Wild. Unsupervised Sep …

Text to brain: predicting the spatial distribution of neuroimaging observations from text reports


Title	Text to brain: predicting the spatial distribution of neuroimaging observations from text reports
Authors	Jérôme Dockès, Demian Wassermann, Russell Poldrack, Fabian Suchanek, Bertrand Thirion, Gaël Varoquaux
Abstract	Despite the digital nature of magnetic resonance imaging, the resulting observations are most frequently reported and stored in text documents. There is a trove of information untapped in medical health records, case reports, and medical publications. In this paper, we propose to mine brain medical publications to learn the spatial distribution associated with anatomical terms. The problem is formulated in terms of minimization of a risk on distributions which leads to a least-deviation cost function. An efficient algorithm in the dual then learns the mapping from documents to brain structures. Empirical results using coordinates extracted from the brain-imaging literature show that i) models must adapt to semantic variation in the terms used to describe a given anatomical structure, ii) voxel-wise parameterization leads to higher likelihood of locations reported in unseen documents, iii) least-deviation cost outperforms least-square. As a proof of concept for our method, we use our model of spatial distributions to predict the distribution of specific neurological conditions from text-only reports.
Tasks
Published	2018-06-04
URL	http://arxiv.org/abs/1806.01139v3
PDF	http://arxiv.org/pdf/1806.01139v3.pdf
PWC	https://paperswithcode.com/paper/text-to-brain-predicting-the-spatial
Repo
Framework

Actor-Critic based Training Framework for Abstractive Summarization


Title	Actor-Critic based Training Framework for Abstractive Summarization
Authors	Piji Li, Lidong Bing, Wai Lam
Abstract	We present a training framework for neural abstractive summarization based on actor-critic approaches from reinforcement learning. In the traditional neural network based methods, the objective is only to maximize the likelihood of the predicted summaries, no other assessment constraints are considered, which may generate low-quality summaries or even incorrect sentences. To alleviate this problem, we employ an actor-critic framework to enhance the training procedure. For the actor, we employ the typical attention based sequence-to-sequence (seq2seq) framework as the policy network for summary generation. For the critic, we combine the maximum likelihood estimator with a well designed global summary quality estimator which is a neural network based binary classifier aiming to make the generated summaries indistinguishable from the human-written ones. Policy gradient method is used to conduct the parameter learning. An alternating training strategy is proposed to conduct the joint training of the actor and critic models. Extensive experiments on some benchmark datasets in different languages show that our framework achieves improvements over the state-of-the-art methods.
Tasks	Abstractive Text Summarization
Published	2018-03-28
URL	http://arxiv.org/abs/1803.11070v2
PDF	http://arxiv.org/pdf/1803.11070v2.pdf
PWC	https://paperswithcode.com/paper/actor-critic-based-training-framework-for
Repo
Framework

A Spatial and Temporal Features Mixture Model with Body Parts for Video-based Person Re-Identification


Title	A Spatial and Temporal Features Mixture Model with Body Parts for Video-based Person Re-Identification
Authors	Jie Liu, Cheng Sun, Xiang Xu, Baomin Xu, Shuangyuan Yu
Abstract	The video-based person re-identification is to recognize a person under different cameras, which is a crucial task applied in visual surveillance system. Most previous methods mainly focused on the feature of full body in the frame. In this paper we propose a novel Spatial and Temporal Features Mixture Model (STFMM) based on convolutional neural network (CNN) and recurrent neural network (RNN), in which the human body is split into $N$ parts in horizontal direction so that we can obtain more specific features. The proposed method skillfully integrates features of each part to achieve more expressive representation of each person. We first split the video sequence into $N$ part sequences which include the information of head, waist, legs and so on. Then the features are extracted by STFMM whose $2N$ inputs are obtained from the developed Siamese network, and these features are combined into a discriminative representation for one person. Experiments are conducted on the iLIDS-VID and PRID-2011 datasets. The results demonstrate that our approach outperforms existing methods for video-based person re-identification. It achieves a rank-1 CMC accuracy of 74% on the iLIDS-VID dataset, exceeding the the most recently developed method ASTPN by 12%. For the cross-data testing, our method achieves a rank-1 CMC accuracy of 48% exceeding the ASTPN method by 18%, which shows that our model has significant stability.
Tasks	Person Re-Identification, Video-Based Person Re-Identification
Published	2018-07-03
URL	http://arxiv.org/abs/1807.00975v1
PDF	http://arxiv.org/pdf/1807.00975v1.pdf
PWC	https://paperswithcode.com/paper/a-spatial-and-temporal-features-mixture-model
Repo
Framework

Distribution Assertive Regression


Title	Distribution Assertive Regression
Authors	Kumarjit Pathak, Jitin Kapila, Aasheesh Barvey, Nikit Gawande
Abstract	In regression modelling approach, the main step is to fit the regression line as close as possible to the target variable. In this process most algorithms try to fit all of the data in a single line and hence fitting all parts of target variable in one go. It was observed that the error between predicted and target variable usually have a varying behavior across the various quantiles of the dependent variable and hence single point diagnostic like MAPE has its limitation to signify the level of fitness across the distribution of Y(dependent variable). To address this problem, a novel approach is proposed in the paper to deal with regression fitting over various quantiles of target variable. Using this approach we have significantly improved the eccentric behavior of the distance (error) between predicted and actual value of regression. Our proposed solution is based on understanding the segmented behavior of the data with respect to the internal segments within the data and approach for retrospectively fitting the data based on each quantile behavior. We believe exploring and using this approach would help in achieving better and more explainable results in most settings of real world data modelling problems.
Tasks
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01618v1
PDF	http://arxiv.org/pdf/1805.01618v1.pdf
PWC	https://paperswithcode.com/paper/distribution-assertive-regression
Repo
Framework

Deep Learning in the Wild


Title	Deep Learning in the Wild
Authors	Thilo Stadelmann, Mohammadreza Amirian, Ismail Arabaci, Marek Arnold, Gilbert François Duivesteijn, Ismail Elezi, Melanie Geiger, Stefan Lörwald, Benjamin Bruno Meier, Katharina Rombach, Lukas Tuggener
Abstract	Deep learning with neural networks is applied by an increasing number of people outside of classic research environments, due to the vast success of the methodology on a wide range of machine perception tasks. While this interest is fueled by beautiful success stories, practical work in deep learning on novel tasks without existing baselines remains challenging. This paper explores the specific challenges arising in the realm of real world tasks, based on case studies from research & development in conjunction with industry, and extracts lessons learned from them. It thus fills a gap between the publication of latest algorithmic and methodical developments, and the usually omitted nitty-gritty of how to make them work. Specifically, we give insight into deep learning projects on face matching, print media monitoring, industrial quality control, music scanning, strategy game playing, and automated machine learning, thereby providing best practices for deep learning in practice.
Tasks
Published	2018-07-13
URL	http://arxiv.org/abs/1807.04950v1
PDF	http://arxiv.org/pdf/1807.04950v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-in-the-wild
Repo
Framework

Unsupervised Separation of Transliterable and Native Words for Malayalam


Title	Unsupervised Separation of Transliterable and Native Words for Malayalam
Authors	Deepak P
Abstract	Differentiating intrinsic language words from transliterable words is a key step aiding text processing tasks involving different natural languages. We consider the problem of unsupervised separation of transliterable words from native words for text in Malayalam language. Outlining a key observation on the diversity of characters beyond the word stem, we develop an optimization method to score words based on their nativeness. Our method relies on the usage of probability distributions over character n-grams that are refined in step with the nativeness scorings in an iterative optimization formulation. Using an empirical evaluation, we illustrate that our method, DTIM, provides significant improvements in nativeness scoring for Malayalam, establishing DTIM as the preferred method for the task.
Tasks
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09641v1
PDF	http://arxiv.org/pdf/1803.09641v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-separation-of-transliterable-and
Repo
Framework

A Generative Model of Textures Using Hierarchical Probabilistic Principal Component Analysis


Title	A Generative Model of Textures Using Hierarchical Probabilistic Principal Component Analysis
Authors	Aiga Suzuki, Hayaru Shouno
Abstract	Modeling of textures in natural images is an important task to make a microscopic model of natural images. Portilla and Simoncelli proposed a generative texture model, which is based on the mechanism of visual systems in brains, with a set of texture features and a feature matching. On the other hand, the texture features, used in Portillas’ model, have redundancy between its components came from typical natural textures. In this paper, we propose a contracted texture model which provides a dimension reduction for the Portillas’ feature. This model is based on a hierarchical principal components analysis using known group structure of the feature. In the experiment, we reveal effective dimensions to describe texture is fewer than the original description. Moreover, we also demonstrate how well the textures can be synthesized from the contracted texture representations.
Tasks	Dimensionality Reduction
Published	2018-10-16
URL	http://arxiv.org/abs/1810.06892v1
PDF	http://arxiv.org/pdf/1810.06892v1.pdf
PWC	https://paperswithcode.com/paper/a-generative-model-of-textures-using
Repo
Framework

Modeling Localness for Self-Attention Networks


Title	Modeling Localness for Self-Attention Networks
Authors	Baosong Yang, Zhaopeng Tu, Derek F. Wong, Fandong Meng, Lidia S. Chao, Tong Zhang
Abstract	Self-attention networks have proven to be of profound value for its strength of capturing global dependencies. In this work, we propose to model localness for self-attention networks, which enhances the ability of capturing useful local context. We cast localness modeling as a learnable Gaussian bias, which indicates the central and scope of the local region to be paid more attention. The bias is then incorporated into the original attention distribution to form a revised distribution. To maintain the strength of capturing long distance dependencies and enhance the ability of capturing short-range dependencies, we only apply localness modeling to lower layers of self-attention networks. Quantitative and qualitative analyses on Chinese-English and English-German translation tasks demonstrate the effectiveness and universality of the proposed approach.
Tasks
Published	2018-10-24
URL	http://arxiv.org/abs/1810.10182v1
PDF	http://arxiv.org/pdf/1810.10182v1.pdf
PWC	https://paperswithcode.com/paper/modeling-localness-for-self-attention
Repo
Framework

Rademacher Complexity and Generalization Performance of Multi-category Margin Classifiers


Title	Rademacher Complexity and Generalization Performance of Multi-category Margin Classifiers
Authors	Khadija Musayeva, Fabien Lauer, Yann Guermeur
Abstract	One of the main open problems in the theory of multi-category margin classification is the form of the optimal dependency of a guaranteed risk on the number C of categories, the sample size m and the margin parameter gamma. From a practical point of view, the theoretical analysis of generalization performance contributes to the development of new learning algorithms. In this paper, we focus only on the theoretical aspect of the question posed. More precisely, under minimal learnability assumptions, we derive a new risk bound for multi-category margin classifiers. We improve the dependency on C over the state of the art when the margin loss function considered satisfies the Lipschitz condition. We start with the basic supremum inequality that involves a Rademacher complexity as a capacity measure. This capacity measure is then linked to the metric entropy through the chaining method. In this context, our improvement is based on the introduction of a new combinatorial metric entropy bound.
Tasks
Published	2018-12-03
URL	http://arxiv.org/abs/1812.00584v1
PDF	http://arxiv.org/pdf/1812.00584v1.pdf
PWC	https://paperswithcode.com/paper/rademacher-complexity-and-generalization
Repo
Framework

Deep Autoencoder for Recommender Systems: Parameter Influence Analysis


Title	Deep Autoencoder for Recommender Systems: Parameter Influence Analysis
Authors	Dai Hoang Tran, Zawar Hussain, Wei Emma Zhang, Nguyen Lu Dang Khoa, Nguyen H. Tran, Quan Z. Sheng
Abstract	Recommender systems have recently attracted many researchers in the deep learning community. The state-of-the-art deep neural network models used in recommender systems are typically multilayer perceptron and deep Autoencoder (DAE), among which DAE usually shows better performance due to its superior capability to reconstruct the inputs. However, we found existing DAE recommendation systems that have similar implementations on similar datasets result in vastly different parameter settings. In this work, we have built a flexible DAE model, named FlexEncoder that uses configurable parameters and unique features to analyse the parameter influences on the prediction accuracy of recommender systems. This will help us identify the best-performance parameters given a dataset. Extensive evaluation on the MovieLens datasets are conducted, which drives our conclusions on the influences of DAE parameters. Specifically, we find that DAE parameters strongly affect the prediction accuracy of the recommender systems, and the effect is transferable to similar datasets in a larger size. We open our code to public which could benefit both new users for DAE – they can quickly understand how DAE works for recommendation systems, and experienced DAE users – it easier for them to tune the parameters on different datasets.
Tasks	Recommendation Systems
Published	2018-12-25
URL	http://arxiv.org/abs/1901.00415v1
PDF	http://arxiv.org/pdf/1901.00415v1.pdf
PWC	https://paperswithcode.com/paper/deep-autoencoder-for-recommender-systems
Repo
Framework

Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching


Title	Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching
Authors	Chen Qu, Feng Ji, Minghui Qiu, Liu Yang, Zhiyu Min, Haiqing Chen, Jun Huang, W. Bruce Croft
Abstract	Deep text matching approaches have been widely studied for many applications including question answering and information retrieval systems. To deal with a domain that has insufficient labeled data, these approaches can be used in a Transfer Learning (TL) setting to leverage labeled data from a resource-rich source domain. To achieve better performance, source domain data selection is essential in this process to prevent the “negative transfer” problem. However, the emerging deep transfer models do not fit well with most existing data selection methods, because the data selection policy and the transfer learning model are not jointly trained, leading to sub-optimal training efficiency. In this paper, we propose a novel reinforced data selector to select high-quality source domain data to help the TL model. Specifically, the data selector “acts” on the source domain data to find a subset for optimization of the TL model, and the performance of the TL model can provide “rewards” in turn to update the selector. We build the reinforced data selector based on the actor-critic framework and integrate it to a DNN based transfer learning model, resulting in a Reinforced Transfer Learning (RTL) method. We perform a thorough experimental evaluation on two major tasks for text matching, namely, paraphrase identification and natural language inference. Experimental results show the proposed RTL can significantly improve the performance of the TL model. We further investigate different settings of states, rewards, and policy optimization methods to examine the robustness of our method. Last, we conduct a case study on the selected data and find our method is able to select source domain data whose Wasserstein distance is close to the target domain data. This is reasonable and intuitive as such source domain data can provide more transferability power to the model.
Tasks	Information Retrieval, Natural Language Inference, Paraphrase Identification, Question Answering, Text Matching, Transfer Learning
Published	2018-12-30
URL	http://arxiv.org/abs/1812.11561v1
PDF	http://arxiv.org/pdf/1812.11561v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-selectively-transfer-reinforced
Repo
Framework

A Structured Learning Approach with Neural Conditional Random Fields for Sleep Staging


Title	A Structured Learning Approach with Neural Conditional Random Fields for Sleep Staging
Authors	Karan Aggarwal, Swaraj Khadanga, Shafiq R. Joty, Louis Kazaglis, Jaideep Srivastava
Abstract	Sleep plays a vital role in human health, both mental and physical. Sleep disorders like sleep apnea are increasing in prevalence, with the rapid increase in factors like obesity. Sleep apnea is most commonly treated with Continuous Positive Air Pressure (CPAP) therapy. Presently, however, there is no mechanism to monitor a patient’s progress with CPAP. Accurate detection of sleep stages from CPAP flow signal is crucial for such a mechanism. We propose, for the first time, an automated sleep staging model based only on the flow signal. Deep neural networks have recently shown high accuracy on sleep staging by eliminating handcrafted features. However, these methods focus exclusively on extracting informative features from the input signal, without paying much attention to the dynamics of sleep stages in the output sequence. We propose an end-to-end framework that uses a combination of deep convolution and recurrent neural networks to extract high-level features from raw flow signal with a structured output layer based on a conditional random field to model the temporal transition structure of the sleep stages. We improve upon the previous methods by 10% using our model, that can be augmented to the previous sleep staging deep learning methods. We also show that our method can be used to accurately track sleep metrics like sleep efficiency calculated from sleep stages that can be deployed for monitoring the response of CPAP therapy on sleep apnea patients. Apart from the technical contributions, we expect this study to motivate new research questions in sleep science.
Tasks
Published	2018-07-23
URL	http://arxiv.org/abs/1807.09119v2
PDF	http://arxiv.org/pdf/1807.09119v2.pdf
PWC	https://paperswithcode.com/paper/a-structured-learning-approach-with-neural
Repo
Framework

Video Summarization Using Fully Convolutional Sequence Networks


Title	Video Summarization Using Fully Convolutional Sequence Networks
Authors	Mrigank Rochan, Linwei Ye, Yang Wang
Abstract	This paper addresses the problem of video summarization. Given an input video, the goal is to select a subset of the frames to create a summary video that optimally captures the important information of the input video. With the large amount of videos available online, video summarization provides a useful tool that assists video search, retrieval, browsing, etc. In this paper, we formulate video summarization as a sequence labeling problem. Unlike existing approaches that use recurrent models, we propose fully convolutional sequence models to solve video summarization. We firstly establish a novel connection between semantic segmentation and video summarization, and then adapt popular semantic segmentation networks for video summarization. Extensive experiments and analysis on two benchmark datasets demonstrate the effectiveness of our models.
Tasks	Semantic Segmentation, Video Summarization
Published	2018-05-26
URL	http://arxiv.org/abs/1805.10538v2
PDF	http://arxiv.org/pdf/1805.10538v2.pdf
PWC	https://paperswithcode.com/paper/video-summarization-using-fully-convolutional
Repo
Framework

Robust Counterfactual Inferences using Feature Learning and their Applications


Title	Robust Counterfactual Inferences using Feature Learning and their Applications
Authors	Abhimanyu Mitra, Kannan Achan, Sushant Kumar
Abstract	In a wide variety of applications, including personalization, we want to measure the difference in outcome due to an intervention and thus have to deal with counterfactual inference. The feedback from a customer in any of these situations is only ‘bandit feedback’ - that is, a partial feedback based on whether we chose to intervene or not. Typically randomized experiments are carried out to understand whether an intervention is overall better than no intervention. Here we present a feature learning algorithm to learn from a randomized experiment where the intervention in consideration is most effective and where it is least effective rather than only focusing on the overall impact, thus adding a context to our learning mechanism and extract more information. From the randomized experiment, we learn the feature representations which divide the population into subpopulations where we observe statistically significant difference in average customer feedback between those who were subjected to the intervention and those who were not, with a level of significance l, where l is a configurable parameter in our model. We use this information to derive the value of the intervention in consideration for each instance in the population. With experiments, we show that using this additional learning, in future interventions, the context for each instance could be leveraged to decide whether to intervene or not.
Tasks	Counterfactual Inference
Published	2018-08-22
URL	http://arxiv.org/abs/1808.07569v1
PDF	http://arxiv.org/pdf/1808.07569v1.pdf
PWC	https://paperswithcode.com/paper/robust-counterfactual-inferences-using
Repo
Framework

LivDet 2017 Fingerprint Liveness Detection Competition 2017


Title	LivDet 2017 Fingerprint Liveness Detection Competition 2017
Authors	Valerio Mura, Giulia Orrù, Roberto Casula, Alessandra Sibiriu, Giulia Loi, Pierluigi Tuveri, Luca Ghiani, Gian Luca Marcialis
Abstract	Fingerprint Presentation Attack Detection (FPAD) deals with distinguishing images coming from artificial replicas of the fingerprint characteristic, made up of materials like silicone, gelatine or latex, and images coming from alive fingerprints. Images are captured by modern scanners, typically relying on solid-state or optical technologies. Since from 2009, the Fingerprint Liveness Detection Competition (LivDet) aims to assess the performance of the state-of-the-art algorithms according to a rigorous experimental protocol and, at the same time, a simple overview of the basic achievements. The competition is open to all academics research centers and all companies that work in this field. The positive, increasing trend of the participants number, which supports the success of this initiative, is confirmed even this year: 17 algorithms were submitted to the competition, with a larger involvement of companies and academies. This means that the topic is relevant for both sides, and points out that a lot of work must be done in terms of fundamental and applied research.
Tasks
Published	2018-03-14
URL	http://arxiv.org/abs/1803.05210v1
PDF	http://arxiv.org/pdf/1803.05210v1.pdf
PWC	https://paperswithcode.com/paper/livdet-2017-fingerprint-liveness-detection
Repo
Framework