January 29, 2020

2826 words 14 mins read

Paper Group ANR 623

Cross-modal Variational Auto-encoder with Distributed Latent Spaces and Associators. Switching Linear Dynamics for Variational Bayes Filtering. Cross-Resolution Learning for Face Recognition. Coupled-Projection Residual Network for MRI Super-Resolution. Fast and Robust Rank Aggregation against Model Misspecification. Context-Constrained Accurate Co …


Title	Cross-modal Variational Auto-encoder with Distributed Latent Spaces and Associators
Authors	Dae Ung Jo, ByeongJu Lee, Jongwon Choi, Haanju Yoo, Jin Young Choi
Abstract	In this paper, we propose a novel structure for a cross-modal data association, which is inspired by the recent research on the associative learning structure of the brain. We formulate the cross-modal association in Bayesian inference framework realized by a deep neural network with multiple variational auto-encoders and variational associators. The variational associators transfer the latent spaces between auto-encoders that represent different modalities. The proposed structure successfully associates even heterogeneous modal data and easily incorporates the additional modality to the entire network via the proposed cross-modal associator. Furthermore, the proposed structure can be trained with only a small amount of paired data since auto-encoders can be trained by unsupervised manner. Through experiments, the effectiveness of the proposed structure is validated on various datasets including visual and auditory data.
Tasks	Bayesian Inference
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12867v1
PDF	https://arxiv.org/pdf/1905.12867v1.pdf
PWC	https://paperswithcode.com/paper/cross-modal-variational-auto-encoder-with
Repo
Framework

Switching Linear Dynamics for Variational Bayes Filtering


Title	Switching Linear Dynamics for Variational Bayes Filtering
Authors	Philip Becker-Ehmck, Jan Peters, Patrick van der Smagt
Abstract	System identification of complex and nonlinear systems is a central problem for model predictive control and model-based reinforcement learning. Despite their complexity, such systems can often be approximated well by a set of linear dynamical systems if broken into appropriate subsequences. This mechanism not only helps us find good approximations of dynamics, but also gives us deeper insight into the underlying system. Leveraging Bayesian inference, Variational Autoencoders and Concrete relaxations, we show how to learn a richer and more meaningful state space, e.g. encoding joint constraints and collisions with walls in a maze, from partial and high-dimensional observations. This representation translates into a gain of accuracy of learned dynamics showcased on various simulated tasks.
Tasks	Bayesian Inference
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12434v1
PDF	https://arxiv.org/pdf/1905.12434v1.pdf
PWC	https://paperswithcode.com/paper/switching-linear-dynamics-for-variational
Repo
Framework

Cross-Resolution Learning for Face Recognition


Title	Cross-Resolution Learning for Face Recognition
Authors	Fabio Valerio Massoli, Giuseppe Amato, Fabrizio Falchi
Abstract	Convolutional Neural Networks have reached extremely high performances on the Face Recognition task. Largely used datasets, such as VGGFace2, focus on gender, pose and age variations trying to balance them to achieve better results. However, the fact that images have different resolutions is not usually discussed and resize to 256 pixels before cropping is used. While specific datasets for very low resolution faces have been proposed, less attention has been payed on the task of cross-resolution matching. Such scenarios are of particular interest for forensic and surveillance systems in which it usually happens that a low-resolution probe has to be matched with higher-resolution galleries. While it is always possible to either increase the resolution of the probe image or to reduce the size of the gallery images, to the best of our knowledge an extensive experimentation of cross-resolution matching was missing in the recent deep learning based literature. In the context of low- and cross-resolution Face Recognition, the contributions of our work are: i) we proposed a training method to fine-tune a state-of-the-art model in order to make it able to extract resolution-robust deep features; ii) we tested our models on the benchmark datasets IJB-B/C considering images at both full and low resolutions in order to show the effectiveness of the proposed training algorithm. To the best of our knowledge, this is the first work testing extensively the performance of a FR model in a cross-resolution scenario; iii) we tested our models on the low resolution and low quality datasets QMUL-SurvFace and TinyFace and showed their superior performances, even though we did not train our model on low-resolution faces only and our main focus was cross-resolution; iv) we showed that our approach can be more effective with respect to preprocessing faces with super resolution techniques.
Tasks	Face Recognition, Super-Resolution
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02851v1
PDF	https://arxiv.org/pdf/1912.02851v1.pdf
PWC	https://paperswithcode.com/paper/cross-resolution-learning-for-face
Repo
Framework

Coupled-Projection Residual Network for MRI Super-Resolution


Title	Coupled-Projection Residual Network for MRI Super-Resolution
Authors	Chun-Mei Feng, Kai Wang, Shijian Lu, Yong Xu, Heng Kong, Ling Shao
Abstract	Magnetic Resonance Imaging(MRI) has been widely used in clinical application and pathology research by helping doctors make more accurate diagnoses. On the other hand, accurate diagnosis by MRI remains a great challenge as images obtained via present MRI techniques usually have low resolutions. Improving MRI image quality and resolution thus becomes a critically important task. This paper presents an innovative Coupled-Projection Residual Network (CPRN) for MRI super-resolution. The CPRN consists of two complementary sub-networks: a shallow network and a deep network that keep the content consistency while learning high frequency differences between low-resolution and high-resolution images. The shallow sub-network employs coupled-projection for better retaining the MRI image details, where a novel feedback mechanism is introduced to guide the reconstruction of high-resolution images. The deep sub-network learns from the residuals of the high-frequency image information, where multiple residual blocks are cascaded to magnify the MRI images at the last network layer. Finally, the features from the shallow and deep sub-networks are fused for the reconstruction of high-resolution MRI images. For effective fusion of features from the deep and shallow sub-networks, a step-wise connection (CPRN S) is designed as inspired by the human cognitive processes (from simple to complex). Experiments over three public MRI datasets show that our proposed CPRN achieves superior MRI super-resolution performance as compared with the state-of-the-art. Our source code will be publicly available at http://www.yongxu.org/lunwen.html.
Tasks	Super-Resolution
Published	2019-07-12
URL	https://arxiv.org/abs/1907.05598v1
PDF	https://arxiv.org/pdf/1907.05598v1.pdf
PWC	https://paperswithcode.com/paper/coupled-projection-residual-network-for-mri
Repo
Framework

Fast and Robust Rank Aggregation against Model Misspecification


Title	Fast and Robust Rank Aggregation against Model Misspecification
Authors	Yuangang Pan, Weijie Chen, Gang Niu, Ivor W. Tsang, Masashi Sugiyama
Abstract	In rank aggregation, preferences from different users are summarized into a total order under the homogeneous data assumption. Thus, model misspecification arises and rank aggregation methods take some noise models into account. However, they all rely on certain noise model assumptions and cannot handle agnostic noises in the real world. In this paper, we propose CoarsenRank, which rectifies the underlying data distribution directly and aligns it to the homogeneous data assumption without involving any noise model. To this end, we define a neighborhood of the data distribution over which Bayesian inference of CoarsenRank is performed, and therefore the resultant posterior enjoys robustness against model misspecification. Further, we derive a tractable closed-form solution for CoarsenRank making it computationally efficient. Experiments on real-world datasets show that CoarsenRank is fast and robust, achieving consistent improvement over baseline methods.
Tasks	Bayesian Inference
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12341v1
PDF	https://arxiv.org/pdf/1905.12341v1.pdf
PWC	https://paperswithcode.com/paper/fast-and-robust-rank-aggregation-against
Repo
Framework

Context-Constrained Accurate Contour Extraction for Occlusion Edge Detection


Title	Context-Constrained Accurate Contour Extraction for Occlusion Edge Detection
Authors	Rui Lu, Menghan Zhou, Anlong Ming, Yu Zhou
Abstract	Occlusion edge detection requires both accurate locations and context constraints of the contour. Existing CNN-based pipeline does not utilize adaptive methods to filter the noise introduced by low-level features. To address this dilemma, we propose a novel Context-constrained accurate Contour Extraction Network (CCENet). Spatial details are retained and contour-sensitive context is augmented through two extraction blocks, respectively. Then, an elaborately designed fusion module is available to integrate features, which plays a complementary role to restore details and remove clutter. Weight response of attention mechanism is eventually utilized to enhance occluded contours and suppress noise. The proposed CCENet significantly surpasses state-of-the-art methods on PIOD and BSDS ownership dataset of object edge detection and occlusion orientation detection.
Tasks	Edge Detection
Published	2019-03-21
URL	http://arxiv.org/abs/1903.08890v1
PDF	http://arxiv.org/pdf/1903.08890v1.pdf
PWC	https://paperswithcode.com/paper/context-constrained-accurate-contour
Repo
Framework

PMD: An Optimal Transportation-based User Distance for Recommender Systems


Title	PMD: An Optimal Transportation-based User Distance for Recommender Systems
Authors	Yitong Meng, Xinyan Dai, Xiao Yan, James Cheng, Weiwen Liu, Benben Liao, Jun Guo, Guangyong Chen
Abstract	Collaborative filtering, a widely-used recommendation technique, predicts a user’s preference by aggregating the ratings from similar users. As a result, these measures cannot fully utilize the rating information and are not suitable for real world sparse data. To solve these issues, we propose a novel user distance measure named Preference Mover’s Distance (PMD) which makes full use of all ratings made by each user. Our proposed PMD can properly measure the distance between a pair of users even if they have no co-rated items. We show that this measure can be cast as an instance of the Earth Mover’s Distance, a well-studied transportation problem for which several highly efficient solvers have been developed. Experimental results show that PMD can help achieve superior recommendation accuracy than state-of-the-art methods, especially when training data is very sparse.
Tasks	Recommendation Systems
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04239v2
PDF	https://arxiv.org/pdf/1909.04239v2.pdf
PWC	https://paperswithcode.com/paper/pmd-a-new-user-distance-for-recommender
Repo
Framework

Vehicle Detection in Deep Learning


Title	Vehicle Detection in Deep Learning
Authors	Yao Xiao
Abstract	Computer vision is developing rapidly with the support of deep learning techniques. This thesis proposes an advanced vehicle-detection model based on an improvement to classical convolutional neural networks. The advanced model was applied against a vehicle detection benchmark and was built to detect on-road objects. First, we propose a high-level architecture for our advanced model, which utilizes different state-of-the-art deep learning techniques. Then, we utilize the residual neural networks and region proposal network to achieve competitive performance according to the vehicle detection benchmark. Lastly, we describe the developing trend of vehicle detection techniques and the future direction of research.
Tasks
Published	2019-05-29
URL	https://arxiv.org/abs/1905.13390v1
PDF	https://arxiv.org/pdf/1905.13390v1.pdf
PWC	https://paperswithcode.com/paper/190513390
Repo
Framework

Generalized Zero-shot ICD Coding


Title	Generalized Zero-shot ICD Coding
Authors	Congzheng Song, Shanghang Zhang, Najmeh Sadoughi, Pengtao Xie, Eric Xing
Abstract	The International Classification of Diseases (ICD) is a list of classification codes for the diagnoses. Automatic ICD coding is in high demand as the manual coding can be labor-intensive and error-prone. It is a multi-label text classification task with extremely long-tailed label distribution, making it difficult to perform fine-grained classification on both frequent and zero-shot codes at the same time. In this paper, we propose a latent feature generation framework for generalized zero-shot ICD coding, where we aim to improve the prediction on codes that have no labeled data without compromising the performance on seen codes. Our framework generates pseudo features conditioned on the ICD code descriptions and exploits the ICD code hierarchical structure. To guarantee the semantic consistency between the generated features and real features, we reconstruct the keywords in the input documents that are related to the conditioned ICD codes. To the best of our knowledge, this works represents the first one that proposes an adversarial generative model for the generalized zero-shot learning on multi-label text classification. Extensive experiments demonstrate the effectiveness of our approach. On the public MIMIC-III dataset, our methods improve the F1 score from nearly 0 to 20.91% for the zero-shot codes, and increase the AUC score by 3% (absolute improvement) from previous state of the art. We also show that the framework improves the performance on few-shot codes.
Tasks	Multi-Label Text Classification, Text Classification, Zero-Shot Learning
Published	2019-09-28
URL	https://arxiv.org/abs/1909.13154v1
PDF	https://arxiv.org/pdf/1909.13154v1.pdf
PWC	https://paperswithcode.com/paper/generalized-zero-shot-icd-coding-1
Repo
Framework

Bayesian Inference for Polya Inverse Gamma Models


Title	Bayesian Inference for Polya Inverse Gamma Models
Authors	Christopher Glynn, Jingyu He, Nicholas G. Polson, Jianeng Xu
Abstract	Probability density functions that include the gamma function are widely used in statistics and machine learning. The normalizing constants of gamma, inverse gamma, beta, and Dirichlet distributions all include model parameters as arguments in the gamma function; however, the gamma function does not naturally admit a conjugate prior distribution in a Bayesian analysis, and statistical inference of these parameters is a significant challenge. In this paper, we construct the Polya-inverse Gamma (P-IG) distribution as an infinite convolution of Generalized inverse Gaussian (GIG) distributions, and we represent the reciprocal gamma function as a scale mixture of normal distributions. As a result, the P-IG distribution yields an efficient data augmentation strategy for fully Bayesian inference on model parameters in gamma, inverse gamma, beta, and Dirichlet distributions. To illustrate the applied utility of our data augmentation strategy, we infer the proportion of overdose deaths in the United States attributed to different opioid and prescription drugs with a Dirichlet allocation model.
Tasks	Bayesian Inference, Data Augmentation
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12141v1
PDF	https://arxiv.org/pdf/1905.12141v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-inference-for-polya-inverse-gamma
Repo
Framework

Detecting Gas Vapor Leaks Using Uncalibrated Sensors


Title	Detecting Gas Vapor Leaks Using Uncalibrated Sensors
Authors	Diaa Badawi, Tuba Ayhan, Sule Ozev, Chengmo Yang, Alex Orailoglu, A. Enis Çetin
Abstract	Chemical and infra-red sensors generate distinct responses under similar conditions because of sensor drift, noise or resolution errors. In this work, we use different time-series data sets obtained by infra-red and E-nose sensors in order to detect Volatile Organic Compounds (VOCs) and Ammonia vapor leaks. We process time-series sensor signals using deep neural networks (DNN). Three neural network algorithms are utilized for this purpose. Additive neural networks (termed AddNet) are based on a multiplication-devoid operator and consequently exhibit energy-efficiency compared to regular neural networks. The second algorithm uses generative adversarial neural networks so as to expose the classifying neural network to more realistic data points in order to help the classifier network to deliver improved generalization. Finally, we use conventional convolutional neural networks as a baseline method and compare their performance with the two aforementioned deep neural network algorithms in order to evaluate their effectiveness empirically.
Tasks	Time Series
Published	2019-08-20
URL	https://arxiv.org/abs/1908.07619v1
PDF	https://arxiv.org/pdf/1908.07619v1.pdf
PWC	https://paperswithcode.com/paper/detecting-gas-vapor-leaks-using-uncalibrated
Repo
Framework

A Fully Stochastic Primal-Dual Algorithm


Title	A Fully Stochastic Primal-Dual Algorithm
Authors	Pascal Bianchi, Walid Hachem, Adil Salim
Abstract	A new stochastic primal-dual algorithm for solving a composite optimization problem is proposed. It is assumed that all the functions / operators that enter the optimization problem are given as statistical expectations. These expectations are unknown but revealed across time through i.i.d realizations. The proposed algorithm is proven to converge to a saddle point of the Lagrangian function. In the framework of the monotone operator theory, the convergence proof relies on recent results on the stochastic Forward Backward algorithm involving random monotone operators. An example of convex optimization under stochastic linear constraints is considered.
Tasks
Published	2019-01-23
URL	https://arxiv.org/abs/1901.08170v3
PDF	https://arxiv.org/pdf/1901.08170v3.pdf
PWC	https://paperswithcode.com/paper/a-fully-stochastic-primal-dual-algorithm
Repo
Framework

Randomized Reference Classifier with Gaussian Distribution and Soft Confusion Matrix Applied to the Improving Weak Classifiers


Title	Randomized Reference Classifier with Gaussian Distribution and Soft Confusion Matrix Applied to the Improving Weak Classifiers
Authors	Pawel Trajdos, Marek Kurzynski
Abstract	In this paper, an issue of building the RRC model using probability distributions other than beta distribution is addressed. More precisely, in this paper, we propose to build the RRR model using the truncated normal distribution. Heuristic procedures for expected value and the variance of the truncated-normal distribution are also proposed. The proposed approach is tested using SCM-based model for testing the consequences of applying the truncated normal distribution in the RRC model. The experimental evaluation is performed using four different base classifiers and seven quality measures. The results showed that the proposed approach is comparable to the RRC model built using beta distribution. What is more, for some base classifiers, the truncated-normal-based SCM algorithm turned out to be better at discovering objects coming from minority classes.
Tasks
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09820v1
PDF	https://arxiv.org/pdf/1905.09820v1.pdf
PWC	https://paperswithcode.com/paper/randomized-reference-classifier-with-gaussian
Repo
Framework

Cross-referencing using Fine-grained Topic Modeling


Title	Cross-referencing using Fine-grained Topic Modeling
Authors	Jeffrey Lund, Piper Armstrong, Wilson Fearn, Stephen Cowley, Emily Hales, Kevin Seppi
Abstract	Cross-referencing, which links passages of text to other related passages, can be a valuable study aid for facilitating comprehension of a text. However, cross-referencing requires first, a comprehensive thematic knowledge of the entire corpus, and second, a focused search through the corpus specifically to find such useful connections. Due to this, cross-reference resources are prohibitively expensive and exist only for the most well-studied texts (e.g. religious texts). We develop a topic-based system for automatically producing candidate cross-references which can be easily verified by human annotators. Our system utilizes fine-grained topic modeling with thousands of highly nuanced and specific topics to identify verse pairs which are topically related. We demonstrate that our system can be cost effective compared to having annotators acquire the expertise necessary to produce cross-reference resources unaided.
Tasks
Published	2019-05-18
URL	https://arxiv.org/abs/1905.07508v1
PDF	https://arxiv.org/pdf/1905.07508v1.pdf
PWC	https://paperswithcode.com/paper/cross-referencing-using-fine-grained-topic
Repo
Framework

Synthetic Human Model Dataset for Skeleton Driven Non-rigid Motion Tracking and 3D Reconstruction


Title	Synthetic Human Model Dataset for Skeleton Driven Non-rigid Motion Tracking and 3D Reconstruction
Authors	Shafeeq Elanattil, Peyman Moghadam
Abstract	We introduce a synthetic dataset for evaluating non-rigid 3D human reconstruction based on conventional RGB-D cameras. The dataset consist of seven motion sequences of a single human model. For each motion sequence per-frame ground truth geometry and ground truth skeleton are given. The dataset also contains skinning weights of the human model. More information about the dataset can be found at: https://research.csiro.au/robotics/our-work/databases/synthetic-human-model-dataset/
Tasks	3D Reconstruction
Published	2019-03-07
URL	http://arxiv.org/abs/1903.02679v1
PDF	http://arxiv.org/pdf/1903.02679v1.pdf
PWC	https://paperswithcode.com/paper/synthetic-human-model-dataset-for-skeleton
Repo
Framework