January 27, 2020

2814 words 14 mins read

Paper Group ANR 1233

Deep Motion Blur Removal Using Noisy/Blurry Image Pairs. Aspect Category Detection via Topic-Attention Network. Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training. Towards multi-sequence MR image recovery from undersampled k-space data. The Practicality of Stochastic Optim …

Deep Motion Blur Removal Using Noisy/Blurry Image Pairs


Title	Deep Motion Blur Removal Using Noisy/Blurry Image Pairs
Authors	Shuang Zhang, Ada Zhen, Robert L. Stevenson
Abstract	Removing spatially variant motion blur from a blurry image is a challenging problem as blur sources are complicated and difficult to model accurately. Recent progress in deep neural networks suggests that kernel free single image deblurring can be efficiently performed, but questions about deblurring performance persist. Thus, we propose to restore a sharp image by fusing a pair of noisy/blurry images captured in a burst. Two neural network structures, DeblurRNN and DeblurMerger, are presented to exploit the pair of images in a sequential manner or parallel manner. To boost the training, gradient loss, adversarial loss and spectral normalization are leveraged. The training dataset that consists of pairs of noisy/blurry images and the corresponding ground truth sharp image is synthesized based on the benchmark dataset GOPRO. We evaluated the trained networks on a variety of synthetic datasets and real image pairs. The results demonstrate that the proposed approach outperforms the state-of-the-art both qualitatively and quantitatively.
Tasks	Deblurring
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08541v2
PDF	https://arxiv.org/pdf/1911.08541v2.pdf
PWC	https://paperswithcode.com/paper/deep-motion-blur-removal-using-noisyblurry
Repo
Framework

Aspect Category Detection via Topic-Attention Network


Title	Aspect Category Detection via Topic-Attention Network
Authors	Sajad Movahedi, Erfan Ghadery, Heshaam Faili, Azadeh Shakery
Abstract	The e-commerce has started a new trend in natural language processing through sentiment analysis of user-generated reviews. Different consumers have different concerns about various aspects of a specific product or service. Aspect category detection, as a subtask of aspect-based sentiment analysis, tackles the problem of categorizing a given review sentence into a set of pre-defined aspect categories. In recent years, deep learning approaches have brought revolutionary advances in multiple branches of natural language processing including sentiment analysis. In this paper, we propose a deep neural network method based on attention mechanism to identify different aspect categories of a given review sentence. Our model utilizes several attentions with different topic contexts, enabling it to attend to different parts of a review sentence based on different topics. Experimental results on two datasets in the restaurant domain released by SemEval workshop demonstrates that our approach outperforms existing methods on both datasets. Visualization of the topic attention weights shows the effectiveness of our model in identifying words related to different topics.
Tasks	Aspect-Based Sentiment Analysis, Sentiment Analysis
Published	2019-01-04
URL	https://arxiv.org/abs/1901.01183v2
PDF	https://arxiv.org/pdf/1901.01183v2.pdf
PWC	https://paperswithcode.com/paper/aspect-category-detection-via-topic-attention
Repo
Framework

Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training


Title	Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training
Authors	Dongwon Park, Dong Un Kang, Jisoo Kim, Se Young Chun
Abstract	Multi-scale (MS) approaches have been widely investigated for blind single image / video deblurring that sequentially recovers deblurred images in low spatial scale first and then in high spatial scale later with the output of lower scales. MS approaches have been effective especially for severe blurs induced by large motions in high spatial scale since those can be seen as small blurs in low spatial scale. In this work, we investigate alternative approach to MS, called multi-temporal (MT) approach, for non-uniform single image deblurring. We propose incremental temporal training with constructed MT level dataset from time-resolved dataset, develop novel MT-RNNs with recurrent feature maps, and investigate progressive single image deblurring over iterations. Our proposed MT methods outperform state-of-the-art MS methods on the GoPro dataset in PSNR with the smallest number of parameters.
Tasks	Deblurring
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07410v1
PDF	https://arxiv.org/pdf/1911.07410v1.pdf
PWC	https://paperswithcode.com/paper/multi-temporal-recurrent-neural-networks-for
Repo
Framework

Towards multi-sequence MR image recovery from undersampled k-space data


Title	Towards multi-sequence MR image recovery from undersampled k-space data
Authors	Cheng Peng, Wei-An Lin, Rama Chellappa, S. Kevin Zhou
Abstract	Undersampled MR image recovery has been widely studied for accelerated MR acquisition. However, it has been mostly studied under a single sequence scenario, despite the fact that multi-sequence MR scan is common in practice. In this paper, we aim to optimize multi-sequence MR image recovery from undersampled k-space data under an overall time constraint while considering the difference in acquisition time for various sequences. We first formulate it as a constrained optimization problem and then show that finding the optimal sampling strategy for all sequences and the best recovery model at the same time is combinatorial and hence computationally prohibitive. To solve this problem, we propose a blind recovery model that simultaneously recovers multiple sequences, and an efficient approach to find proper combination of sampling strategy and recovery model. Our experiments demonstrate that the proposed method outperforms sequence-wise recovery, and sheds light on how to decide the undersampling strategy for sequences within an overall time budget.
Tasks
Published	2019-08-15
URL	https://arxiv.org/abs/1908.05615v2
PDF	https://arxiv.org/pdf/1908.05615v2.pdf
PWC	https://paperswithcode.com/paper/towards-multi-sequence-mr-image-recovery-from
Repo
Framework

The Practicality of Stochastic Optimization in Imaging Inverse Problems


Title	The Practicality of Stochastic Optimization in Imaging Inverse Problems
Authors	Junqi Tang, Karen Egiazarian, Mohammad Golbabaee, Mike Davies
Abstract	In this work we investigate the practicality of stochastic gradient descent and recently introduced variants with variance-reduction techniques in imaging inverse problems. Such algorithms have been shown in the machine learning literature to have optimal complexities in theory, and provide great improvement empirically over the deterministic gradient methods. Surprisingly, in some tasks such as image deblurring, many of such methods fail to converge faster than the accelerated deterministic gradient methods, even in terms of epoch counts. We investigate this phenomenon and propose a theory-inspired mechanism for the practitioners to efficiently characterize whether it is beneficial for an inverse problem to be solved by stochastic optimization techniques or not. Using standard tools in numerical linear algebra, we derive conditions on the spectral structure of the inverse problem for being a suitable application of stochastic gradient methods. Particularly, we show that, for an imaging inverse problem, if and only if its Hessain matrix has a fast-decaying eigenspectrum, then the stochastic gradient methods can be more advantageous than deterministic methods for solving such a problem. Our results also provide guidance on choosing appropriately the partition minibatch schemes, showing that a good minibatch scheme typically has relatively low correlation within each of the minibatches. Finally, we propose an accelerated primal-dual SGD algorithm in order to tackle another key bottleneck of stochastic optimization which is the heavy computation of proximal operators. The proposed method has fast convergence rate in practice, and is able to efficiently handle non-smooth regularization terms which are coupled with linear operators.
Tasks	Deblurring, Stochastic Optimization
Published	2019-10-22
URL	https://arxiv.org/abs/1910.10100v2
PDF	https://arxiv.org/pdf/1910.10100v2.pdf
PWC	https://paperswithcode.com/paper/the-practicality-of-stochastic-optimization
Repo
Framework

Approximation Properties of Variational Bayes for Vector Autoregressions


Title	Approximation Properties of Variational Bayes for Vector Autoregressions
Authors	Reza Hajargasht
Abstract	Variational Bayes (VB) is a recent approximate method for Bayesian inference. It has the merit of being a fast and scalable alternative to Markov Chain Monte Carlo (MCMC) but its approximation error is often unknown. In this paper, we derive the approximation error of VB in terms of mean, mode, variance, predictive density and KL divergence for the linear Gaussian multi-equation regression. Our results indicate that VB approximates the posterior mean perfectly. Factors affecting the magnitude of underestimation in posterior variance and mode are revealed. Importantly, We demonstrate that VB estimates predictive densities accurately.
Tasks	Bayesian Inference
Published	2019-03-02
URL	http://arxiv.org/abs/1903.00617v1
PDF	http://arxiv.org/pdf/1903.00617v1.pdf
PWC	https://paperswithcode.com/paper/approximation-properties-of-variational-bayes
Repo
Framework

Unconstrained Road Marking Recognition with Generative Adversarial Networks


Title	Unconstrained Road Marking Recognition with Generative Adversarial Networks
Authors	Younkwan Lee, Juhyun Lee, Yoojin Hong, YeongMin Ko, Moongu Jeon
Abstract	Recent road marking recognition has achieved great success in the past few years along with the rapid development of deep learning. Although considerable advances have been made, they are often over-dependent on unrepresentative datasets and constrained conditions. In this paper, to overcome these drawbacks, we propose an alternative method that achieves higher accuracy and generates high-quality samples as data augmentation. With the following two major contributions: 1) The proposed deblurring network can successfully recover a clean road marking from a blurred one by adopting generative adversarial networks (GAN). 2) The proposed data augmentation method, based on mutual information, can preserve and learn semantic context from the given dataset. We construct and train a class-conditional GAN to increase the size of training set, which makes it suitable to recognize target. The experimental results have shown that our proposed framework generates deblurred clean samples from blurry ones, and outperforms other methods even with unconstrained road marking datasets.
Tasks	Data Augmentation, Deblurring
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04326v1
PDF	https://arxiv.org/pdf/1910.04326v1.pdf
PWC	https://paperswithcode.com/paper/unconstrained-road-marking-recognition-with
Repo
Framework

Static force field representation of environments based on agents nonlinear motions


Title	Static force field representation of environments based on agents nonlinear motions
Authors	Damian Campo, Alejandro Betancourt, Lucio Marcenaro, Carlo Regazzoni
Abstract	This paper presents a methodology that aims at the incremental representation of areas inside environments in terms of attractive forces. It is proposed a parametric representation of velocity fields ruling the dynamics of moving agents. It is assumed that attractive spots in the environment are responsible for modifying the motion of agents. A switching model is used to describe near and far velocity fields, which in turn are used to learn attractive characteristics of environments. The effect of such areas is considered radial over all the scene. Based on the estimation of attractive areas, a map that describes their effects in terms of their localizations, ranges of action, and intensities is derived in an online way. Information of static attractive areas is added dynamically into a set of filters that describes possible interactions between moving agents and an environment. The proposed approach is first evaluated on synthetic data; posteriorly, the method is applied on real trajectories coming from moving pedestrians in an indoor environment.
Tasks
Published	2019-09-09
URL	https://arxiv.org/abs/1909.04010v1
PDF	https://arxiv.org/pdf/1909.04010v1.pdf
PWC	https://paperswithcode.com/paper/static-force-field-representation-of
Repo
Framework

Convergence of Adversarial Training in Overparametrized Neural Networks


Title	Convergence of Adversarial Training in Overparametrized Neural Networks
Authors	Ruiqi Gao, Tianle Cai, Haochuan Li, Liwei Wang, Cho-Jui Hsieh, Jason D. Lee
Abstract	Neural networks are vulnerable to adversarial examples, i.e. inputs that are imperceptibly perturbed from natural data and yet incorrectly classified by the network. Adversarial training, a heuristic form of robust optimization that alternates between minimization and maximization steps, has proven to be among the most successful methods to train networks to be robust against a pre-defined family of perturbations. This paper provides a partial answer to the success of adversarial training, by showing that it converges to a network where the surrogate loss with respect to the the attack algorithm is within $\epsilon$ of the optimal robust loss. Then we show that the optimal robust loss is also close to zero, hence adversarial training finds a robust classifier. The analysis technique leverages recent work on the analysis of neural networks via Neural Tangent Kernel (NTK), combined with motivation from online-learning when the maximization is solved by a heuristic, and the expressiveness of the NTK kernel in the $\ell_\infty$-norm. In addition, we also prove that robust interpolation requires more model capacity, supporting the evidence that adversarial training requires wider networks.
Tasks
Published	2019-06-19
URL	https://arxiv.org/abs/1906.07916v2
PDF	https://arxiv.org/pdf/1906.07916v2.pdf
PWC	https://paperswithcode.com/paper/convergence-of-adversarial-training-in
Repo
Framework

A Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Games


Title	A Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Games
Authors	Waïss Azizian, Ioannis Mitliagkas, Simon Lacoste-Julien, Gauthier Gidel
Abstract	We consider differentiable games where the goal is to find a Nash equilibrium. The machine learning community has recently started using variants of the gradient method (GD). Prime examples are extragradient (EG), the optimistic gradient method (OG) and consensus optimization (CO), which enjoy linear convergence in cases like bilinear games, where the standard GD fails. The full benefits of theses relatively new methods are not known as there is no unified analysis for both strongly monotone and bilinear games. We provide new analyses of the EG’s local and global convergence properties and use is to get a tighter global convergence rate for OG and CO. Our analysis covers the whole range of settings between bilinear and strongly monotone games. It reveals that these methods converge via different mechanisms at these extremes; in between, it exploits the most favorable mechanism for the given problem. We then prove that EG achieves the optimal rate for a wide class of algorithms with any number of extrapolations. Our tight analysis of EG’s convergence rate in games shows that, unlike in convex minimization, EG may be much faster than GD.
Tasks
Published	2019-06-13
URL	https://arxiv.org/abs/1906.05945v4
PDF	https://arxiv.org/pdf/1906.05945v4.pdf
PWC	https://paperswithcode.com/paper/a-tight-and-unified-analysis-of-extragradient
Repo
Framework

Signal Combination for Language Identification


Title	Signal Combination for Language Identification
Authors	Shengye Wang, Li Wan, Yang Yu, Ignacio Lopez Moreno
Abstract	Google’s multilingual speech recognition system combines low-level acoustic signals with language-specific recognizer signals to better predict the language of an utterance. This paper presents our experience with different signal combination methods to improve overall language identification accuracy. We compare the performance of a lattice-based ensemble model and a deep neural network model to combine signals from recognizers with that of a baseline that only uses low-level acoustic signals. Experimental results show that the deep neural network model outperforms the lattice-based ensemble model, and it reduced the error rate from 5.5% in the baseline to 4.3%, which is a 21.8% relative reduction.
Tasks	Language Identification, Speech Recognition
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09687v2
PDF	https://arxiv.org/pdf/1910.09687v2.pdf
PWC	https://paperswithcode.com/paper/signal-combination-for-language
Repo
Framework

Natural Language Understanding with the Quora Question Pairs Dataset


Title	Natural Language Understanding with the Quora Question Pairs Dataset
Authors	Lakshay Sharma, Laura Graesser, Nikita Nangia, Utku Evci
Abstract	This paper explores the task Natural Language Understanding (NLU) by looking at duplicate question detection in the Quora dataset. We conducted extensive exploration of the dataset and used various machine learning models, including linear and tree-based models. Our final finding was that a simple Continuous Bag of Words neural network model had the best performance, outdoing more complicated recurrent and attention based models. We also conducted error analysis and found some subjectivity in the labeling of the dataset.
Tasks
Published	2019-07-01
URL	https://arxiv.org/abs/1907.01041v1
PDF	https://arxiv.org/pdf/1907.01041v1.pdf
PWC	https://paperswithcode.com/paper/natural-language-understanding-with-the-quora
Repo
Framework

Transformer ASR with Contextual Block Processing


Title	Transformer ASR with Contextual Block Processing
Authors	Emiru Tsunoo, Yosuke Kashiwagi, Toshiyuki Kumakura, Shinji Watanabe
Abstract	The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks (RNNs) in end-to-end (E2E) automatic speech recognition (ASR) systems. However, the Transformer has a drawback in that the entire input sequence is required to compute self-attention. In this paper, we propose a new block processing method for the Transformer encoder by introducing a context-aware inheritance mechanism. An additional context embedding vector handed over from the previously processed block helps to encode not only local acoustic information but also global linguistic, channel, and speaker attributes. We introduce a novel mask technique to implement the context inheritance to train the model efficiently. Evaluations of the Wall Street Journal (WSJ), Librispeech, VoxForge Italian, and AISHELL-1 Mandarin speech recognition datasets show that our proposed contextual block processing method outperforms naive block processing consistently. Furthermore, the attention weight tendency of each layer is analyzed to clarify how the added contextual inheritance mechanism models the global information.
Tasks	Speech Recognition
Published	2019-10-16
URL	https://arxiv.org/abs/1910.07204v1
PDF	https://arxiv.org/pdf/1910.07204v1.pdf
PWC	https://paperswithcode.com/paper/transformer-asr-with-contextual-block
Repo
Framework

Graph Filtration Learning


Title	Graph Filtration Learning
Authors	Christoph D. Hofer, Florian Graf, Bastian Rieck, Marc Niethammer, Roland Kwitt
Abstract	We propose an approach to learning with graph-structured data in the problem domain of graph classification. In particular, we present a novel type of readout operation to aggregate node features into a graph-level representation. To this end, we leverage persistent homology computed via a real-valued, learnable, filter function. We establish the theoretical foundation for differentiating through the persistent homology computation. Empirically, we show that this type of readout operation compares favorably to previous techniques, especially when the graph connectivity structure is informative for the learning problem.
Tasks	Graph Classification
Published	2019-05-27
URL	https://arxiv.org/abs/1905.10996v2
PDF	https://arxiv.org/pdf/1905.10996v2.pdf
PWC	https://paperswithcode.com/paper/graph-filtration-learning
Repo
Framework

Improved Super-Resolution Convolution Neural Network for Large Images


Title	Improved Super-Resolution Convolution Neural Network for Large Images
Authors	Junyu, Wang, Rong Song
Abstract	Single image super-resolution (SISR) is a very popular topic nowadays, which has both research value and practical value. In daily life, we crop a large image into sub-images to do super-resolution and then merge them together. Although convolution neural network performs very well in the research field, if we use it to do super-resolution, we can easily observe cutting lines from merged pictures. To address these problems, in this paper, we propose a refined architecture of SRCNN with ‘Symmetric padding’, ‘Random learning’ and ‘Residual learning’. Moreover, we have done a lot of experiments to prove our model performs best among a lot of the state-of-art methods.
Tasks	Image Super-Resolution, Super-Resolution
Published	2019-07-26
URL	https://arxiv.org/abs/1907.12928v1
PDF	https://arxiv.org/pdf/1907.12928v1.pdf
PWC	https://paperswithcode.com/paper/improved-super-resolution-convolution-neural
Repo
Framework