October 16, 2019

3030 words 15 mins read

Paper Group ANR 1134

Super-resolution of spatiotemporal event-stream image captured by the asynchronous temporal contrast vision sensor. The Coherent Point Drift for Clustered Point Sets. Towards Robust Neural Networks with Lipschitz Continuity. Discourse-Aware Neural Rewards for Coherent Text Generation. Gaussian Process Classification with Privileged Information by S …

Super-resolution of spatiotemporal event-stream image captured by the asynchronous temporal contrast vision sensor


Title	Super-resolution of spatiotemporal event-stream image captured by the asynchronous temporal contrast vision sensor
Authors	Hongmin Li, Guoqi Li, Hanchao Liu, Luping Shi
Abstract	Super-resolution (SR) is a useful technology to generate a high-resolution (HR) visual output from the low-resolution (LR) visual inputs overcoming the physical limitations of the cameras. However, SR has not been applied to enhance the resolution of spatiotemporal event-stream images captured by the frame-free dynamic vision sensors (DVSs). SR of event-stream image is fundamentally different from existing frame-based schemes since basically each pixel value of DVS images is an event sequence. In this work, a two-stage scheme is proposed to solve the SR problem of the spatiotemporal event-stream image. We use a nonhomogeneous Poisson point process to model the event sequence, and sample the events of each pixel by simulating a nonhomogeneous Poisson process according to the specified event number and rate function. Firstly, the event number of each pixel of the HR DVS image is determined with a sparse signal representation based method to obtain the HR event-count map from that of the LR DVS recording. The rate function over time line of the point process of each HR pixel is computed using a spatiotemporal filter on the corresponding LR neighbor pixels. Secondly, the event sequence of each new pixel is generated with a thinning based event sampling algorithm. Two metrics are proposed to assess the event-stream SR results. The proposed method is demonstrated through obtaining HR event-stream images from a series of DVS recordings with the proposed method. Results show that the upscaled HR event streams has perceptually higher spatial texture detail than the LR DVS images. Besides, the temporal properties of the upscaled HR event streams match that of the original input very well. This work enables many potential applications of event-based vision.
Tasks	Event-based vision, Super-Resolution
Published	2018-02-07
URL	http://arxiv.org/abs/1802.02398v2
PDF	http://arxiv.org/pdf/1802.02398v2.pdf
PWC	https://paperswithcode.com/paper/super-resolution-of-spatiotemporal-event
Repo
Framework

The Coherent Point Drift for Clustered Point Sets


Title	The Coherent Point Drift for Clustered Point Sets
Authors	Dmitry Lachinov, Vadim Turlapov
Abstract	The problem of non-rigid point set registration is a key problem for many computer vision tasks. In many cases the nature of the data or capabilities of the point detection algorithms can give us some prior information on point sets distribution. In non-rigid case this information is able to drastically improve registration results by limiting number of possible solutions. In this paper we explore use of prior information about point sets clustering, such information can be obtained with preliminary segmentation. We extend existing probabilistic framework for fitting two level Gaussian mixture model and derive closed form solution for maximization step of the EM algorithm. This enables us to improve method accuracy with almost no performance loss. We evaluate our approach and compare the Cluster Coherent Point Drift with other existing non-rigid point set registration methods and show it’s advantages for digital medicine tasks, especially for heart template model personalization using patient’s medical data.
Tasks
Published	2018-12-14
URL	http://arxiv.org/abs/1812.05869v1
PDF	http://arxiv.org/pdf/1812.05869v1.pdf
PWC	https://paperswithcode.com/paper/the-coherent-point-drift-for-clustered-point
Repo
Framework

Towards Robust Neural Networks with Lipschitz Continuity


Title	Towards Robust Neural Networks with Lipschitz Continuity
Authors	Muhammad Usama, Dong Eui Chang
Abstract	Deep neural networks have shown remarkable performance across a wide range of vision-based tasks, particularly due to the availability of large-scale datasets for training and better architectures. However, data seen in the real world are often affected by distortions that not accounted for by the training datasets. In this paper, we address the challenge of robustness and stability of neural networks and propose a general training method that can be used to make the existing neural network architectures more robust and stable to input visual perturbations while using only available datasets for training. Proposed training method is convenient to use as it does not require data augmentation or changes in the network architecture. We provide theoretical proof as well as empirical evidence for the efficiency of the proposed training method by performing experiments with existing neural network architectures and demonstrate that same architecture when trained with the proposed training method perform better than when trained with conventional training approach in the presence of noisy datasets.
Tasks	Data Augmentation
Published	2018-11-22
URL	http://arxiv.org/abs/1811.09008v1
PDF	http://arxiv.org/pdf/1811.09008v1.pdf
PWC	https://paperswithcode.com/paper/towards-robust-neural-networks-with-lipschitz
Repo
Framework

Discourse-Aware Neural Rewards for Coherent Text Generation


Title	Discourse-Aware Neural Rewards for Coherent Text Generation
Authors	Antoine Bosselut, Asli Celikyilmaz, Xiaodong He, Jianfeng Gao, Po-Sen Huang, Yejin Choi
Abstract	In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to model cross-sentence ordering as a means to approximate desired discourse structure. Empirical results demonstrate that a generator trained with the learned reward produces more coherent and less repetitive text than models trained with cross-entropy or with reinforcement learning with commonly used scores as rewards.
Tasks	Sentence Ordering, Text Generation
Published	2018-05-10
URL	http://arxiv.org/abs/1805.03766v1
PDF	http://arxiv.org/pdf/1805.03766v1.pdf
PWC	https://paperswithcode.com/paper/discourse-aware-neural-rewards-for-coherent
Repo
Framework

Gaussian Process Classification with Privileged Information by Soft-to-Hard Labeling Transfer


Title	Gaussian Process Classification with Privileged Information by Soft-to-Hard Labeling Transfer
Authors	Ryosuke Kamesawa, Issei Sato, Masashi Sugiyama
Abstract	Learning using privileged information is an attractive problem setting that helps many learning scenarios in the real world. A state-of-the-art method of Gaussian process classification (GPC) with privileged information is GPC+, which incorporates privileged information into a noise term of the likelihood. A drawback of GPC+ is that it requires numerical quadrature to calculate the posterior distribution of the latent function, which is extremely time-consuming. To overcome this limitation, we propose a novel classification method with privileged information based on Gaussian processes, called “soft-label-transferred Gaussian process (SLT-GP).” Our basic idea is that we construct another learning task of predicting soft labels (continuous values) obtained from privileged information and we perform transfer learning from this task to the target task of predicting hard labels. We derive a PAC-Bayesian bound of our proposed method, which justifies optimizing hyperparameters by the empirical Bayes method. We also experimentally show the usefulness of our proposed method compared with GPC and GPC+.
Tasks	Gaussian Processes, Transfer Learning
Published	2018-02-12
URL	http://arxiv.org/abs/1802.03877v1
PDF	http://arxiv.org/pdf/1802.03877v1.pdf
PWC	https://paperswithcode.com/paper/gaussian-process-classification-with
Repo
Framework

A Text Classification Application: Poet Detection from Poetry


Title	A Text Classification Application: Poet Detection from Poetry
Authors	Durmus Ozkan Sahin, Oguz Emre Kural, Erdal Kilic, Armagan Karabina
Abstract	With the widespread use of the internet, the size of the text data increases day by day. Poems can be given as an example of the growing text. In this study, we aim to classify poetry according to poet. Firstly, data set consisting of three different poetry of poets written in English have been constructed. Then, text categorization techniques are implemented on it. Chi-Square technique are used for feature selection. In addition, five different classification algorithms are tried. These algorithms are Sequential minimal optimization, Naive Bayes, C4.5 decision tree, Random Forest and k-nearest neighbors. Although each classifier showed very different results, over the 70% classification success rate was taken by sequential minimal optimization technique.
Tasks	Feature Selection, Text Categorization, Text Classification
Published	2018-10-24
URL	http://arxiv.org/abs/1810.11414v1
PDF	http://arxiv.org/pdf/1810.11414v1.pdf
PWC	https://paperswithcode.com/paper/a-text-classification-application-poet
Repo
Framework

Recent progress in semantic image segmentation


Title	Recent progress in semantic image segmentation
Authors	Xiaolong Liu, Zhidong Deng, Yuhan Yang
Abstract	Semantic image segmentation, which becomes one of the key applications in image processing and computer vision domain, has been used in multiple domains such as medical area and intelligent transportation. Lots of benchmark datasets are released for researchers to verify their algorithms. Semantic segmentation has been studied for many years. Since the emergence of Deep Neural Network (DNN), segmentation has made a tremendous progress. In this paper, we divide semantic image segmentation methods into two categories: traditional and recent DNN method. Firstly, we briefly summarize the traditional method as well as datasets released for segmentation, then we comprehensively investigate recent methods based on DNN which are described in the eight aspects: fully convolutional network, upsample ways, FCN joint with CRF methods, dilated convolution approaches, progresses in backbone network, pyramid methods, Multi-level feature and multi-stage method, supervised, weakly-supervised and unsupervised methods. Finally, a conclusion in this area is drawn.
Tasks	Semantic Segmentation
Published	2018-09-20
URL	http://arxiv.org/abs/1809.10198v1
PDF	http://arxiv.org/pdf/1809.10198v1.pdf
PWC	https://paperswithcode.com/paper/recent-progress-in-semantic-image
Repo
Framework

Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation


Title	Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
Authors	Bohan Zhuang, Chunhua Shen, Mingkui Tan, Lingqiao Liu, Ian Reid
Abstract	In this paper, we propose to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models specifically} for mobile devices with limited power capacity and computation resources. Previous works on quantizing CNNs seek to approximate the floating-point information using a set of discrete values, which we call value approximation, but typically assume the same architecture as the full-precision networks. In this paper, however, we take a novel ‘structure approximation’ view for quantization—it is very likely that a different architecture may be better for best performance. In particular, we propose a `network decomposition’ strategy, named \textbf{Group-Net}, in which we divide the network into groups. In this way, each full-precision group can be effectively reconstructed by aggregating a set of homogeneous binary branches. In addition, we learn effective connections among groups to improve the representational capability. Moreover, the proposed Group-Net shows strong generalization to other tasks. For instance, we extend Group-Net for highly accurate semantic segmentation by embedding rich context into the binary structure. Experiments on both classification and semantic segmentation tasks demonstrate the superior performance of the proposed methods over various popular architectures. In particular, we outperform the previous best binary neural networks in terms of accuracy and major computation savings. \|
Tasks	Image Classification, Quantization, Semantic Segmentation
Published	2018-11-22
URL	http://arxiv.org/abs/1811.10413v2
PDF	http://arxiv.org/pdf/1811.10413v2.pdf
PWC	https://paperswithcode.com/paper/structured-binary-neural-networks-for
Repo
Framework

Steady-state Non-Line-of-Sight Imaging


Title	Steady-state Non-Line-of-Sight Imaging
Authors	Wenzheng Chen, Simon Daneau, Fahim Mannan, Felix Heide
Abstract	Conventional intensity cameras recover objects in the direct line-of-sight of the camera, whereas occluded scene parts are considered lost in this process. Non-line-of-sight imaging (NLOS) aims at recovering these occluded objects by analyzing their indirect reflections on visible scene surfaces. Existing NLOS methods temporally probe the indirect light transport to unmix light paths based on their travel time, which mandates specialized instrumentation that suffers from low photon efficiency, high cost, and mechanical scanning. We depart from temporal probing and demonstrate steady-state NLOS imaging using conventional intensity sensors and continuous illumination. Instead of assuming perfectly isotropic scattering, the proposed method exploits directionality in the hidden surface reflectance, resulting in (small) spatial variation of their indirect reflections for varying illumination. To tackle the shape-dependence of these variations, we propose a trainable architecture which learns to map diffuse indirect reflections to scene reflectance using only synthetic training data. Relying on consumer color image sensors, with high fill factor, high quantum efficiency and low read-out noise, we demonstrate high-fidelity color NLOS imaging for scene configurations tackled before with picosecond time resolution.
Tasks
Published	2018-11-24
URL	http://arxiv.org/abs/1811.09910v2
PDF	http://arxiv.org/pdf/1811.09910v2.pdf
PWC	https://paperswithcode.com/paper/steady-state-non-line-of-sight-imaging
Repo
Framework

An Adaptive Population Size Differential Evolution with Novel Mutation Strategy for Constrained Optimization


Title	An Adaptive Population Size Differential Evolution with Novel Mutation Strategy for Constrained Optimization
Authors	Yuan Fu, Hu Wang, Meng-Zhu Yang
Abstract	Differential evolution (DE) has competitive performance on constrained optimization problems (COPs), which targets at searching for global optimal solution without violating the constraints. Generally, researchers pay more attention on avoiding violating the constraints than better objective function value. To achieve the aim of searching the feasible solutions accurately, an adaptive population size method and an adaptive mutation strategy are proposed in the paper. The adaptive population method is similar to a state switch which controls the exploring state and exploiting state according to the situation of feasible solution search. The novel mutation strategy is designed to enhance the effect of status switch based on adaptive population size, which is useful to reduce the constraint violations. Moreover, a mechanism based on multipopulation competition and a more precise method of constraint control are adopted in the proposed algorithm. The proposed differential evolution algorithm, APDE-NS, is evaluated on the benchmark problems from CEC2017 constrained real parameter optimization. The experimental results show the effectiveness of the proposed method is competitive compared to other state-of-the-art algorithms.
Tasks
Published	2018-05-11
URL	http://arxiv.org/abs/1805.04217v1
PDF	http://arxiv.org/pdf/1805.04217v1.pdf
PWC	https://paperswithcode.com/paper/an-adaptive-population-size-differential
Repo
Framework

Global Second-order Pooling Convolutional Networks


Title	Global Second-order Pooling Convolutional Networks
Authors	Zilin Gao, Jiangtao Xie, Qilong Wang, Peihua Li
Abstract	Deep Convolutional Networks (ConvNets) are fundamental to, besides large-scale visual recognition, a lot of vision tasks. As the primary goal of the ConvNets is to characterize complex boundaries of thousands of classes in a high-dimensional space, it is critical to learn higher-order representations for enhancing non-linear modeling capability. Recently, Global Second-order Pooling (GSoP), plugged at the end of networks, has attracted increasing attentions, achieving much better performance than classical, first-order networks in a variety of vision tasks. However, how to effectively introduce higher-order representation in earlier layers for improving non-linear capability of ConvNets is still an open problem. In this paper, we propose a novel network model introducing GSoP across from lower to higher layers for exploiting holistic image information throughout a network. Given an input 3D tensor outputted by some previous convolutional layer, we perform GSoP to obtain a covariance matrix which, after nonlinear transformation, is used for tensor scaling along channel dimension. Similarly, we can perform GSoP along spatial dimension for tensor scaling as well. In this way, we can make full use of the second-order statistics of the holistic image throughout a network. The proposed networks are thoroughly evaluated on large-scale ImageNet-1K, and experiments have shown that they outperformed non-trivially the counterparts while achieving state-of-the-art results.
Tasks	Object Recognition
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12006v2
PDF	http://arxiv.org/pdf/1811.12006v2.pdf
PWC	https://paperswithcode.com/paper/global-second-order-pooling-convolutional
Repo
Framework

Retrospective correction of Rigid and Non-Rigid MR motion artifacts using GANs


Title	Retrospective correction of Rigid and Non-Rigid MR motion artifacts using GANs
Authors	Karim Armanious, Sergios Gatidis, Konstantin Nikolaou, Bin Yang, Thomas Küstner
Abstract	Motion artifacts are a primary source of magnetic resonance (MR) image quality deterioration with strong repercussions on diagnostic performance. Currently, MR motion correction is carried out either prospectively, with the help of motion tracking systems, or retrospectively by mainly utilizing computationally expensive iterative algorithms. In this paper, we utilize a new adversarial framework, titled MedGAN, for the joint retrospective correction of rigid and non-rigid motion artifacts in different body regions and without the need for a reference image. MedGAN utilizes a unique combination of non-adversarial losses and a new generator architecture to capture the textures and fine-detailed structures of the desired artifact-free MR images. Quantitative and qualitative comparisons with other adversarial techniques have illustrated the proposed model performance.
Tasks
Published	2018-09-17
URL	http://arxiv.org/abs/1809.06276v2
PDF	http://arxiv.org/pdf/1809.06276v2.pdf
PWC	https://paperswithcode.com/paper/retrospective-correction-of-rigid-and-non
Repo
Framework

A Trace Lasso Regularized L1-norm Graph Cut for Highly Correlated Noisy Hyperspectral Image


Title	A Trace Lasso Regularized L1-norm Graph Cut for Highly Correlated Noisy Hyperspectral Image
Authors	Ramanarayan Mohanty, S L Happy, Nilesh Suthar, Aurobinda Routray
Abstract	This work proposes an adaptive trace lasso regularized L1-norm based graph cut method for dimensionality reduction of Hyperspectral images, called as `Trace Lasso-L1 Graph Cut’ (TL-L1GC). The underlying idea of this method is to generate the optimal projection matrix by considering both the sparsity as well as the correlation of the data samples. The conventional L2-norm used in the objective function is sensitive to noise and outliers. Therefore, in this work L1-norm is utilized as a robust alternative to L2-norm. Besides, for further improvement of the results, we use a penalty function of trace lasso with the L1GC method. It adaptively balances the L2-norm and L1-norm simultaneously by considering the data correlation along with the sparsity. We obtain the optimal projection matrix by maximizing the ratio of between-class dispersion to within-class dispersion using L1-norm with trace lasso as the penalty. Furthermore, an iterative procedure for this TL-L1GC method is proposed to solve the optimization function. The effectiveness of this proposed method is evaluated on two benchmark HSI datasets. \|
Tasks	Dimensionality Reduction
Published	2018-07-22
URL	http://arxiv.org/abs/1807.10602v1
PDF	http://arxiv.org/pdf/1807.10602v1.pdf
PWC	https://paperswithcode.com/paper/a-trace-lasso-regularized-l1-norm-graph-cut
Repo
Framework

BomJi at SemEval-2018 Task 10: Combining Vector-, Pattern- and Graph-based Information to Identify Discriminative Attributes


Title	BomJi at SemEval-2018 Task 10: Combining Vector-, Pattern- and Graph-based Information to Identify Discriminative Attributes
Authors	Enrico Santus, Chris Biemann, Emmanuele Chersoni
Abstract	This paper describes BomJi, a supervised system for capturing discriminative attributes in word pairs (e.g. yellow as discriminative for banana over watermelon). The system relies on an XGB classifier trained on carefully engineered graph-, pattern- and word embedding based features. It participated in the SemEval- 2018 Task 10 on Capturing Discriminative Attributes, achieving an F1 score of 0:73 and ranking 2nd out of 26 participant systems.
Tasks
Published	2018-04-30
URL	http://arxiv.org/abs/1804.11251v1
PDF	http://arxiv.org/pdf/1804.11251v1.pdf
PWC	https://paperswithcode.com/paper/bomji-at-semeval-2018-task-10-combining
Repo
Framework

Multi-Output Convolution Spectral Mixture for Gaussian Processes


Title	Multi-Output Convolution Spectral Mixture for Gaussian Processes
Authors	Kai Chen, Perry Groot, Jinsong Chen, Elena Marchiori
Abstract	Multi-output Gaussian processes (MOGPs) are recently extended by using spectral mixture kernel, which enables expressively pattern extrapolation with a strong interpretation. In particular, Multi-Output Spectral Mixture kernel (MOSM) is a recent, powerful state of the art method. However, MOSM cannot reduce to the ordinary spectral mixture kernel (SM) when using a single channel. Moreover, when the spectral density of different channels is either very close or very far from each other in the frequency domain, MOSM generates unreasonable scale effects on cross weights which produces an incorrect description of the channel correlation structure. In this paper, we tackle these drawbacks and introduce a principled multi-output convolution spectral mixture kernel (MOCSM) framework. In our framework, we model channel dependencies through convolution of time and phase delayed spectral mixtures between different channels. Results of extensive experiments on synthetic and real datasets demontrate the advantages of MOCSM and its state of the art performance.
Tasks	Gaussian Processes
Published	2018-08-07
URL	http://arxiv.org/abs/1808.02266v6
PDF	http://arxiv.org/pdf/1808.02266v6.pdf
PWC	https://paperswithcode.com/paper/multi-output-convolution-spectral-mixture-for
Repo
Framework