October 19, 2019

3231 words 16 mins read

Paper Group ANR 324

Soft Computing Techniques for Dependable Cyber-Physical Systems. Face Recognition from Sequential Sparse 3D Data via Deep Registration. Planning and Synthesis Under Assumptions. A Segmentation-aware Deep Fusion Network for Compressed Sensing MRI. Conditional Infilling GANs for Data Augmentation in Mammogram Classification. Approximate Distribution …

Soft Computing Techniques for Dependable Cyber-Physical Systems


Title	Soft Computing Techniques for Dependable Cyber-Physical Systems
Authors	Muhammad Atif, Siddique Latif, Rizwan Ahmad, Adnan Khalid Kiani, Junaid Qadir, Adeel Baig, Hisao Ishibuchi, Waseem Abbas
Abstract	Cyber-Physical Systems (CPS) allow us to manipulate objects in the physical world by providing a communication bridge between computation and actuation elements. In the current scheme of things, this sought-after control is marred by limitations inherent in the underlying communication network(s) as well as by the uncertainty found in the physical world. These limitations hamper fine-grained control of elements that may be separated by large-scale distances. In this regard, soft computing is an emerging paradigm that can help to overcome the vulnerabilities, and unreliability of CPS by using techniques including fuzzy systems, neural network, evolutionary computation, probabilistic reasoning and rough sets. In this paper, we present a comprehensive contemporary review of soft computing techniques for CPS dependability modeling, analysis, and improvement. This paper provides an overview of CPS applications, explores the foundations of dependability engineering, and highlights the potential role of soft computing techniques for CPS dependability with various case studies, while identifying common pitfalls and future directions. In addition, this paper provides a comprehensive survey on the use of various soft computing techniques for making CPS dependable.
Tasks
Published	2018-01-25
URL	http://arxiv.org/abs/1801.10472v1
PDF	http://arxiv.org/pdf/1801.10472v1.pdf
PWC	https://paperswithcode.com/paper/soft-computing-techniques-for-dependable
Repo
Framework

Face Recognition from Sequential Sparse 3D Data via Deep Registration


Title	Face Recognition from Sequential Sparse 3D Data via Deep Registration
Authors	Yang Tan, Hongxin Lin, Zelin Xiao, Shengyong Ding, Hongyang Chao
Abstract	Previous works have shown that face recognition with high accurate 3D data is more reliable and insensitive to pose and illumination variations. Recently, low-cost and portable 3D acquisition techniques like ToF(Time of Flight) and DoE based structured light systems enable us to access 3D data easily, e.g., via a mobile phone. However, such devices only provide sparse(limited speckles in structured light system) and noisy 3D data which can not support face recognition directly. In this paper, we aim at achieving high-performance face recognition for devices equipped with such modules which is very meaningful in practice as such devices will be very popular. We propose a framework to perform face recognition by fusing a sequence of low-quality 3D data. As 3D data are sparse and noisy which can not be well handled by conventional methods like the ICP algorithm, we design a PointNet-like Deep Registration Network(DRNet) which works with ordered 3D point coordinates while preserving the ability of mining local structures via convolution. Meanwhile we develop a novel loss function to optimize our DRNet based on the quaternion expression which obviously outperforms other widely used functions. For face recognition, we design a deep convolutional network which takes the fused 3D depth-map as input based on AMSoftmax model. Experiments show that our DRNet can achieve rotation error 0.95{\deg} and translation error 0.28mm for registration. The face recognition on fused data also achieves rank-1 accuracy 99.2% , FAR-0.001 97.5% on Bosphorus dataset which is comparable with state-of-the-art high-quality data based recognition performance.
Tasks	Face Recognition
Published	2018-10-23
URL	http://arxiv.org/abs/1810.09658v3
PDF	http://arxiv.org/pdf/1810.09658v3.pdf
PWC	https://paperswithcode.com/paper/face-recognition-from-sequential-sparse-3d
Repo
Framework

Planning and Synthesis Under Assumptions


Title	Planning and Synthesis Under Assumptions
Authors	Benjamin Aminof, Giuseppe De Giacomo, Aniello Murano, Sasha Rubin
Abstract	In Reasoning about Action and Planning, one synthesizes the agent plan by taking advantage of the assumption on how the environment works (that is, one exploits the environment’s effects, its fairness, its trajectory constraints). In this paper we study this form of synthesis in detail. We consider assumptions as constraints on the possible strategies that the environment can have in order to respond to the agent’s actions. Such constraints may be given in the form of a planning domain (or action theory), as linear-time formulas over infinite or finite runs, or as a combination of the two. We argue though that not all assumption specifications are meaningful: they need to be consistent, which means that there must exist an environment strategy fulfilling the assumption in spite of the agent actions. For such assumptions, we study how to do synthesis/planning for agent goals, ranging from a classical reachability to goal on traces specified in \LTL and \LTLf/\LDLf, characterizing the problem both mathematically and algorithmically.
Tasks
Published	2018-07-18
URL	https://arxiv.org/abs/1807.06777v2
PDF	https://arxiv.org/pdf/1807.06777v2.pdf
PWC	https://paperswithcode.com/paper/planning-and-synthesis-under-assumptions
Repo
Framework

A Segmentation-aware Deep Fusion Network for Compressed Sensing MRI


Title	A Segmentation-aware Deep Fusion Network for Compressed Sensing MRI
Authors	Zhiwen Fan, Liyan Sun, Xinghao Ding, Yue Huang, Congbo Cai, John Paisley
Abstract	Compressed sensing MRI is a classic inverse problem in the field of computational imaging, accelerating the MR imaging by measuring less k-space data. The deep neural network models provide the stronger representation ability and faster reconstruction compared with “shallow” optimization-based methods. However, in the existing deep-based CS-MRI models, the high-level semantic supervision information from massive segmentation-labels in MRI dataset is overlooked. In this paper, we proposed a segmentation-aware deep fusion network called SADFN for compressed sensing MRI. The multilayer feature aggregation (MLFA) method is introduced here to fuse all the features from different layers in the segmentation network. Then, the aggregated feature maps containing semantic information are provided to each layer in the reconstruction network with a feature fusion strategy. This guarantees the reconstruction network is aware of the different regions in the image it reconstructs, simplifying the function mapping. We prove the utility of the cross-layer and cross-task information fusion strategy by comparative study. Extensive experiments on brain segmentation benchmark MRBrainS validated that the proposed SADFN model achieves state-of-the-art accuracy in compressed sensing MRI. This paper provides a novel approach to guide the low-level visual task using the information from mid- or high-level task.
Tasks	Brain Segmentation
Published	2018-04-04
URL	http://arxiv.org/abs/1804.01210v1
PDF	http://arxiv.org/pdf/1804.01210v1.pdf
PWC	https://paperswithcode.com/paper/a-segmentation-aware-deep-fusion-network-for
Repo
Framework

Conditional Infilling GANs for Data Augmentation in Mammogram Classification


Title	Conditional Infilling GANs for Data Augmentation in Mammogram Classification
Authors	Eric Wu, Kevin Wu, David Cox, William Lotter
Abstract	Deep learning approaches to breast cancer detection in mammograms have recently shown promising results. However, such models are constrained by the limited size of publicly available mammography datasets, in large part due to privacy concerns and the high cost of generating expert annotations. Limited dataset size is further exacerbated by substantial class imbalance since “normal” images dramatically outnumber those with findings. Given the rapid progress of generative models in synthesizing realistic images, and the known effectiveness of simple data augmentation techniques (e.g. horizontal flipping), we ask if it is possible to synthetically augment mammogram datasets using generative adversarial networks (GANs). We train a class-conditional GAN to perform contextual in-filling, which we then use to synthesize lesions onto healthy screening mammograms. First, we show that GANs are capable of generating high-resolution synthetic mammogram patches. Next, we experimentally evaluate using the augmented dataset to improve breast cancer classification performance. We observe that a ResNet-50 classifier trained with GAN-augmented training data produces a higher AUROC compared to the same model trained only on traditionally augmented data, demonstrating the potential of our approach.
Tasks	Breast Cancer Detection, Data Augmentation
Published	2018-07-21
URL	http://arxiv.org/abs/1807.08093v2
PDF	http://arxiv.org/pdf/1807.08093v2.pdf
PWC	https://paperswithcode.com/paper/conditional-infilling-gans-for-data
Repo
Framework

Approximate Distribution Matching for Sequence-to-Sequence Learning


Title	Approximate Distribution Matching for Sequence-to-Sequence Learning
Authors	Wenhu Chen, Guanlin Li, Shujie Liu, Zhirui Zhang, Mu Li, Ming Zhou
Abstract	Sequence-to-Sequence models were introduced to tackle many real-life problems like machine translation, summarization, image captioning, etc. The standard optimization algorithms are mainly based on example-to-example matching like maximum likelihood estimation, which is known to suffer from data sparsity problem. Here we present an alternate view to explain sequence-to-sequence learning as a distribution matching problem, where each source or target example is viewed to represent a local latent distribution in the source or target domain. Then, we interpret sequence-to-sequence learning as learning a transductive model to transform the source local latent distributions to match their corresponding target distributions. In our framework, we approximate both the source and target latent distributions with recurrent neural networks (augmenter). During training, the parallel augmenters learn to better approximate the local latent distributions, while the sequence prediction model learns to minimize the KL-divergence of the transformed source distributions and the approximated target distributions. This algorithm can alleviate the data sparsity issues in sequence learning by locally augmenting more unseen data pairs and increasing the model’s robustness. Experiments conducted on machine translation and image captioning consistently demonstrate the superiority of our proposed algorithm over the other competing algorithms.
Tasks	Image Captioning, Machine Translation
Published	2018-08-24
URL	http://arxiv.org/abs/1808.08003v3
PDF	http://arxiv.org/pdf/1808.08003v3.pdf
PWC	https://paperswithcode.com/paper/approximate-distribution-matching-for
Repo
Framework

Clustering-Enhanced Stochastic Gradient MCMC for Hidden Markov Models with Rare States


Title	Clustering-Enhanced Stochastic Gradient MCMC for Hidden Markov Models with Rare States
Authors	Rihui Ou, Alexander L Young, David B Dunson
Abstract	MCMC algorithms for hidden Markov models, which often rely on the forward-backward sampler, suffer with large sample size due to the temporal dependence inherent in the data. Recently, a number of approaches have been developed for posterior inference which make use of the mixing of the hidden Markov process to approximate the full posterior by using small chunks of the data. However, in the presence of imbalanced data resulting from rare latent states, the proposed minibatch estimates will often exclude rare state data resulting in poor inference of the associated emission parameters and inaccurate prediction or detection of rare events. Here, we propose to use a preliminary clustering to over-sample the rare clusters and reduce variance in gradient estimation within Stochastic Gradient MCMC. We demonstrate very substantial gains in predictive and inferential accuracy on real and synthetic examples.
Tasks
Published	2018-10-31
URL	http://arxiv.org/abs/1810.13431v1
PDF	http://arxiv.org/pdf/1810.13431v1.pdf
PWC	https://paperswithcode.com/paper/clustering-enhanced-stochastic-gradient-mcmc
Repo
Framework

Searching Toward Pareto-Optimal Device-Aware Neural Architectures


Title	Searching Toward Pareto-Optimal Device-Aware Neural Architectures
Authors	An-Chieh Cheng, Jin-Dong Dong, Chi-Hung Hsu, Shu-Huan Chang, Min Sun, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, Da-Cheng Juan
Abstract	Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding. However, most existing works only optimize for model accuracy and largely ignore other important factors imposed by the underlying hardware and devices, such as latency and energy, when making inference. In this paper, we first introduce the problem of NAS and provide a survey on recent works. Then we deep dive into two recent advancements on extending NAS into multiple-objective frameworks: MONAS and DPP-Net. Both MONAS and DPP-Net are capable of optimizing accuracy and other objectives imposed by devices, searching for neural architectures that can be best deployed on a wide spectrum of devices: from embedded systems and mobile devices to workstations. Experimental results are poised to show that architectures found by MONAS and DPP-Net achieves Pareto optimality w.r.t the given objectives for various devices.
Tasks	Image Classification
Published	2018-08-29
URL	http://arxiv.org/abs/1808.09830v2
PDF	http://arxiv.org/pdf/1808.09830v2.pdf
PWC	https://paperswithcode.com/paper/searching-toward-pareto-optimal-device-aware
Repo
Framework

A Unified Analysis of Stochastic Momentum Methods for Deep Learning


Title	A Unified Analysis of Stochastic Momentum Methods for Deep Learning
Authors	Yan Yan, Tianbao Yang, Zhe Li, Qihang Lin, Yi Yang
Abstract	Stochastic momentum methods have been widely adopted in training deep neural networks. However, their theoretical analysis of convergence of the training objective and the generalization error for prediction is still under-explored. This paper aims to bridge the gap between practice and theory by analyzing the stochastic gradient (SG) method, and the stochastic momentum methods including two famous variants, i.e., the stochastic heavy-ball (SHB) method and the stochastic variant of Nesterov’s accelerated gradient (SNAG) method. We propose a framework that unifies the three variants. We then derive the convergence rates of the norm of gradient for the non-convex optimization problem, and analyze the generalization performance through the uniform stability approach. Particularly, the convergence analysis of the training objective exhibits that SHB and SNAG have no advantage over SG. However, the stability analysis shows that the momentum term can improve the stability of the learned model and hence improve the generalization performance. These theoretical insights verify the common wisdom and are also corroborated by our empirical analysis on deep learning.
Tasks
Published	2018-08-30
URL	http://arxiv.org/abs/1808.10396v1
PDF	http://arxiv.org/pdf/1808.10396v1.pdf
PWC	https://paperswithcode.com/paper/a-unified-analysis-of-stochastic-momentum
Repo
Framework

Multitask Learning for Large-scale Semantic Change Detection


Title	Multitask Learning for Large-scale Semantic Change Detection
Authors	Rodrigo Caye Daudt, Bertrand Le Saux, Alexandre Boulch, Yann Gousseau
Abstract	Change detection is one of the main problems in remote sensing, and is essential to the accurate processing and understanding of the large scale Earth observation data available through programs such as Sentinel and Landsat. Most of the recently proposed change detection methods bring deep learning to this context, but openly available change detection datasets are still very scarce, which limits the methods that can be proposed and tested. In this paper we present the first large scale high resolution semantic change detection (HRSCD) dataset, which enables the usage of deep learning methods for semantic change detection. The dataset contains coregistered RGB image pairs, pixel-wise change information and land cover information. We then propose several methods using fully convolutional neural networks to perform semantic change detection. Most notably, we present a network architecture that performs change detection and land cover mapping simultaneously, while using the predicted land cover information to help to predict changes. We also describe a sequential training scheme that allows this network to be trained without setting a hyperparameter that balances different loss functions and achieves the best overall results.
Tasks
Published	2018-10-19
URL	https://arxiv.org/abs/1810.08452v2
PDF	https://arxiv.org/pdf/1810.08452v2.pdf
PWC	https://paperswithcode.com/paper/high-resolution-semantic-change-detection
Repo
Framework

An Efficient Approach to Informative Feature Extraction from Multimodal Data


Title	An Efficient Approach to Informative Feature Extraction from Multimodal Data
Authors	Lichen Wang, Jiaxiang Wu, Shao-Lun Huang, Lizhong Zheng, Xiangxiang Xu, Lin Zhang, Junzhou Huang
Abstract	One primary focus in multimodal feature extraction is to find the representations of individual modalities that are maximally correlated. As a well-known measure of dependence, the Hirschfeld-Gebelein-R'{e}nyi (HGR) maximal correlation becomes an appealing objective because of its operational meaning and desirable properties. However, the strict whitening constraints formalized in the HGR maximal correlation limit its application. To address this problem, this paper proposes Soft-HGR, a novel framework to extract informative features from multiple data modalities. Specifically, our framework prevents the “hard” whitening constraints, while simultaneously preserving the same feature geometry as in the HGR maximal correlation. The objective of Soft-HGR is straightforward, only involving two inner products, which guarantees the efficiency and stability in optimization. We further generalize the framework to handle more than two modalities and missing modalities. When labels are partially available, we enhance the discriminative power of the feature representations by making a semi-supervised adaptation. Empirical evaluation implies that our approach learns more informative feature mappings and is more efficient to optimize.
Tasks
Published	2018-11-22
URL	https://arxiv.org/abs/1811.08979v2
PDF	https://arxiv.org/pdf/1811.08979v2.pdf
PWC	https://paperswithcode.com/paper/an-efficient-approach-to-informative-feature
Repo
Framework

Deep Template Matching for Offline Handwritten Chinese Character Recognition


Title	Deep Template Matching for Offline Handwritten Chinese Character Recognition
Authors	Zhiyuan Li, Min Jin, Qi Wu, Huaxiang Lu
Abstract	Just like its remarkable achievements in many computer vision tasks, the convolutional neural networks (CNN) provide an end-to-end solution in handwritten Chinese character recognition (HCCR) with great success. However, the process of learning discriminative features for image recognition is difficult in cases where little data is available. In this paper, we propose a novel method for learning siamese neural network which employ a special structure to predict the similarity between handwritten Chinese characters and template images. The optimization of siamese neural network can be treated as a simple binary classification problem. When the training process has been finished, the powerful discriminative features help us to generalize the predictive power not just to new data, but to entirely new classes that never appear in the training set. Experiments performed on the ICDAR-2013 offline HCCR datasets have shown that the proposed method has a very promising generalization ability to the new classes that never appear in the training set.
Tasks	Offline Handwritten Chinese Character Recognition
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06347v1
PDF	http://arxiv.org/pdf/1811.06347v1.pdf
PWC	https://paperswithcode.com/paper/deep-template-matching-for-offline
Repo
Framework

Critères de qualité d’un classifieur généraliste


Title	Critères de qualité d’un classifieur généraliste
Authors	Gilles R. Ducharme
Abstract	This paper considers the problem of choosing a good classifier. For each problem there exist an optimal classifier, but none are optimal, regarding the error rate, in all cases. Because there exists a large number of classifiers, a user would rather prefer an all-purpose classifier that is easy to adjust, in the hope that it will do almost as good as the optimal. In this paper we establish a list of criteria that a good generalist classifier should satisfy . We first discuss data analytic, these criteria are presented. Six among the most popular classifiers are selected and scored according to these criteria. Tables allow to easily appreciate the relative values of each. In the end, random forests turn out to be the best classifiers.
Tasks
Published	2018-02-10
URL	http://arxiv.org/abs/1802.03567v2
PDF	http://arxiv.org/pdf/1802.03567v2.pdf
PWC	https://paperswithcode.com/paper/criteres-de-qualite-dun-classifieur
Repo
Framework

ReGAN: RE[LAX|BAR|INFORCE] based Sequence Generation using GANs


Title	ReGAN: RE[LAX
Authors	Aparna Balagopalan, Satya Gorti, Mathieu Ravaut, Raeid Saqur
Abstract	Generative Adversarial Networks (GANs) have seen steep ascension to the peak of ML research zeitgeist in recent years. Mostly catalyzed by its success in the domain of image generation, the technique has seen wide range of adoption in a variety of other problem domains. Although GANs have had a lot of success in producing more realistic images than other approaches, they have only seen limited use for text sequences. Generation of longer sequences compounds this problem. Most recently, SeqGAN (Yu et al., 2017) has shown improvements in adversarial evaluation and results with human evaluation compared to a MLE based trained baseline. The main contributions of this paper are three-fold: 1. We show results for sequence generation using a GAN architecture with efficient policy gradient estimators, 2. We attain improved training stability, and 3. We perform a comparative study of recent unbiased low variance gradient estimation techniques such as REBAR (Tucker et al., 2017), RELAX (Grathwohl et al., 2018) and REINFORCE (Williams, 1992). Using a simple grammar on synthetic datasets with varying length, we indicate the quality of sequences generated by the model.
Tasks	Image Generation
Published	2018-05-08
URL	http://arxiv.org/abs/1805.02788v1
PDF	http://arxiv.org/pdf/1805.02788v1.pdf
PWC	https://paperswithcode.com/paper/regan-relaxbarinforce-based-sequence
Repo
Framework

Rendu basé image avec contraintes sur les gradients


Title	Rendu basé image avec contraintes sur les gradients
Authors	Grégoire Nieto, Frédéric Devernay, James Crowley
Abstract	Multi-view image-based rendering consists in generating a novel view of a scene from a set of source views. In general, this works by first doing a coarse 3D reconstruction of the scene, and then using this reconstruction to establish correspondences between source and target views, followed by blending the warped views to get the final image. Unfortunately, discontinuities in the blending weights, due to scene geometry or camera placement, result in artifacts in the target view. In this paper, we show how to avoid these artifacts by imposing additional constraints on the image gradients of the novel view. We propose a variational framework in which an energy functional is derived and optimized by iteratively solving a linear system. We demonstrate this method on several structured and unstructured multi-view datasets, and show that it numerically outperforms state-of-the-art methods, and eliminates artifacts that result from visibility discontinuities
Tasks	3D Reconstruction
Published	2018-12-29
URL	http://arxiv.org/abs/1812.11339v1
PDF	http://arxiv.org/pdf/1812.11339v1.pdf
PWC	https://paperswithcode.com/paper/rendu-base-image-avec-contraintes-sur-les
Repo
Framework