January 30, 2020

3065 words 15 mins read

Paper Group ANR 299

Minimizing Perceived Image Quality Loss Through Adversarial Attack Scoping. Learn to Allocate Resources in Vehicular Networks. Adversarial Attacks against Deep Saliency Models. A Machine Learning Approach to Comment Toxicity Classification. SEGAN: Structure-Enhanced Generative Adversarial Network for Compressed Sensing MRI Reconstruction. Deep Clos …

Minimizing Perceived Image Quality Loss Through Adversarial Attack Scoping


Title	Minimizing Perceived Image Quality Loss Through Adversarial Attack Scoping
Authors	Kostiantyn Khabarlak, Larysa Koriashkina
Abstract	Neural networks are now actively being used for computer vision tasks in security critical areas such as robotics, face recognition, autonomous vehicles yet their safety is under question after the discovery of adversarial attacks. In this paper we develop simplified adversarial attack algorithms based on a scoping idea, which enables execution of fast adversarial attacks that minimize structural image quality (SSIM) loss, allows performing efficient transfer attacks with low target inference network call count and opens a possibility of an attack using pen-only drawings on a paper for the MNIST handwritten digit dataset. The presented adversarial attack analysis and the idea of attack scoping can be easily expanded to different datasets, thus making the paper’s results applicable to a wide range of practical tasks.
Tasks	Adversarial Attack, Autonomous Vehicles, Face Recognition
Published	2019-04-23
URL	http://arxiv.org/abs/1904.10390v1
PDF	http://arxiv.org/pdf/1904.10390v1.pdf
PWC	https://paperswithcode.com/paper/minimizing-perceived-image-quality-loss
Repo
Framework

Learn to Allocate Resources in Vehicular Networks


Title	Learn to Allocate Resources in Vehicular Networks
Authors	Liang Wang, Hao Ye, Le Liang, Geoffrey Ye Li
Abstract	Resource allocation has a direct and profound impact on the performance of vehicle-to-everything (V2X) networks. Considering the dynamic nature of vehicular environments, it is appealing to devise a decentralized strategy to perform effective resource sharing. In this paper, we exploit deep learning to promote coordination among multiple vehicles and propose a hybrid architecture consisting of centralized decision making and distributed resource sharing to maximize the long-term sum rate of all vehicles. To reduce the network signaling overhead, each vehicle uses a deep neural network to compress its own observed information that is thereafter fed back to the centralized decision-making unit, which employs a deep Q-network to allocate resources and then sends the decision results to all vehicles. We further adopt a quantization layer for each vehicle that learns to quantize the continuous feedback. Extensive simulation results demonstrate that the proposed hybrid architecture can achieve near-optimal performance. Meanwhile, there exists an optimal number of continuous feedback and binary feedback, respectively. Besides, this architecture is robust to different feedback intervals, input noise, and feedback noise.
Tasks	Decision Making, Quantization
Published	2019-07-30
URL	https://arxiv.org/abs/1908.03447v1
PDF	https://arxiv.org/pdf/1908.03447v1.pdf
PWC	https://paperswithcode.com/paper/learn-to-allocate-resources-in-vehicular
Repo
Framework

Adversarial Attacks against Deep Saliency Models


Title	Adversarial Attacks against Deep Saliency Models
Authors	Zhaohui Che, Ali Borji, Guangtao Zhai, Suiyi Ling, Guodong Guo, Patrick Le Callet
Abstract	Currently, a plethora of saliency models based on deep neural networks have led great breakthroughs in many complex high-level vision tasks (e.g. scene description, object detection). The robustness of these models, however, has not yet been studied. In this paper, we propose a sparse feature-space adversarial attack method against deep saliency models for the first time. The proposed attack only requires a part of the model information, and is able to generate a sparser and more insidious adversarial perturbation, compared to traditional image-space attacks. These adversarial perturbations are so subtle that a human observer cannot notice their presences, but the model outputs will be revolutionized. This phenomenon raises security threats to deep saliency models in practical applications. We also explore some intriguing properties of the feature-space attack, e.g. 1) the hidden layers with bigger receptive fields generate sparser perturbations, 2) the deeper hidden layers achieve higher attack success rates, and 3) different loss functions and different attacked layers will result in diverse perturbations. Experiments indicate that the proposed method is able to successfully attack different model architectures across various image scenes.
Tasks	Adversarial Attack, Object Detection
Published	2019-04-02
URL	http://arxiv.org/abs/1904.01231v1
PDF	http://arxiv.org/pdf/1904.01231v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-attacks-against-deep-saliency
Repo
Framework

A Machine Learning Approach to Comment Toxicity Classification


Title	A Machine Learning Approach to Comment Toxicity Classification
Authors	Navoneel Chakrabarty
Abstract	Now-a-days, derogatory comments are often made by one another, not only in offline environment but also immensely in online environments like social networking websites and online communities. So, an Identification combined with Prevention System in all social networking websites and applications, including all the communities, existing in the digital world is a necessity. In such a system, the Identification Block should identify any negative online behaviour and should signal the Prevention Block to take action accordingly. This study aims to analyse any piece of text and detecting different types of toxicity like obscenity, threats, insults and identity-based hatred. The labelled Wikipedia Comment Dataset prepared by Jigsaw is used for the purpose. A 6-headed Machine Learning tf-idf Model has been made and trained separately, yielding a Mean Validation Accuracy of 98.08% and Absolute Validation Accuracy of 91.61%. Such an Automated System should be deployed for enhancing healthy online conversation
Tasks
Published	2019-02-27
URL	http://arxiv.org/abs/1903.06765v1
PDF	http://arxiv.org/pdf/1903.06765v1.pdf
PWC	https://paperswithcode.com/paper/a-machine-learning-approach-to-comment
Repo
Framework

SEGAN: Structure-Enhanced Generative Adversarial Network for Compressed Sensing MRI Reconstruction


Title	SEGAN: Structure-Enhanced Generative Adversarial Network for Compressed Sensing MRI Reconstruction
Authors	Zhongnian Li, Tao Zhang, Peng Wan, Daoqiang Zhang
Abstract	Generative Adversarial Networks (GANs) are powerful tools for reconstructing Compressed Sensing Magnetic Resonance Imaging (CS-MRI). However most recent works lack exploration of structure information of MRI images that is crucial for clinical diagnosis. To tackle this problem, we propose the Structure-Enhanced GAN (SEGAN) that aims at restoring structure information at both local and global scale. SEGAN defines a new structure regularization called Patch Correlation Regularization (PCR) which allows for efficient extraction of structure information. In addition, to further enhance the ability to uncover structure information, we propose a novel generator SU-Net by incorporating multiple-scale convolution filters into each layer. Besides, we theoretically analyze the convergence of stochastic factors contained in training process. Experimental results show that SEGAN is able to learn target structure information and achieves state-of-the-art performance for CS-MRI reconstruction.
Tasks
Published	2019-02-18
URL	http://arxiv.org/abs/1902.06455v2
PDF	http://arxiv.org/pdf/1902.06455v2.pdf
PWC	https://paperswithcode.com/paper/segan-structure-enhanced-generative
Repo
Framework

Deep Closed-Form Subspace Clustering


Title	Deep Closed-Form Subspace Clustering
Authors	Junghoon Seo, Jamyoung Koo, Taegyun Jeon
Abstract	We propose Deep Closed-Form Subspace Clustering (DCFSC), a new embarrassingly simple model for subspace clustering with learning non-linear mapping. Compared with the previous deep subspace clustering (DSC) techniques, our DCFSC does not have any parameters at all for the self-expressive layer. Instead, DCFSC utilizes the implicit data-driven self-expressive layer derived from closed-form shallow auto-encoder. Moreover, DCFSC also has no complicated optimization scheme, unlike the other subspace clustering methods. With its extreme simplicity, DCFSC has significant memory-related benefits over the existing DSC method, especially on the large dataset. Several experiments showed that our DCFSC model had enough potential to be a new reference model for subspace clustering on large-scale high-dimensional dataset.
Tasks
Published	2019-08-26
URL	https://arxiv.org/abs/1908.09419v1
PDF	https://arxiv.org/pdf/1908.09419v1.pdf
PWC	https://paperswithcode.com/paper/deep-closed-form-subspace-clustering
Repo
Framework

Brain-inspired automated visual object discovery and detection


Title	Brain-inspired automated visual object discovery and detection
Authors	Lichao Chen, Sudhir Singh, Thomas Kailath, Vwani Roychowdhury
Abstract	Despite significant recent progress, machine vision systems lag considerably behind their biological counterparts in performance, scalability, and robustness. A distinctive hallmark of the brain is its ability to automatically discover and model objects, at multiscale resolutions, from repeated exposures to unlabeled contextual data and then to be able to robustly detect the learned objects under various nonideal circumstances, such as partial occlusion and different view angles. Replication of such capabilities in a machine would require three key ingredients: (i) access to large-scale perceptual data of the kind that humans experience, (ii) flexible representations of objects, and (iii) an efficient unsupervised learning algorithm. The Internet fortunately provides unprecedented access to vast amounts of visual data. This paper leverages the availability of such data to develop a scalable framework for unsupervised learning of object prototypes–brain-inspired flexible, scale, and shift invariant representations of deformable objects (e.g., humans, motorcycles, cars, airplanes) comprised of parts, their different configurations and views, and their spatial relationships. Computationally, the object prototypes are represented as geometric associative networks using probabilistic constructs such as Markov random fields. We apply our framework to various datasets and show that our approach is computationally scalable and can construct accurate and operational part-aware object models much more efficiently than in much of the recent computer vision literature. We also present efficient algorithms for detection and localization in new scenes of objects and their partial views.
Tasks
Published	2019-09-30
URL	https://arxiv.org/abs/1910.04864v1
PDF	https://arxiv.org/pdf/1910.04864v1.pdf
PWC	https://paperswithcode.com/paper/brain-inspired-automated-visual-object
Repo
Framework

Prior Activation Distribution (PAD): A Versatile Representation to Utilize DNN Hidden Units


Title	Prior Activation Distribution (PAD): A Versatile Representation to Utilize DNN Hidden Units
Authors	Lakmal Meegahapola, Vengateswaran Subramaniam, Lance Kaplan, Archan Misra
Abstract	In this paper, we introduce the concept of Prior Activation Distribution (PAD) as a versatile and general technique to capture the typical activation patterns of hidden layer units of a Deep Neural Network used for classification tasks. We show that the combined neural activations of such a hidden layer have class-specific distributional properties, and then define multiple statistical measures to compute how far a test sample’s activations deviate from such distributions. Using a variety of benchmark datasets (including MNIST, CIFAR10, Fashion-MNIST & notMNIST), we show how such PAD-based measures can be used, independent of any training technique, to (a) derive fine-grained uncertainty estimates for inferences; (b) provide inferencing accuracy competitive with alternatives that require execution of the full pipeline, and (c) reliably isolate out-of-distribution test samples.
Tasks
Published	2019-07-05
URL	https://arxiv.org/abs/1907.02711v1
PDF	https://arxiv.org/pdf/1907.02711v1.pdf
PWC	https://paperswithcode.com/paper/prior-activation-distribution-pad-a-versatile
Repo
Framework

Convolutional Prototype Learning for Zero-Shot Recognition


Title	Convolutional Prototype Learning for Zero-Shot Recognition
Authors	Zhizhe Liu, Xingxing Zhang, Zhenfeng Zhu, Shuai Zheng, Yao Zhao, Jian Cheng
Abstract	Zero-shot learning (ZSL) has received increasing attention in recent years especially in areas of fine-grained object recognition, retrieval, and image captioning. The key to ZSL is to transfer knowledge from the seen to the unseen classes via auxiliary class attribute vectors. However, the popularly learned projection functions in previous works cannot generalize well since they assume the distribution consistency between seen and unseen domains at sample-level.Besides, the provided non-visual and unique class attributes can significantly degrade the recognition performance in semantic space. In this paper, we propose a simple yet effective convolutional prototype learning (CPL) framework for zero-shot recognition. By assuming distribution consistency at task-level, our CPL is capable of transferring knowledge smoothly to recognize unseen samples.Furthermore, inside each task, discriminative visual prototypes are learned via a distance based training mechanism. Consequently, we can perform recognition in visual space, instead of semantic space. An extensive group of experiments are then carefully designed and presented, demonstrating that CPL obtains more favorable effectiveness, over currently available alternatives under various settings.
Tasks	Image Captioning, Object Recognition, Zero-Shot Learning
Published	2019-10-22
URL	https://arxiv.org/abs/1910.09728v3
PDF	https://arxiv.org/pdf/1910.09728v3.pdf
PWC	https://paperswithcode.com/paper/convolutional-prototype-learning-for-zero
Repo
Framework

Multichannel Speech Enhancement by Raw Waveform-mapping using Fully Convolutional Networks


Title	Multichannel Speech Enhancement by Raw Waveform-mapping using Fully Convolutional Networks
Authors	Chang-Le Liu, Sze-Wei Fu, You-Jin Li, Jen-Wei Huang, Hsin-Min Wang, Yu Tsao
Abstract	In recent years, waveform-mapping-based speech enhancement (SE) methods have garnered significant attention. These methods generally use a deep learning model to directly process and reconstruct speech waveforms. Because both the input and output are in waveform format, the waveform-mapping-based SE methods can overcome the distortion caused by imperfect phase estimation, which may be encountered in spectral-mapping-based SE systems. So far, most waveform-mapping-based SE methods have focused on single-channel tasks. In this paper, we propose a novel fully convolutional network (FCN) with Sinc and dilated convolutional layers (termed SDFCN) for multichannel SE that operates in the time domain. We also propose an extended version of SDFCN, called the residual SDFCN (termed rSDFCN). The proposed methods are evaluated on two multichannel SE tasks, namely the dual-channel inner-ear microphones SE task and the distributed microphones SE task. The experimental results confirm the outstanding denoising capability of the proposed SE systems on both tasks and the benefits of using the residual architecture on the overall SE performance.
Tasks	Denoising, Speech Enhancement
Published	2019-09-26
URL	https://arxiv.org/abs/1909.11909v3
PDF	https://arxiv.org/pdf/1909.11909v3.pdf
PWC	https://paperswithcode.com/paper/multichannel-speech-enhancement-by-raw
Repo
Framework

Statistical Deformation Reconstruction Using Multi-organ Shape Features for Pancreatic Cancer Localization


Title	Statistical Deformation Reconstruction Using Multi-organ Shape Features for Pancreatic Cancer Localization
Authors	Megumi Nakao, Mitsuhiro Nakamura, Takashi Mizowaki, Tetsuya Matsuda
Abstract	Respiratory motion and the associated deformations of abdominal organs and tumors are essential information in clinical applications. However, inter- and intra-patient multi-organ deformations are complex and have not been statistically formulated, whereas single organ deformations have been widely studied. In this paper, we introduce a multi-organ deformation library and its application to deformation reconstruction based on the shape features of multiple abdominal organs. Statistical multi-organ motion/deformation models of the stomach, liver, left and right kidneys, and duodenum were generated by shape matching their region labels defined on four-dimensional computed tomography images. A total of 250 volumes were measured from 25 pancreatic cancer patients. This paper also proposes a per-region-based deformation learning using the reproducing kernel to predict the displacement of pancreatic cancer for adaptive radiotherapy. The experimental results show that the proposed concept estimates deformations better than general per-patient-based learning models and achieves a clinically acceptable estimation error with a mean distance of 1.2 $\pm$ 0.7 mm and a Hausdorff distance of 4.2 $\pm$ 2.3 mm throughout the respiratory motion.
Tasks
Published	2019-11-13
URL	https://arxiv.org/abs/1911.05439v1
PDF	https://arxiv.org/pdf/1911.05439v1.pdf
PWC	https://paperswithcode.com/paper/statistical-deformation-reconstruction-using
Repo
Framework

Multi-echo Reconstruction from Partial K-space Scans via Adaptively Learnt Basis


Title	Multi-echo Reconstruction from Partial K-space Scans via Adaptively Learnt Basis
Authors	Jyoti Maggu, Prerna Singh, Angshul Majumdar
Abstract	In multi echo imaging, multiple T1/T2 weighted images of the same cross section is acquired. Acquiring multiple scans is time consuming. In order to accelerate, compressed sensing based techniques have been proposed. In recent times, it has been observed in several areas of traditional compressed sensing, that instead of using fixed basis (wavelet, DCT etc.), considerably better results can be achieved by learning the basis adaptively from the data. Motivated by these studies, we propose to employ such adaptive learning techniques to improve reconstruction of multi-echo scans. This work will be based on two basis learning models synthesis (better known as dictionary learning) and analysis (known as transform learning). We modify these basic methods by incorporating structure of the multi echo scans. Our work shows that we can indeed significantly improve multi-echo imaging over compressed sensing based techniques and other unstructured adaptive sparse recovery methods.
Tasks	Dictionary Learning
Published	2019-12-11
URL	https://arxiv.org/abs/1912.06631v1
PDF	https://arxiv.org/pdf/1912.06631v1.pdf
PWC	https://paperswithcode.com/paper/multi-echo-reconstruction-from-partial-k
Repo
Framework

Controllable and Progressive Image Extrapolation


Title	Controllable and Progressive Image Extrapolation
Authors	Yijun Li, Lu Jiang, Ming-Hsuan Yang
Abstract	Image extrapolation aims at expanding the narrow field of view of a given image patch. Existing models mainly deal with natural scene images of homogeneous regions and have no control of the content generation process. In this work, we study conditional image extrapolation to synthesize new images guided by the input structured text. The text is represented as a graph to specify the objects and their spatial relation to the unknown regions of the image. Inspired by drawing techniques, we propose a progressive generative model of three stages, i.e., generating a coarse bounding-boxes layout, refining it to a finer segmentation layout, and mapping the layout to a realistic output. Such a multi-stage design is shown to facilitate the training process and generate more controllable results. We validate the effectiveness of the proposed method on the face and human clothing dataset in terms of visual results, quantitative evaluations and flexible controls.
Tasks
Published	2019-12-25
URL	https://arxiv.org/abs/1912.11711v1
PDF	https://arxiv.org/pdf/1912.11711v1.pdf
PWC	https://paperswithcode.com/paper/controllable-and-progressive-image
Repo
Framework

UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation


Title	UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation
Authors	Junjiao Tian, Wesley Cheung, Nathan Glaser, Yen-Cheng Liu, Zsolt Kira
Abstract	The fusion of multiple sensor modalities, especially through deep learning architectures, has been an active area of study. However, an under-explored aspect of such work is whether the methods can be robust to degradations across their input modalities, especially when they must generalize to degradations not seen during training. In this work, we propose an uncertainty-aware fusion scheme to effectively fuse inputs that might suffer from a range of known and unknown degradations. Specifically, we analyze a number of uncertainty measures, each of which captures a different aspect of uncertainty, and we propose a novel way to fuse degraded inputs by scaling modality-specific output softmax probabilities. We additionally propose a novel data-dependent spatial temperature scaling method to complement these existing uncertainty measures. Finally, we integrate the uncertainty-scaled output from each modality using a probabilistic noisy-or fusion method. In a photo-realistic simulation environment (AirSim), we show that our method achieves significantly better results on a semantic segmentation task, compared to state-of-art fusion architectures, on a range of degradations (e.g. fog, snow, frost, and various other types of noise), some of which are unknown during training. We specifically improve upon the state-of-art[1] by 28% in mean IoU on various degradations. [1] Abhinav Valada, Rohit Mohan, and Wolfram Burgard. Self-Supervised Model Adaptation for Multimodal Semantic Segmentation. In: arXiv e-prints, arXiv:1808.03833 (Aug. 2018), arXiv:1808.03833. arXiv: 1808.03833 [cs.CV].
Tasks	Semantic Segmentation
Published	2019-11-06
URL	https://arxiv.org/abs/1911.05611v2
PDF	https://arxiv.org/pdf/1911.05611v2.pdf
PWC	https://paperswithcode.com/paper/uno-uncertainty-aware-noisy-or-multimodal
Repo
Framework

The Case for Evaluating Causal Models Using Interventional Measures and Empirical Data


Title	The Case for Evaluating Causal Models Using Interventional Measures and Empirical Data
Authors	Amanda Gentzel, Dan Garant, David Jensen
Abstract	Causal inference is central to many areas of artificial intelligence, including complex reasoning, planning, knowledge-base construction, robotics, explanation, and fairness. An active community of researchers develops and enhances algorithms that learn causal models from data, and this work has produced a series of impressive technical advances. However, evaluation techniques for causal modeling algorithms have remained somewhat primitive, limiting what we can learn from experimental studies of algorithm performance, constraining the types of algorithms and model representations that researchers consider, and creating a gap between theory and practice. We argue for more frequent use of evaluation techniques that examine interventional measures rather than structural or observational measures, and that evaluate those measures on empirical data rather than synthetic data. We survey the current practice in evaluation and show that the techniques we recommend are rarely used in practice. We show that such techniques are feasible and that data sets are available to conduct such evaluations. We also show that these techniques produce substantially different results than using structural measures and synthetic data.
Tasks	Causal Inference
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05387v2
PDF	https://arxiv.org/pdf/1910.05387v2.pdf
PWC	https://paperswithcode.com/paper/the-case-for-evaluating-causal-models-using
Repo
Framework