April 2, 2020

3079 words 15 mins read

Paper Group ANR 320

Paper Group ANR 320

Total Deep Variation for Linear Inverse Problems. Transferability of Adversarial Examples to Attack Cloud-based Image Classifier Service. Learning Cross-domain Semantic-Visual Relation for Transductive Zero-Shot Learning. AD-VO: Scale-Resilient Visual Odometry Using Attentive Disparity Map. Confidence Sets and Hypothesis Testing in a Likelihood-Fre …

Total Deep Variation for Linear Inverse Problems

Title Total Deep Variation for Linear Inverse Problems
Authors Erich Kobler, Alexander Effland, Karl Kunisch, Thomas Pock
Abstract Diverse inverse problems in imaging can be cast as variational problems composed of a task-specific data fidelity term and a regularization term. In this paper, we propose a novel learnable general-purpose regularizer exploiting recent architectural design patterns from deep learning. We cast the learning problem as a discrete sampled optimal control problem, for which we derive the adjoint state equations and an optimality condition. By exploiting the variational structure of our approach, we perform a sensitivity analysis with respect to the learned parameters obtained from different training datasets. Moreover, we carry out a nonlinear eigenfunction analysis, which reveals interesting properties of the learned regularizer. We show state-of-the-art performance for classical image restoration and medical image reconstruction problems.
Tasks Image Reconstruction, Image Restoration
Published 2020-01-14
URL https://arxiv.org/abs/2001.05005v2
PDF https://arxiv.org/pdf/2001.05005v2.pdf
PWC https://paperswithcode.com/paper/total-deep-variation-for-linear-inverse

Transferability of Adversarial Examples to Attack Cloud-based Image Classifier Service

Title Transferability of Adversarial Examples to Attack Cloud-based Image Classifier Service
Authors Dou Goodman
Abstract In recent years, Deep Learning(DL) techniques have been extensively deployed for computer vision tasks, particularly visual classification problems, where new algorithms reported to achieve or even surpass the human performance. While many recent works demonstrated that DL models are vulnerable to adversarial examples. Fortunately, generating adversarial examples usually requires white-box access to the victim model, and real-world cloud-based image classification services are more complex than white-box classifier,the architecture and parameters of DL models on cloud platforms cannot be obtained by the attacker. The attacker can only access the APIs opened by cloud platforms. Thus, keeping models in the cloud can usually give a (false) sense of security. In this paper, we mainly focus on studying the security of real-world cloud-based image classification services. Specifically, (1) We propose a novel attack method, Fast Featuremap Loss PGD (FFL-PGD) attack based on Substitution model, which achieves a high bypass rate with a very limited number of queries. Instead of millions of queries in previous studies, our method finds the adversarial examples using only two queries per image; and (2) we make the first attempt to conduct an extensive empirical study of black-box attacks against real-world cloud-based classification services. Through evaluations on four popular cloud platforms including Amazon, Google, Microsoft, Clarifai, we demonstrate that FFL-PGD attack has a success rate over 90% among different classification services. (3) We discuss the possible defenses to address these security challenges in cloud-based classification services. Our defense technology is mainly divided into model training stage and image preprocessing stage.
Tasks Image Classification
Published 2020-01-08
URL https://arxiv.org/abs/2001.03460v3
PDF https://arxiv.org/pdf/2001.03460v3.pdf
PWC https://paperswithcode.com/paper/cloud-based-image-classification-service-is-1

Learning Cross-domain Semantic-Visual Relation for Transductive Zero-Shot Learning

Title Learning Cross-domain Semantic-Visual Relation for Transductive Zero-Shot Learning
Authors Jianyang Zhang, Fengmao Lv, Guowu Yang, Lei Feng, Yufeng Yu, Lixin Duan
Abstract Zero-Shot Learning (ZSL) aims to learn recognition models for recognizing new classes without labeled data. In this work, we propose a novel approach dubbed Transferrable Semantic-Visual Relation (TSVR) to facilitate the cross-category transfer in transductive ZSL. Our approach draws on an intriguing insight connecting two challenging problems, i.e. domain adaptation and zero-shot learning. Domain adaptation aims to transfer knowledge across two different domains (i.e., source domain and target domain) that share the identical task/label space. For ZSL, the source and target domains have different tasks/label spaces. Hence, ZSL is usually considered as a more difficult transfer setting compared with domain adaptation. Although the existing ZSL approaches use semantic attributes of categories to bridge the source and target domains, their performances are far from satisfactory due to the large domain gap between different categories. In contrast, our method directly transforms ZSL into a domain adaptation task through redrawing ZSL as predicting the similarity/dissimilarity labels for the pairs of semantic attributes and visual features. For this redrawn domain adaptation problem, we propose to use a domain-specific batch normalization component to reduce the domain discrepancy of semantic-visual pairs. Experimental results over diverse ZSL benchmarks clearly demonstrate the superiority of our method.
Tasks Domain Adaptation, Zero-Shot Learning
Published 2020-03-31
URL https://arxiv.org/abs/2003.14105v1
PDF https://arxiv.org/pdf/2003.14105v1.pdf
PWC https://paperswithcode.com/paper/learning-cross-domain-semantic-visual

AD-VO: Scale-Resilient Visual Odometry Using Attentive Disparity Map

Title AD-VO: Scale-Resilient Visual Odometry Using Attentive Disparity Map
Authors Joosung Lee, Sangwon Hwang, Kyungjae Lee, Woo Jin Kim, Junhyeop Lee, Tae-young Chung, Sangyoun Lee
Abstract Visual odometry is an essential key for a localization module in SLAM systems. However, previous methods require tuning the system to adapt environment changes. In this paper, we propose a learning-based approach for frame-to-frame monocular visual odometry estimation. The proposed network is only learned by disparity maps for not only covering the environment changes but also solving the scale problem. Furthermore, attention block and skip-ordering scheme are introduced to achieve robust performance in various driving environment. Our network is compared with the conventional methods which use common domain such as color or optical flow. Experimental results confirm that the proposed network shows better performance than other approaches with higher and more stable results.
Tasks Monocular Visual Odometry, Optical Flow Estimation, Visual Odometry
Published 2020-01-07
URL https://arxiv.org/abs/2001.02090v1
PDF https://arxiv.org/pdf/2001.02090v1.pdf
PWC https://paperswithcode.com/paper/ad-vo-scale-resilient-visual-odometry-using

Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference Setting

Title Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference Setting
Authors Niccolò Dalmasso, Rafael Izbicki, Ann B. Lee
Abstract Parameter estimation, statistical tests and confidence sets are the cornerstones of classical statistics that allow scientists to make inferences about the underlying process that generated the observed data. A key question is whether one can still construct hypothesis tests and confidence sets with proper coverage and high power in a so-called likelihood-free inference (LFI) setting; that is, a setting where the likelihood is not explicitly known but one can forward-simulate observable data according to a stochastic model. In this paper, we present $\texttt{ACORE}$ (Approximate Computation via Odds Ratio Estimation), a frequentist approach to LFI that first formulates the classical likelihood ratio test (LRT) as a parametrized classification problem, and then uses the equivalence of tests and confidence sets to build confidence regions for parameters of interest. We also present a goodness-of-fit procedure for checking whether the constructed tests and confidence regions are valid. $\texttt{ACORE}$ is based on the key observation that the LRT statistic, the rejection probability of the test, and the coverage of the confidence set are conditional distribution functions which often vary smoothly as a function of the parameters of interest. Hence, instead of relying solely on samples simulated at fixed parameter settings (as is the convention in standard Monte Carlo solutions), one can leverage machine learning tools and data simulated in the neighborhood of a parameter to improve estimates of quantities of interest. We demonstrate the efficacy of $\texttt{ACORE}$ with both theoretical and empirical results. Our implementation is available on Github.
Published 2020-02-24
URL https://arxiv.org/abs/2002.10399v1
PDF https://arxiv.org/pdf/2002.10399v1.pdf
PWC https://paperswithcode.com/paper/confidence-sets-and-hypothesis-testing-in-a

DEEVA: A Deep Learning and IoT Based Computer Vision System to Address Safety and Security of Production Sites in Energy Industry

Title DEEVA: A Deep Learning and IoT Based Computer Vision System to Address Safety and Security of Production Sites in Energy Industry
Authors Nimish M. Awalgaonkar, Haining Zheng, Christopher S. Gurciullo
Abstract When it comes to addressing the safety/security related needs at different production/construction sites, accurate detection of the presence of workers, vehicles, equipment important and formed an integral part of computer vision-based surveillance systems (CVSS). Traditional CVSS systems focus on the use of different computer vision and pattern recognition algorithms overly reliant on manual extraction of features and small datasets, limiting their usage because of low accuracy, need for expert knowledge and high computational costs. The main objective of this paper is to provide decision makers at sites with a practical yet comprehensive deep learning and IoT based solution to tackle various computer vision related problems such as scene classification, object detection in scenes, semantic segmentation, scene captioning etc. Our overarching goal is to address the central question of What is happening at this site and where is it happening in an automated fashion minimizing the need for human resources dedicated to surveillance. We developed Deep ExxonMobil Eye for Video Analysis (DEEVA) package to handle scene classification, object detection, semantic segmentation and captioning of scenes in a hierarchical approach. The results reveal that transfer learning with the RetinaNet object detector is able to detect the presence of workers, different types of vehicles/construction equipment, safety related objects at a high level of accuracy (above 90%). With the help of deep learning to automatically extract features and IoT technology to automatic capture, transfer and process vast amount of realtime images, this framework is an important step towards the development of intelligent surveillance systems aimed at addressing myriads of open ended problems in the realm of security/safety monitoring, productivity assessments and future decision making.
Tasks Decision Making, Object Detection, Scene Classification, Semantic Segmentation, Transfer Learning
Published 2020-03-02
URL https://arxiv.org/abs/2003.01196v1
PDF https://arxiv.org/pdf/2003.01196v1.pdf
PWC https://paperswithcode.com/paper/deeva-a-deep-learning-and-iot-based-computer

CARPAL: Confidence-Aware Intent Recognition for Parallel Autonomy

Title CARPAL: Confidence-Aware Intent Recognition for Parallel Autonomy
Authors Xin Huang, Stephen G. McGill, Jonathan A. DeCastro, Brian C. Williams, Luke Fletcher, John J. Leonard, Guy Rosman
Abstract Predicting the behavior of road agents is a difficult and crucial task for both advanced driver assistance and autonomous driving systems. Traditional confidence measures for this important task often ignore the way predicted trajectories affect downstream decisions and their utilities. In this paper we devise a novel neural network regressor to estimate the utility distribution given the predictions. Based on reasonable assumptions on the utility function, we establish a decision criterion that takes into account the role of prediction in decision making. We train our real-time regressor along with a human driver intent predictor and use it in shared autonomy scenarios where decisions depend on the prediction confidence. We test our system on a realistic urban driving dataset, present the advantage of the resulting system in terms of recall and fall-out performance compared to baseline methods, and demonstrate its effectiveness in intervention and warning use cases.
Tasks Autonomous Driving, Decision Making
Published 2020-03-18
URL https://arxiv.org/abs/2003.08003v1
PDF https://arxiv.org/pdf/2003.08003v1.pdf
PWC https://paperswithcode.com/paper/carpal-confidence-aware-intent-recognition

Learning to Optimize Autonomy in Competence-Aware Systems

Title Learning to Optimize Autonomy in Competence-Aware Systems
Authors Connor Basich, Justin Svegliato, Kyle Hollins Wray, Stefan Witwicki, Joydeep Biswas, Shlomo Zilberstein
Abstract Interest in semi-autonomous systems (SAS) is growing rapidly as a paradigm to deploy autonomous systems in domains that require occasional reliance on humans. This paradigm allows service robots or autonomous vehicles to operate at varying levels of autonomy and offer safety in situations that require human judgment. We propose an introspective model of autonomy that is learned and updated online through experience and dictates the extent to which the agent can act autonomously in any given situation. We define a competence-aware system (CAS) that explicitly models its own proficiency at different levels of autonomy and the available human feedback. A CAS learns to adjust its level of autonomy based on experience to maximize overall efficiency, factoring in the cost of human assistance. We analyze the convergence properties of CAS and provide experimental results for robot delivery and autonomous driving domains that demonstrate the benefits of the approach.
Tasks Autonomous Driving, Autonomous Vehicles
Published 2020-03-17
URL https://arxiv.org/abs/2003.07745v1
PDF https://arxiv.org/pdf/2003.07745v1.pdf
PWC https://paperswithcode.com/paper/learning-to-optimize-autonomy-in-competence

Stepwise Model Selection for Sequence Prediction via Deep Kernel Learning

Title Stepwise Model Selection for Sequence Prediction via Deep Kernel Learning
Authors Yao Zhang, Daniel Jarrett, Mihaela van der Schaar
Abstract An essential problem in automated machine learning (AutoML) is that of model selection. A unique challenge in the sequential setting is the fact that the optimal model itself may vary over time, depending on the distribution of features and labels available up to each point in time. In this paper, we propose a novel Bayesian optimization (BO) algorithm to tackle the challenge of model selection in this setting. This is accomplished by treating the performance at each time step as its own black-box function. In order to solve the resulting multiple black-box function optimization problem jointly and efficiently, we exploit potential correlations among black-box functions using deep kernel learning (DKL). To the best of our knowledge, we are the first to formulate the problem of stepwise model selection (SMS) for sequence prediction, and to design and demonstrate an efficient joint-learning algorithm for this purpose. Using multiple real-world datasets, we verify that our proposed method outperforms both standard BO and multi-objective BO algorithms on a variety of sequence prediction tasks.
Tasks AutoML, Model Selection
Published 2020-01-12
URL https://arxiv.org/abs/2001.03898v3
PDF https://arxiv.org/pdf/2001.03898v3.pdf
PWC https://paperswithcode.com/paper/stepwise-model-selection-for-sequence

LaserFlow: Efficient and Probabilistic Object Detection and Motion Forecasting

Title LaserFlow: Efficient and Probabilistic Object Detection and Motion Forecasting
Authors Gregory P. Meyer, Jake Charland, Shreyash Pandey, Ankit Laddha, Carlos Vallespi-Gonzalez, Carl K. Wellington
Abstract In this work, we present LaserFlow, an efficient method for 3D object detection and motion forecasting from LiDAR. Unlike the previous work, our approach utilizes the native range view representation of the LiDAR, which enables our method to operate at the full range of the sensor in real-time without voxelization or compression of the data. We propose a new multi-sweep fusion architecture, which extracts and merges temporal features directly from the range images. Furthermore, we propose a novel technique for learning a probability distribution over future trajectories inspired by curriculum learning. We evaluate LaserFlow on two autonomous driving datasets and demonstrate competitive results when compared to the existing state-of-the-art methods.
Tasks 3D Object Detection, Autonomous Driving, Motion Forecasting, Object Detection
Published 2020-03-12
URL https://arxiv.org/abs/2003.05982v1
PDF https://arxiv.org/pdf/2003.05982v1.pdf
PWC https://paperswithcode.com/paper/laserflow-efficient-and-probabilistic-object

Adversarial Perturbations Prevail in the Y-Channel of the YCbCr Color Space

Title Adversarial Perturbations Prevail in the Y-Channel of the YCbCr Color Space
Authors Camilo Pestana, Naveed Akhtar, Wei Liu, David Glance, Ajmal Mian
Abstract Deep learning offers state of the art solutions for image recognition. However, deep models are vulnerable to adversarial perturbations in images that are subtle but significantly change the model’s prediction. In a white-box attack, these perturbations are generally learned for deep models that operate on RGB images and, hence, the perturbations are equally distributed in the RGB color space. In this paper, we show that the adversarial perturbations prevail in the Y-channel of the YCbCr space. Our finding is motivated from the fact that the human vision and deep models are more responsive to shape and texture rather than color. Based on our finding, we propose a defense against adversarial images. Our defence, coined ResUpNet, removes perturbations only from the Y-channel by exploiting ResNet features in an upsampling framework without the need for a bottleneck. At the final stage, the untouched CbCr-channels are combined with the refined Y-channel to restore the clean image. Note that ResUpNet is model agnostic as it does not modify the DNN structure. ResUpNet is trained end-to-end in Pytorch and the results are compared to existing defence techniques in the input transformation category. Our results show that our approach achieves the best balance between defence against adversarial attacks such as FGSM, PGD and DDN and maintaining the original accuracies of VGG-16, ResNet50 and DenseNet121 on clean images. We perform another experiment to show that learning adversarial perturbations only for the Y-channel results in higher fooling rates for the same perturbation magnitude.
Published 2020-02-25
URL https://arxiv.org/abs/2003.00883v1
PDF https://arxiv.org/pdf/2003.00883v1.pdf
PWC https://paperswithcode.com/paper/adversarial-perturbations-prevail-in-the-y

Fast Complete Algorithm for Multiplayer Nash Equilibrium

Title Fast Complete Algorithm for Multiplayer Nash Equilibrium
Authors Sam Ganzfried
Abstract We describe a new complete algorithm for computing Nash equilibrium in multiplayer general-sum games, based on a quadratically-constrained feasibility program formulation. We demonstrate that the algorithm runs significantly faster than the prior fastest complete algorithm on several game classes previously studied and that its runtimes even outperform the best incomplete algorithms.
Published 2020-02-11
URL https://arxiv.org/abs/2002.04734v2
PDF https://arxiv.org/pdf/2002.04734v2.pdf
PWC https://paperswithcode.com/paper/fast-complete-algorithm-for-multiplayer-nash

A survey on Machine Learning-based Performance Improvement of Wireless Networks: PHY, MAC and Network layer

Title A survey on Machine Learning-based Performance Improvement of Wireless Networks: PHY, MAC and Network layer
Authors Merima Kulin, Tarik Kazaz, Ingrid Moerman, Eli de Poorter
Abstract This paper provides a systematic and comprehensive survey that reviews the latest research efforts focused on machine learning (ML) based performance improvement of wireless networks, while considering all layers of the protocol stack (PHY, MAC and network). First, the related work and paper contributions are discussed, followed by providing the necessary background on data-driven approaches and machine learning for non-machine learning experts to understand all discussed techniques. Then, a comprehensive review is presented on works employing ML-based approaches to optimize the wireless communication parameters settings to achieve improved network quality-of-service (QoS) and quality-of-experience (QoE). We first categorize these works into: radio analysis, MAC analysis and network prediction approaches, followed by subcategories within each. Finally, open challenges and broader perspectives are discussed.
Published 2020-01-13
URL https://arxiv.org/abs/2001.04561v2
PDF https://arxiv.org/pdf/2001.04561v2.pdf
PWC https://paperswithcode.com/paper/a-survey-on-machine-learning-based

Structural Combinatorial of Network Information System of Systems based on Evolutionary Optimization Method

Title Structural Combinatorial of Network Information System of Systems based on Evolutionary Optimization Method
Authors Tingting Zhang, Yushi Lan, Aiguo Song, Kun Liu, Nan Wang
Abstract The network information system is a military information network system with evolution characteristics. Evolution is a process of replacement between disorder and order, chaos and equilibrium. Given that the concept of evolution originates from biological systems, in this article, the evolution of network information architecture is analyzed by genetic algorithms, and the network information architecture is represented by chromosomes. Besides, the genetic algorithm is also applied to find the optimal chromosome in the architecture space. The evolutionary simulation is used to predict the optimal scheme of the network information architecture and provide a reference for system construction.
Published 2020-02-22
URL https://arxiv.org/abs/2002.09706v1
PDF https://arxiv.org/pdf/2002.09706v1.pdf
PWC https://paperswithcode.com/paper/structural-combinatorial-of-network

Fake News Detection with Different Models

Title Fake News Detection with Different Models
Authors Sairamvinay Vijayaraghavan, Ye Wang, Zhiyuan Guo, John Voong, Wenda Xu, Armand Nasseri, Jiaru Cai, Linda Li, Kevin Vuong, Eshan Wadhwa
Abstract This is a paper for exploring various different models aiming at developing fake news detection models and we had used certain machine learning algorithms and we had used pretrained algorithms such as TFIDF and CV and W2V as features for processing textual data.
Tasks Fake News Detection
Published 2020-02-15
URL https://arxiv.org/abs/2003.04978v1
PDF https://arxiv.org/pdf/2003.04978v1.pdf
PWC https://paperswithcode.com/paper/fake-news-detection-with-different-models
comments powered by Disqus