January 27, 2020

3335 words 16 mins read

Paper Group ANR 1344

Cooperative coevolution of real predator robots and virtual robots in the pursuit domain. Momentum-Net: Fast and convergent iterative neural network for inverse problems. Efficient Decision-based Black-box Adversarial Attacks on Face Recognition. The Challenge of Imputation in Explainable Artificial Intelligence Models. Cost-aware Multi-objective B …

Cooperative coevolution of real predator robots and virtual robots in the pursuit domain


Title	Cooperative coevolution of real predator robots and virtual robots in the pursuit domain
Authors	Lijun Sun, Chao Lyu, Yuhui Shi
Abstract	The pursuit domain, or predator-prey problem is a standard testbed for the study of coordination techniques. In spite that its problem setup is apparently simple, it is challenging for the research of the emerged swarm intelligence. This paper presents a particle swarm optimization (PSO) based cooperative coevolutionary algorithm for the predator robots, called CCPSO-R, where real and virtual robots coexist for the first time in an evolutionary algorithm (EA). Virtual robots sample and explore the vicinity of the corresponding real robot and act as their action spaces, while the real robots consist of the real predators swarm who actually pursue the prey robot without fixed behavior rules under the immediate guidance of the fitness function, which is designed in a modular manner with very limited domain knowledges. In addition, kinematic limits and collision avoidance considerations are integrated into the update rules of robots. Experiments are conducted on a scalable predator robots swarm with 4 types of preys, the statistical results of which show the reliability, generality, and scalability of the proposed CCPSO-R. Finally, the codes of this paper are public availabe at: https://github.com/LijunSun90/pursuitCCPSO_R.
Tasks
Published	2019-01-23
URL	http://arxiv.org/abs/1901.07865v1
PDF	http://arxiv.org/pdf/1901.07865v1.pdf
PWC	https://paperswithcode.com/paper/cooperative-coevolution-of-real-predator
Repo
Framework

Momentum-Net: Fast and convergent iterative neural network for inverse problems


Title	Momentum-Net: Fast and convergent iterative neural network for inverse problems
Authors	Il Yong Chun, Zhengyu Huang, Hongki Lim, Jeffrey A. Fessler
Abstract	Iterative neural networks (INN) are rapidly gaining attention for solving inverse problems in imaging, image processing, and computer vision. INNs combine regression NNs and an iterative model-based image reconstruction (MBIR) algorithm, leading to both good generalization capability and outperforming reconstruction quality over existing MBIR optimization models. This paper proposes the first fast and convergent INN architecture, Momentum-Net, by generalizing a block-wise MBIR algorithm that uses momentums and majorizers with regression NNs. For fast MBIR, Momentum-Net uses momentum terms in extrapolation modules, and noniterative MBIR modules at each layer by using majorizers, where each layer of Momentum-Net consists of three core modules: image refining, extrapolation, and MBIR. Momentum-Net guarantees convergence to a fixed-point for general differentiable (non)convex MBIR functions (or data-fit terms) and convex feasible sets, under two asymptomatic conditions. To consider data-fit variations across training and testing samples, we also propose a regularization parameter selection scheme based on the spectral radius of majorization matrices. Numerical experiments for light-field photography using a focal stack and sparse-view computational tomography demonstrate that given identical regression NN architectures, Momentum-Net significantly improves MBIR speed and accuracy over several existing INNs; it significantly improves reconstruction quality compared to a state-of-the-art MBIR method in each application.
Tasks	Image Reconstruction
Published	2019-07-26
URL	https://arxiv.org/abs/1907.11818v2
PDF	https://arxiv.org/pdf/1907.11818v2.pdf
PWC	https://paperswithcode.com/paper/momentum-net-fast-and-convergent-iterative
Repo
Framework

Efficient Decision-based Black-box Adversarial Attacks on Face Recognition


Title	Efficient Decision-based Black-box Adversarial Attacks on Face Recognition
Authors	Yinpeng Dong, Hang Su, Baoyuan Wu, Zhifeng Li, Wei Liu, Tong Zhang, Jun Zhu
Abstract	Face recognition has obtained remarkable progress in recent years due to the great improvement of deep convolutional neural networks (CNNs). However, deep CNNs are vulnerable to adversarial examples, which can cause fateful consequences in real-world face recognition applications with security-sensitive purposes. Adversarial attacks are widely studied as they can identify the vulnerability of the models before they are deployed. In this paper, we evaluate the robustness of state-of-the-art face recognition models in the decision-based black-box attack setting, where the attackers have no access to the model parameters and gradients, but can only acquire hard-label predictions by sending queries to the target model. This attack setting is more practical in real-world face recognition systems. To improve the efficiency of previous methods, we propose an evolutionary attack algorithm, which can model the local geometries of the search directions and reduce the dimension of the search space. Extensive experiments demonstrate the effectiveness of the proposed method that induces a minimum perturbation to an input face image with fewer queries. We also apply the proposed method to attack a real-world face recognition system successfully.
Tasks	Face Recognition
Published	2019-04-09
URL	http://arxiv.org/abs/1904.04433v1
PDF	http://arxiv.org/pdf/1904.04433v1.pdf
PWC	https://paperswithcode.com/paper/efficient-decision-based-black-box
Repo
Framework

The Challenge of Imputation in Explainable Artificial Intelligence Models


Title	The Challenge of Imputation in Explainable Artificial Intelligence Models
Authors	Muhammad Aurangzeb Ahmad, Carly Eckert, Ankur Teredesai
Abstract	Explainable models in Artificial Intelligence are often employed to ensure transparency and accountability of AI systems. The fidelity of the explanations are dependent upon the algorithms used as well as on the fidelity of the data. Many real world datasets have missing values that can greatly influence explanation fidelity. The standard way to deal with such scenarios is imputation. This can, however, lead to situations where the imputed values may correspond to a setting which refer to counterfactuals. Acting on explanations from AI models with imputed values may lead to unsafe outcomes. In this paper, we explore different settings where AI models with imputation can be problematic and describe ways to address such scenarios.
Tasks	Imputation
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12669v1
PDF	https://arxiv.org/pdf/1907.12669v1.pdf
PWC	https://paperswithcode.com/paper/the-challenge-of-imputation-in-explainable
Repo
Framework

Cost-aware Multi-objective Bayesian optimisation


Title	Cost-aware Multi-objective Bayesian optimisation
Authors	Majid Abdolshah, Alistair Shilton, Santu Rana, Sunil Gupta, Svetha Venkatesh
Abstract	The notion of expense in Bayesian optimisation generally refers to the uniformly expensive cost of function evaluations over the whole search space. However, in some scenarios, the cost of evaluation for black-box objective functions is non-uniform since different inputs from search space may incur different costs for function evaluations. We introduce a cost-aware multi-objective Bayesian optimisation with non-uniform evaluation cost over objective functions by defining cost-aware constraints over the search space. The cost-aware constraints are a sorted tuple of indexes that demonstrate the ordering of dimensions of the search space based on the user’s prior knowledge about their cost of usage. We formulate a new multi-objective Bayesian optimisation acquisition function with detailed analysis of the convergence that incorporates this cost-aware constraints while optimising the objective functions. We demonstrate our algorithm based on synthetic and real-world problems in hyperparameter tuning of neural networks and random forests.
Tasks	Bayesian Optimisation
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03600v1
PDF	https://arxiv.org/pdf/1909.03600v1.pdf
PWC	https://paperswithcode.com/paper/cost-aware-multi-objective-bayesian
Repo
Framework

Iterative augmentation of visual evidence for weakly-supervised lesion localization in deep interpretability frameworks


Title	Iterative augmentation of visual evidence for weakly-supervised lesion localization in deep interpretability frameworks
Authors	Cristina González-Gonzalo, Bart Liefers, Bram van Ginneken, Clara I. Sánchez
Abstract	Interpretability of deep learning (DL) systems is gaining attention in medical imaging to increase experts’ trust in the obtained predictions and facilitate their integration in clinical settings. We propose a deep visualization method to generate interpretability of DL classification tasks in medical imaging by means of visual evidence augmentation. The proposed method iteratively unveils abnormalities based on the prediction of a classifier trained only with image-level labels. For each image, initial visual evidence of the prediction is extracted with a given visual attribution technique. This provides localization of abnormalities that are then removed through selective inpainting. We iteratively apply this procedure until the system considers the image as normal. This yields augmented visual evidence, including less discriminative lesions which were not detected at first but should be considered for final diagnosis. We apply the method to grading of two retinal diseases in color fundus images: diabetic retinopathy (DR) and age-related macular degeneration (AMD). We evaluate the generated visual evidence and the performance of weakly-supervised localization of different types of DR and AMD abnormalities, both qualitatively and quantitatively. We show that the augmented visual evidence of the predictions highlights the biomarkers considered by the experts for diagnosis and improves the final localization performance. It results in a relative increase of 11.2$\pm$2.0% per image regarding average sensitivity per average 10 false positives, when applied to different classification tasks, visual attribution techniques and network architectures. This makes the proposed method a useful tool for exhaustive visual support of DL classifiers in medical imaging.
Tasks
Published	2019-10-16
URL	https://arxiv.org/abs/1910.07373v1
PDF	https://arxiv.org/pdf/1910.07373v1.pdf
PWC	https://paperswithcode.com/paper/iterative-augmentation-of-visual-evidence-for
Repo
Framework

Off-road Autonomous Vehicles Traversability Analysis and Trajectory Planning Based on Deep Inverse Reinforcement Learning


Title	Off-road Autonomous Vehicles Traversability Analysis and Trajectory Planning Based on Deep Inverse Reinforcement Learning
Authors	Zeyu Zhu, Nan Li, Ruoyu Sun, Huijing Zhao, Donghao Xu
Abstract	Terrain traversability analysis is a fundamental issue to achieve the autonomy of a robot at off-road environments. Geometry-based and appearance-based methods have been studied in decades, while behavior-based methods exploiting learning from demonstration (LfD) are new trends. Behavior-based methods learn cost functions that guide trajectory planning in compliance with experts’ demonstrations, which can be more scalable to various scenes and driving behaviors. This research proposes a method of off-road traversability analysis and trajectory planning using Deep Maximum Entropy Inverse Reinforcement Learning. To incorporate vehicle’s kinematics while solving the problem of exponential increase of state-space complexity, two convolutional neural networks, i.e., RL ConvNet and Svf ConvNet, are developed to encode kinematics into convolution kernels and achieve efficient forward reinforcement learning. We conduct experiments in off-road environments. Scene maps are generated using 3D LiDAR data, and expert demonstrations are either the vehicle’s real driving trajectories at the scene or synthesized ones to represent specific behaviors such as crossing negative obstacles. Four cost functions of traversability analysis are learned and tested at various scenes of capability in guiding the trajectory planning of different behaviors. We also demonstrate the computation efficiency of the proposed method.
Tasks	Autonomous Vehicles
Published	2019-09-16
URL	https://arxiv.org/abs/1909.06953v1
PDF	https://arxiv.org/pdf/1909.06953v1.pdf
PWC	https://paperswithcode.com/paper/off-road-autonomous-vehicles-traversability
Repo
Framework

uniblock: Scoring and Filtering Corpus with Unicode Block Information


Title	uniblock: Scoring and Filtering Corpus with Unicode Block Information
Authors	Yingbo Gao, Weiyue Wang, Hermann Ney
Abstract	The preprocessing pipelines in Natural Language Processing usually involve a step of removing sentences consisted of illegal characters. The definition of illegal characters and the specific removal strategy depend on the task, language, domain, etc, which often lead to tiresome and repetitive scripting of rules. In this paper, we introduce a simple statistical method, uniblock, to overcome this problem. For each sentence, uniblock generates a fixed-size feature vector using Unicode block information of the characters. A Gaussian mixture model is then estimated on some clean corpus using variational inference. The learned model can then be used to score sentences and filter corpus. We present experimental results on Sentiment Analysis, Language Modeling and Machine Translation, and show the simplicity and effectiveness of our method.
Tasks	Language Modelling, Machine Translation, Sentiment Analysis
Published	2019-08-26
URL	https://arxiv.org/abs/1908.09716v1
PDF	https://arxiv.org/pdf/1908.09716v1.pdf
PWC	https://paperswithcode.com/paper/uniblock-scoring-and-filtering-corpus-with
Repo
Framework

Are Self-Driving Cars Secure? Evasion Attacks against Deep Neural Networks for Steering Angle Prediction


Title	Are Self-Driving Cars Secure? Evasion Attacks against Deep Neural Networks for Steering Angle Prediction
Authors	Alesia Chernikova, Alina Oprea, Cristina Nita-Rotaru, BaekGyu Kim
Abstract	Deep Neural Networks (DNNs) have tremendous potential in advancing the vision for self-driving cars. However, the security of DNN models in this context leads to major safety implications and needs to be better understood. We consider the case study of steering angle prediction from camera images, using the dataset from the 2014 Udacity challenge. We demonstrate for the first time adversarial testing-time attacks for this application for both classification and regression settings. We show that minor modifications to the camera image (an L2 distance of 0.82 for one of the considered models) result in mis-classification of an image to any class of attacker’s choice. Furthermore, our regression attack results in a significant increase in Mean Square Error (MSE) by a factor of 69 in the worst case.
Tasks	Self-Driving Cars
Published	2019-04-15
URL	http://arxiv.org/abs/1904.07370v1
PDF	http://arxiv.org/pdf/1904.07370v1.pdf
PWC	https://paperswithcode.com/paper/are-self-driving-cars-secure-evasion-attacks
Repo
Framework

Generative Adversarial Network for Wireless Signal Spoofing


Title	Generative Adversarial Network for Wireless Signal Spoofing
Authors	Yi Shi, Kemal Davaslioglu, Yalin E. Sagduyu
Abstract	The paper presents a novel approach of spoofing wireless signals by using a general adversarial network (GAN) to generate and transmit synthetic signals that cannot be reliably distinguished from intended signals. It is of paramount importance to authenticate wireless signals at the PHY layer before they proceed through the receiver chain. For that purpose, various waveform, channel, and radio hardware features that are inherent to original wireless signals need to be captured. In the meantime, adversaries become sophisticated with the cognitive radio capability to record, analyze, and manipulate signals before spoofing. Building upon deep learning techniques, this paper introduces a spoofing attack by an adversary pair of a transmitter and a receiver that assume the generator and discriminator roles in the GAN and play a minimax game to generate the best spoofing signals that aim to fool the best trained defense mechanism. The output of this approach is two-fold. From the attacker point of view, a deep learning-based spoofing mechanism is trained to potentially fool a defense mechanism such as RF fingerprinting. From the defender point of view, a deep learning-based defense mechanism is trained against potential spoofing attacks when an adversary pair of a transmitter and a receiver cooperates. The probability that the spoofing signal is misclassified as the intended signal is measured for random signal, replay, and GAN-based spoofing attacks. Results show that the GAN-based spoofing attack provides a major increase in the success probability of wireless signal spoofing even when a deep learning classifier is used as the defense.
Tasks
Published	2019-05-03
URL	https://arxiv.org/abs/1905.01008v2
PDF	https://arxiv.org/pdf/1905.01008v2.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-network-for-wireless
Repo
Framework

ANODEV2: A Coupled Neural ODE Evolution Framework


Title	ANODEV2: A Coupled Neural ODE Evolution Framework
Authors	Tianjun Zhang, Zhewei Yao, Amir Gholami, Kurt Keutzer, Joseph Gonzalez, George Biros, Michael Mahoney
Abstract	It has been observed that residual networks can be viewed as the explicit Euler discretization of an Ordinary Differential Equation (ODE). This observation motivated the introduction of so-called Neural ODEs, which allow more general discretization schemes with adaptive time stepping. Here, we propose ANODEV2, which is an extension of this approach that also allows evolution of the neural network parameters, in a coupled ODE-based formulation. The Neural ODE method introduced earlier is in fact a special case of this new more general framework. We present the formulation of ANODEV2, derive optimality conditions, and implement a coupled reaction-diffusion-advection version of this framework in PyTorch. We present empirical results using several different configurations of ANODEV2, testing them on multiple models on CIFAR-10. We report results showing that this coupled ODE-based framework is indeed trainable, and that it achieves higher accuracy, as compared to the baseline models as well as the recently-proposed Neural ODE approach.
Tasks
Published	2019-06-10
URL	https://arxiv.org/abs/1906.04596v1
PDF	https://arxiv.org/pdf/1906.04596v1.pdf
PWC	https://paperswithcode.com/paper/anodev2-a-coupled-neural-ode-evolution
Repo
Framework

Explainable Fashion Recommendation: A Semantic Attribute Region Guided Approach


Title	Explainable Fashion Recommendation: A Semantic Attribute Region Guided Approach
Authors	Min Hou, Le Wu, Enhong Chen, Zhi Li, Vincent W. Zheng, Qi Liu
Abstract	In fashion recommender systems, each product usually consists of multiple semantic attributes (e.g., sleeves, collar, etc). When making cloth decisions, people usually show preferences for different semantic attributes (e.g., the clothes with v-neck collar). Nevertheless, most previous fashion recommendation models comprehend the clothing images with a global content representation and lack detailed understanding of users’ semantic preferences, which usually leads to inferior recommendation performance. To bridge this gap, we propose a novel Semantic Attribute Explainable Recommender System (SAERS). Specifically, we first introduce a fine-grained interpretable semantic space. We then develop a Semantic Extraction Network (SEN) and Fine-grained Preferences Attention (FPA) module to project users and items into this space, respectively. With SAERS, we are capable of not only providing cloth recommendations for users, but also explaining the reason why we recommend the cloth through intuitive visual attribute semantic highlights in a personalized manner. Extensive experiments conducted on real-world datasets clearly demonstrate the effectiveness of our approach compared with the state-of-the-art methods.
Tasks	Recommendation Systems
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12862v2
PDF	https://arxiv.org/pdf/1905.12862v2.pdf
PWC	https://paperswithcode.com/paper/explainable-fashion-recommendation-a-semantic
Repo
Framework

Motion correction of dynamic contrast enhanced MRI of the liver


Title	Motion correction of dynamic contrast enhanced MRI of the liver
Authors	Mariëlle J. A. Jansen, Wouter B. Veldhuis, Maarten S. van Leeuwen, Josien P. W. Pluim
Abstract	Motion correction of dynamic contrast enhanced magnetic resonance images (DCE-MRI) is a challenging task, due to changes in image appearance. In this study a groupwise registration, using a principle component analysis (PCA) based metric,1 is evaluated for clinical DCE MRI of the liver. The groupwise registration transforms the images to a common space, rather than to a reference volume as conventional pairwise methods do, and computes the similarity metric on all volumes simultaneously. This groupwise registration method is compared to a pairwise approach using a mutual information metric. Clinical DCE MRI of the abdomen of eight patients were included. Per patient one lesion in the liver was manually segmented in all temporal images (N=16). The registered images were compared for accuracy, spatial and temporal smoothness after transformation, and lesion volume change. Compared to a pairwise method or no registration, groupwise registration provided better alignment. In our recently started clinical study groupwise registered clinical DCE MRI of the abdomen of nine patients were scored by three radiologists. Groupwise registration increased the assessed quality of alignment. The gain in reading time for the radiologist was estimated to vary from no difference to almost a minute. A slight increase in reader confidence was also observed. Registration had no added value for images with little motion. In conclusion, the groupwise registration of DCE MR images results in better alignment than achieved by pairwise registration, which is beneficial for clinical assessment.
Tasks
Published	2019-08-22
URL	https://arxiv.org/abs/1908.08254v1
PDF	https://arxiv.org/pdf/1908.08254v1.pdf
PWC	https://paperswithcode.com/paper/motion-correction-of-dynamic-contrast
Repo
Framework

Synthetic Examples Improve Generalization for Rare Classes


Title	Synthetic Examples Improve Generalization for Rare Classes
Authors	Sara Beery, Yang Liu, Dan Morris, Jim Piavis, Ashish Kapoor, Markus Meister, Neel Joshi, Pietro Perona
Abstract	The ability to detect and classify rare occurrences in images has important applications - for example, counting rare and endangered species when studying biodiversity, or detecting infrequent traffic scenarios that pose a danger to self-driving cars. Few-shot learning is an open problem: current computer vision systems struggle to categorize objects they have seen only rarely during training, and collecting a sufficient number of training examples of rare events is often challenging and expensive, and sometimes outright impossible. We explore in depth an approach to this problem: complementing the few available training images with ad-hoc simulated data. Our testbed is animal species classification, which has a real-world long-tailed distribution. We analyze the effect of different axes of variation in simulation, such as pose, lighting, model, and simulation method, and we prescribe best practices for efficiently incorporating simulated data for real-world performance gain. Our experiments reveal that synthetic data can considerably reduce error rates for classes that are rare, that as the amount of simulated data is increased, accuracy on the target class improves, and that high variation of simulated data provides maximum performance gain.
Tasks	Few-Shot Learning, Self-Driving Cars
Published	2019-04-11
URL	https://arxiv.org/abs/1904.05916v2
PDF	https://arxiv.org/pdf/1904.05916v2.pdf
PWC	https://paperswithcode.com/paper/synthetic-examples-improve-generalization-for
Repo
Framework

Towards Self-Supervised High Level Sensor Fusion


Title	Towards Self-Supervised High Level Sensor Fusion
Authors	Qadeer Khan, Torsten Schön, Patrick Wenzel
Abstract	In this paper, we present a framework to control a self-driving car by fusing raw information from RGB images and depth maps. A deep neural network architecture is used for mapping the vision and depth information, respectively, to steering commands. This fusion of information from two sensor sources allows to provide redundancy and fault tolerance in the presence of sensor failures. Even if one of the input sensors fails to produce the correct output, the other functioning sensor would still be able to maneuver the car. Such redundancy is crucial in the critical application of self-driving cars. The experimental results have showed that our method is capable of learning to use the relevant sensor information even when one of the sensors fail without any explicit signal.
Tasks	Self-Driving Cars, Sensor Fusion
Published	2019-02-12
URL	http://arxiv.org/abs/1902.04272v1
PDF	http://arxiv.org/pdf/1902.04272v1.pdf
PWC	https://paperswithcode.com/paper/towards-self-supervised-high-level-sensor
Repo
Framework