October 18, 2019

3131 words 15 mins read

Paper Group ANR 559

Compositional GAN: Learning Image-Conditional Binary Composition. Surrogate Model Assisted Cooperative Coevolution for Large Scale Optimization. Importance of the Mathematical Foundations of Machine Learning Methods for Scientific and Engineering Applications. Rogue Signs: Deceiving Traffic Sign Recognition with Malicious Ads and Logos. Depth and n …

Compositional GAN: Learning Image-Conditional Binary Composition


Title	Compositional GAN: Learning Image-Conditional Binary Composition
Authors	Samaneh Azadi, Deepak Pathak, Sayna Ebrahimi, Trevor Darrell
Abstract	Generative Adversarial Networks (GANs) can produce images of remarkable complexity and realism but are generally structured to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could be present in a scene. Capturing such complex interactions between different objects in the world, including their relative scaling, spatial layout, occlusion, or viewpoint transformation is a challenging problem. In this work, we propose a novel self-consistent Composition-by-Decomposition (CoDe) network to compose a pair of objects. Given object images from two distinct distributions, our model can generate a realistic composite image from their joint distribution following the texture and shape of the input objects. We evaluate our approach through qualitative experiments and user evaluations. Our results indicate that the learned model captures potential interactions between the two object domains, and generates realistic composed scenes at test time.
Tasks
Published	2018-07-19
URL	http://arxiv.org/abs/1807.07560v3
PDF	http://arxiv.org/pdf/1807.07560v3.pdf
PWC	https://paperswithcode.com/paper/compositional-gan-learning-conditional-image
Repo
Framework

Surrogate Model Assisted Cooperative Coevolution for Large Scale Optimization


Title	Surrogate Model Assisted Cooperative Coevolution for Large Scale Optimization
Authors	Zhigang Ren, Bei Pang, Yongsheng Liang, An Chen, Yipeng Zhang
Abstract	It has been shown that cooperative coevolution (CC) can effectively deal with large scale optimization problems (LSOPs) through a divide-and-conquer strategy. However, its performance is severely restricted by the current context-vector-based sub-solution evaluation method since this method needs to access the original high dimensional simulation model when evaluating each sub-solution and thus requires many computation resources. To alleviate this issue, this study proposes a novel surrogate model assisted cooperative coevolution (SACC) framework. SACC constructs a surrogate model for each sub-problem obtained via decomposition and employs it to evaluate corresponding sub-solutions. The original simulation model is only adopted to reevaluate some good sub-solutions selected by surrogate models, and these real evaluated sub-solutions will be in turn employed to update surrogate models. By this means, the computation cost could be greatly reduced without significantly sacrificing evaluation quality. To show the efficiency of SACC, this study uses radial basis function (RBF) and success-history based adaptive differential evolution (SHADE) as surrogate model and optimizer, respectively. RBF and SHADE have been proved to be effective on small and medium scale problems. This study first scales them up to LSOPs of 1000 dimensions under the SACC framework, where they are tailored to a certain extent for adapting to the characteristics of LSOP and SACC. Empirical studies on IEEE CEC 2010 benchmark functions demonstrate that SACC significantly enhances the evaluation efficiency on sub-solutions, and even with much fewer computation resource, the resultant RBF-SHADE-SACC algorithm is able to find much better solutions than traditional CC algorithms.
Tasks
Published	2018-02-27
URL	http://arxiv.org/abs/1802.09746v1
PDF	http://arxiv.org/pdf/1802.09746v1.pdf
PWC	https://paperswithcode.com/paper/surrogate-model-assisted-cooperative
Repo
Framework

Importance of the Mathematical Foundations of Machine Learning Methods for Scientific and Engineering Applications


Title	Importance of the Mathematical Foundations of Machine Learning Methods for Scientific and Engineering Applications
Authors	Paul J. Atzberger
Abstract	There has been a lot of recent interest in adopting machine learning methods for scientific and engineering applications. This has in large part been inspired by recent successes and advances in the domains of Natural Language Processing (NLP) and Image Classification (IC). However, scientific and engineering problems have their own unique characteristics and requirements raising new challenges for effective design and deployment of machine learning approaches. There is a strong need for further mathematical developments on the foundations of machine learning methods to increase the level of rigor of employed methods and to ensure more reliable and interpretable results. Also as reported in the recent literature on state-of-the-art results and indicated by the No Free Lunch Theorems of statistical learning theory incorporating some form of inductive bias and domain knowledge is essential to success. Consequently, even for existing and widely used methods there is a strong need for further mathematical work to facilitate ways to incorporate prior scientific knowledge and related inductive biases into learning frameworks and algorithms. We briefly discuss these topics and discuss some ideas proceeding in this direction.
Tasks	Image Classification
Published	2018-08-07
URL	http://arxiv.org/abs/1808.02213v1
PDF	http://arxiv.org/pdf/1808.02213v1.pdf
PWC	https://paperswithcode.com/paper/importance-of-the-mathematical-foundations-of
Repo
Framework

Rogue Signs: Deceiving Traffic Sign Recognition with Malicious Ads and Logos


Title	Rogue Signs: Deceiving Traffic Sign Recognition with Malicious Ads and Logos
Authors	Chawin Sitawarin, Arjun Nitin Bhagoji, Arsalan Mosenia, Prateek Mittal, Mung Chiang
Abstract	We propose a new real-world attack against the computer vision based systems of autonomous vehicles (AVs). Our novel Sign Embedding attack exploits the concept of adversarial examples to modify innocuous signs and advertisements in the environment such that they are classified as the adversary’s desired traffic sign with high confidence. Our attack greatly expands the scope of the threat posed to AVs since adversaries are no longer restricted to just modifying existing traffic signs as in previous work. Our attack pipeline generates adversarial samples which are robust to the environmental conditions and noisy image transformations present in the physical world. We ensure this by including a variety of possible image transformations in the optimization problem used to generate adversarial samples. We verify the robustness of the adversarial samples by printing them out and carrying out drive-by tests simulating the conditions under which image capture would occur in a real-world scenario. We experimented with physical attack samples for different distances, lighting conditions and camera angles. In addition, extensive evaluations were carried out in the virtual setting for a variety of image transformations. The adversarial samples generated using our method have adversarial success rates in excess of 95% in the physical as well as virtual settings.
Tasks	Autonomous Vehicles, Traffic Sign Recognition
Published	2018-01-09
URL	http://arxiv.org/abs/1801.02780v3
PDF	http://arxiv.org/pdf/1801.02780v3.pdf
PWC	https://paperswithcode.com/paper/rogue-signs-deceiving-traffic-sign
Repo
Framework

Depth and nonlinearity induce implicit exploration for RL


Title	Depth and nonlinearity induce implicit exploration for RL
Authors	Justas Dauparas, Ryota Tomioka, Katja Hofmann
Abstract	The question of how to explore, i.e., take actions with uncertain outcomes to learn about possible future rewards, is a key question in reinforcement learning (RL). Here, we show a surprising result: We show that Q-learning with nonlinear Q-function and no explicit exploration (i.e., a purely greedy policy) can learn several standard benchmark tasks, including mountain car, equally well as, or better than, the most commonly-used $\epsilon$-greedy exploration. We carefully examine this result and show that both the depth of the Q-network and the type of nonlinearity are important to induce such deterministic exploration.
Tasks	Q-Learning
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11711v1
PDF	http://arxiv.org/pdf/1805.11711v1.pdf
PWC	https://paperswithcode.com/paper/depth-and-nonlinearity-induce-implicit
Repo
Framework

Bayesian inference for bivariate ranks


Title	Bayesian inference for bivariate ranks
Authors	Simon Guillotte, François Perron, Johan Segers
Abstract	A recommender system based on ranks is proposed, where an expert’s ranking of a set of objects and a user’s ranking of a subset of those objects are combined to make a prediction of the user’s ranking of all objects. The rankings are assumed to be induced by latent continuous variables corresponding to the grades assigned by the expert and the user to the objects. The dependence between the expert and user grades is modelled by a copula in some parametric family. Given a prior distribution on the copula parameter, the user’s complete ranking is predicted by the mode of the posterior predictive distribution of the user’s complete ranking conditional on the expert’s complete and the user’s incomplete rankings. Various Markov chain Monte-Carlo algorithms are proposed to approximate the predictive distribution or only its mode. The predictive distribution can be obtained exactly for the Farlie-Gumbel-Morgenstern copula family, providing a benchmark for the approximation accuracy of the algorithms. The method is applied to the MovieLens 100k dataset with a Gaussian copula modelling dependence between the expert’s and user’s grades.
Tasks	Bayesian Inference, Recommendation Systems
Published	2018-02-09
URL	http://arxiv.org/abs/1802.03300v1
PDF	http://arxiv.org/pdf/1802.03300v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-inference-for-bivariate-ranks
Repo
Framework

PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach


Title	PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach
Authors	Tsui-Wei Weng, Pin-Yu Chen, Lam M. Nguyen, Mark S. Squillante, Ivan Oseledets, Luca Daniel
Abstract	With deep neural networks providing state-of-the-art machine learning models for numerous machine learning tasks, quantifying the robustness of these models has become an important area of research. However, most of the research literature merely focuses on the \textit{worst-case} setting where the input of the neural network is perturbed with noises that are constrained within an $\ell_p$ ball; and several algorithms have been proposed to compute certified lower bounds of minimum adversarial distortion based on such worst-case analysis. In this paper, we address these limitations and extend the approach to a \textit{probabilistic} setting where the additive noises can follow a given distributional characterization. We propose a novel probabilistic framework PROVEN to PRObabilistically VErify Neural networks with statistical guarantees – i.e., PROVEN certifies the probability that the classifier’s top-1 prediction cannot be altered under any constrained $\ell_p$ norm perturbation to a given input. Importantly, we show that it is possible to derive closed-form probabilistic certificates based on current state-of-the-art neural network robustness verification frameworks. Hence, the probabilistic certificates provided by PROVEN come naturally and with almost no overhead when obtaining the worst-case certified lower bounds from existing methods such as Fast-Lin, CROWN and CNN-Cert. Experiments on small and large MNIST and CIFAR neural network models demonstrate our probabilistic approach can achieve up to around $75%$ improvement in the robustness certification with at least a $99.99%$ confidence compared with the worst-case robustness certificate delivered by CROWN.
Tasks
Published	2018-12-18
URL	http://arxiv.org/abs/1812.08329v2
PDF	http://arxiv.org/pdf/1812.08329v2.pdf
PWC	https://paperswithcode.com/paper/proven-certifying-robustness-of-neural
Repo
Framework

Domain Adaptation for MRI Organ Segmentation using Reverse Classification Accuracy


Title	Domain Adaptation for MRI Organ Segmentation using Reverse Classification Accuracy
Authors	Vanya V. Valindria, Ioannis Lavdas, Wenjia Bai, Konstantinos Kamnitsas, Eric O. Aboagye, Andrea G. Rockall, Daniel Rueckert, Ben Glocker
Abstract	The variations in multi-center data in medical imaging studies have brought the necessity of domain adaptation. Despite the advancement of machine learning in automatic segmentation, performance often degrades when algorithms are applied on new data acquired from different scanners or sequences than the training data. Manual annotation is costly and time consuming if it has to be carried out for every new target domain. In this work, we investigate automatic selection of suitable subjects to be annotated for supervised domain adaptation using the concept of reverse classification accuracy (RCA). RCA predicts the performance of a trained model on data from the new domain and different strategies of selecting subjects to be included in the adaptation via transfer learning are evaluated. We perform experiments on a two-center MR database for the task of organ segmentation. We show that subject selection via RCA can reduce the burden of annotation of new data for the target domain.
Tasks	Domain Adaptation, Transfer Learning
Published	2018-06-01
URL	http://arxiv.org/abs/1806.00363v1
PDF	http://arxiv.org/pdf/1806.00363v1.pdf
PWC	https://paperswithcode.com/paper/domain-adaptation-for-mri-organ-segmentation
Repo
Framework

Diffusion Maps meet Nyström


Title	Diffusion Maps meet Nyström
Authors	N. Benjamin Erichson, Lionel Mathelin, Steven L. Brunton, J. Nathan Kutz
Abstract	Diffusion maps are an emerging data-driven technique for non-linear dimensionality reduction, which are especially useful for the analysis of coherent structures and nonlinear embeddings of dynamical systems. However, the computational complexity of the diffusion maps algorithm scales with the number of observations. Thus, long time-series data presents a significant challenge for fast and efficient embedding. We propose integrating the Nystr"om method with diffusion maps in order to ease the computational demand. We achieve a speedup of roughly two to four times when approximating the dominant diffusion map components.
Tasks	Dimensionality Reduction, Time Series
Published	2018-02-23
URL	http://arxiv.org/abs/1802.08762v1
PDF	http://arxiv.org/pdf/1802.08762v1.pdf
PWC	https://paperswithcode.com/paper/diffusion-maps-meet-nystrom
Repo
Framework

Adversarial Learning for Image Forensics Deep Matching with Atrous Convolution


Title	Adversarial Learning for Image Forensics Deep Matching with Atrous Convolution
Authors	Yaqi Liu, Xianfeng Zhao, Xiaobin Zhu, Yun Cao
Abstract	Constrained image splicing detection and localization (CISDL) is a newly proposed challenging task for image forensics, which investigates two input suspected images and identifies whether one image has suspected regions pasted from the other. In this paper, we propose a novel adversarial learning framework to train the deep matching network for CISDL. Our framework mainly consists of three building blocks: 1) the deep matching network based on atrous convolution (DMAC) aims to generate two high-quality candidate masks which indicate the suspected regions of the two input images, 2) the detection network is designed to rectify inconsistencies between the two corresponding candidate masks, 3) the discriminative network drives the DMAC network to produce masks that are hard to distinguish from ground-truth ones. In DMAC, atrous convolution is adopted to extract features with rich spatial information, the correlation layer based on the skip architecture is proposed to capture hierarchical features, and atrous spatial pyramid pooling is constructed to localize tampered regions at multiple scales. The detection network and the discriminative network act as the losses with auxiliary parameters to supervise the training of DMAC in an adversarial way. Extensive experiments, conducted on 21 generated testing sets and two public datasets, demonstrate the effectiveness of the proposed framework and the superior performance of DMAC.
Tasks
Published	2018-09-08
URL	http://arxiv.org/abs/1809.02791v1
PDF	http://arxiv.org/pdf/1809.02791v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-learning-for-image-forensics-deep
Repo
Framework

Generalized Score Matching for Non-Negative Data


Title	Generalized Score Matching for Non-Negative Data
Authors	Shiqing Yu, Mathias Drton, Ali Shojaie
Abstract	A common challenge in estimating parameters of probability density functions is the intractability of the normalizing constant. While in such cases maximum likelihood estimation may be implemented using numerical integration, the approach becomes computationally intensive. The score matching method of Hyv"arinen [2005] avoids direct calculation of the normalizing constant and yields closed-form estimates for exponential families of continuous distributions over $\mathbb{R}^m$. Hyv"arinen [2007] extended the approach to distributions supported on the non-negative orthant, $\mathbb{R}_+^m$. In this paper, we give a generalized form of score matching for non-negative data that improves estimation efficiency. As an example, we consider a general class of pairwise interaction models. Addressing an overlooked inexistence problem, we generalize the regularized score matching method of Lin et al. [2016] and improve its theoretical guarantees for non-negative Gaussian graphical models.
Tasks
Published	2018-12-26
URL	https://arxiv.org/abs/1812.10551v2
PDF	https://arxiv.org/pdf/1812.10551v2.pdf
PWC	https://paperswithcode.com/paper/generalized-score-matching-for-non-negative
Repo
Framework


Title	Cookie Synchronization: Everything You Always Wanted to Know But Were Afraid to Ask
Authors	Panagiotis Papadopoulos, Nicolas Kourtellis, Evangelos P. Markatos
Abstract	User data is the primary input of digital advertising, fueling the free Internet as we know it. As a result, web companies invest a lot in elaborate tracking mechanisms to acquire user data that can sell to data markets and advertisers. However, with same-origin policy, and cookies as a primary identification mechanism on the web, each tracker knows the same user with a different ID. To mitigate this, Cookie Synchronization (CSync) came to the rescue, facilitating an information sharing channel between third parties that may or not have direct access to the website the user visits. In the background, with CSync, they merge user data they own, but also reconstruct a user’s browsing history, bypassing the same origin policy. In this paper, we perform a first to our knowledge in-depth study of CSync in the wild, using a year-long weblog from 850 real mobile users. Through our study, we aim to understand the characteristics of the CSync protocol and the impact it has on web users’ privacy. For this, we design and implement CONRAD, a holistic mechanism to detect CSync events at real time, and the privacy loss on the user side, even when the synced IDs are obfuscated. Using CONRAD, we find that 97% of the regular web users are exposed to CSync: most of them within the first week of their browsing, and the median userID gets leaked, on average, to 3.5 different domains. Finally, we see that CSync increases the number of domains that track the user by a factor of 6.75.
Tasks
Published	2018-05-26
URL	https://arxiv.org/abs/1805.10505v3
PDF	https://arxiv.org/pdf/1805.10505v3.pdf
PWC	https://paperswithcode.com/paper/cookie-synchronization-everything-you-always
Repo
Framework

Toward Efficient Breast Cancer Diagnosis and Survival Prediction Using L-Perceptron


Title	Toward Efficient Breast Cancer Diagnosis and Survival Prediction Using L-Perceptron
Authors	Hadi Mansourifar, Weidong Shi
Abstract	Breast cancer is the most frequently reported cancer type among the women around the globe and beyond that it has the second highest female fatality rate among all cancer types. Despite all the progresses made in prevention and early intervention, early prognosis and survival prediction rates are still unsatisfactory. In this paper, we propose a novel type of perceptron called L-Perceptron which outperforms all the previous supervised learning methods by reaching 97.42 % and 98.73 % in terms of accuracy and sensitivity, respectively in Wisconsin Breast Cancer dataset. Experimental results on Haberman’s Breast Cancer Survival dataset, show the superiority of proposed method by reaching 75.18 % and 83.86 % in terms of accuracy and F1 score, respectively. The results are the best reported ones obtained in 10-fold cross validation in absence of any preprocessing or feature selection.
Tasks	Feature Selection
Published	2018-11-05
URL	http://arxiv.org/abs/1811.03016v1
PDF	http://arxiv.org/pdf/1811.03016v1.pdf
PWC	https://paperswithcode.com/paper/toward-efficient-breast-cancer-diagnosis-and
Repo
Framework

Improving Model-Based Control and Active Exploration with Reconstruction Uncertainty Optimization


Title	Improving Model-Based Control and Active Exploration with Reconstruction Uncertainty Optimization
Authors	Norman Di Palo, Harri Valpola
Abstract	Model based predictions of future trajectories of a dynamical system often suffer from inaccuracies, forcing model based control algorithms to re-plan often, thus being computationally expensive, suboptimal and not reliable. In this work, we propose a model agnostic method for estimating the uncertainty of a model?s predictions based on reconstruction error, using it in control and exploration. As our experiments show, this uncertainty estimation can be used to improve control performance on a wide variety of environments by choosing predictions of which the model is confident. It can also be used for active learning to explore more efficiently the environment by planning for trajectories with high uncertainty, allowing faster model learning.
Tasks	Active Learning
Published	2018-12-10
URL	http://arxiv.org/abs/1812.03955v1
PDF	http://arxiv.org/pdf/1812.03955v1.pdf
PWC	https://paperswithcode.com/paper/improving-model-based-control-and-active
Repo
Framework

Web-STAR: A Visual Web-Based IDE for a Story Comprehension System


Title	Web-STAR: A Visual Web-Based IDE for a Story Comprehension System
Authors	Christos Rodosthenous, Loizos Michael
Abstract	We present Web-STAR, an online platform for story understanding built on top of the STAR reasoning engine for STory comprehension through ARgumentation. The platform includes a web-based IDE, integration with the STAR system, and a web service infrastructure to support integration with other systems that rely on story understanding functionality to complete their tasks. The platform also delivers a number of “social” features, including a community repository for public story sharing with a built-in commenting system, and tools for collaborative story editing that can be used for team development projects and for educational purposes.
Tasks
Published	2018-07-28
URL	http://arxiv.org/abs/1808.00048v1
PDF	http://arxiv.org/pdf/1808.00048v1.pdf
PWC	https://paperswithcode.com/paper/web-star-a-visual-web-based-ide-for-a-story
Repo
Framework