January 28, 2020

3173 words 15 mins read

Paper Group ANR 791

On Physical Adversarial Patches for Object Detection. MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground Imagery. Author Profiling for Hate Speech Detection. DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections. Distributed Metropolis Sampler with Optimal Parallelism. Trouble on the Horizon: F …

On Physical Adversarial Patches for Object Detection


Title	On Physical Adversarial Patches for Object Detection
Authors	Mark Lee, Zico Kolter
Abstract	In this paper, we demonstrate a physical adversarial patch attack against object detectors, notably the YOLOv3 detector. Unlike previous work on physical object detection attacks, which required the patch to overlap with the objects being misclassified or avoiding detection, we show that a properly designed patch can suppress virtually all the detected objects in the image. That is, we can place the patch anywhere in the image, causing all existing objects in the image to be missed entirely by the detector, even those far away from the patch itself. This in turn opens up new lines of physical attacks against object detection systems, which require no modification of the objects in a scene. A demo of the system can be found at https://youtu.be/WXnQjbZ1e7Y.
Tasks	Object Detection
Published	2019-06-20
URL	https://arxiv.org/abs/1906.11897v1
PDF	https://arxiv.org/pdf/1906.11897v1.pdf
PWC	https://paperswithcode.com/paper/on-physical-adversarial-patches-for-object
Repo
Framework

MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground Imagery


Title	MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground Imagery
Authors	Reza Bahmanyar, Elenora Vig, Peter Reinartz
Abstract	In spite of the many advantages of aerial imagery for crowd monitoring and management at mass events, datasets of aerial images of crowds are still lacking in the field. As a remedy, in this work we introduce a novel crowd dataset, the DLR Aerial Crowd Dataset (DLR-ACD), which is composed of 33 large aerial images acquired from 16 flight campaigns over mass events with 226,291 persons annotated. To the best of our knowledge, DLR-ACD is the first aerial crowd dataset and will be released publicly. To tackle the problem of accurate crowd counting and density map estimation in aerial images of crowds, this work also proposes a new encoder-decoder convolutional neural network, the so-called Multi-Resolution Crowd Network MRCNet. The encoder is based on the VGG-16 network and the decoder is composed of a set of bilinear upsampling and convolutional layers. Using two losses, one at an earlier level and another at the last level of the decoder, MRCNet estimates crowd counts and high-resolution crowd density maps as two different but interrelated tasks. In addition, MRCNet utilizes contextual and detailed local information by combining high- and low-level features through a number of lateral connections inspired by the Feature Pyramid Network (FPN) technique. We evaluated MRCNet on the proposed DLR-ACD dataset as well as on the ShanghaiTech dataset, a CCTV-based crowd counting benchmark. The results demonstrate that MRCNet outperforms the state-of-the-art crowd counting methods in estimating the crowd counts and density maps for both aerial and CCTV-based images.
Tasks	Crowd Counting
Published	2019-09-27
URL	https://arxiv.org/abs/1909.12743v1
PDF	https://arxiv.org/pdf/1909.12743v1.pdf
PWC	https://paperswithcode.com/paper/mrcnet-crowd-counting-and-density-map
Repo
Framework

Author Profiling for Hate Speech Detection


Title	Author Profiling for Hate Speech Detection
Authors	Pushkar Mishra, Marco Del Tredici, Helen Yannakoudakis, Ekaterina Shutova
Abstract	The rapid growth of social media in recent years has fed into some highly undesirable phenomena such as proliferation of abusive and offensive language on the Internet. Previous research suggests that such hateful content tends to come from users who share a set of common stereotypes and form communities around them. The current state-of-the-art approaches to hate speech detection are oblivious to user and community information and rely entirely on textual (i.e., lexical and semantic) cues. In this paper, we propose a novel approach to this problem that incorporates community-based profiling features of Twitter users. Experimenting with a dataset of 16k tweets, we show that our methods significantly outperform the current state of the art in hate speech detection. Further, we conduct a qualitative analysis of model characteristics. We release our code, pre-trained models and all the resources used in the public domain.
Tasks	Hate Speech Detection
Published	2019-02-14
URL	http://arxiv.org/abs/1902.06734v1
PDF	http://arxiv.org/pdf/1902.06734v1.pdf
PWC	https://paperswithcode.com/paper/author-profiling-for-hate-speech-detection
Repo
Framework

DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections


Title	DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections
Authors	Ofir Nachum, Yinlam Chow, Bo Dai, Lihong Li
Abstract	In many real-world reinforcement learning applications, access to the environment is limited to a fixed dataset, instead of direct (online) interaction with the environment. When using this data for either evaluation or training of a new policy, accurate estimates of discounted stationary distribution ratios – correction terms which quantify the likelihood that the new policy will experience a certain state-action pair normalized by the probability with which the state-action pair appears in the dataset – can improve accuracy and performance. In this work, we propose an algorithm, DualDICE, for estimating these quantities. In contrast to previous approaches, our algorithm is agnostic to knowledge of the behavior policy (or policies) used to generate the dataset. Furthermore, it eschews any direct use of importance weights, thus avoiding potential optimization instabilities endemic of previous methods. In addition to providing theoretical guarantees, we present an empirical study of our algorithm applied to off-policy policy evaluation and find that our algorithm significantly improves accuracy compared to existing techniques.
Tasks
Published	2019-06-10
URL	https://arxiv.org/abs/1906.04733v2
PDF	https://arxiv.org/pdf/1906.04733v2.pdf
PWC	https://paperswithcode.com/paper/dualdice-behavior-agnostic-estimation-of
Repo
Framework

Distributed Metropolis Sampler with Optimal Parallelism


Title	Distributed Metropolis Sampler with Optimal Parallelism
Authors	Weiming Feng, Thomas P. Hayes, Yitong Yin
Abstract	The Metropolis-Hastings algorithm is a fundamental Markov chain Monte Carlo (MCMC) method for sampling and inference. With the advent of Big Data, distributed and parallel variants of MCMC methods are attracting increased attention. In this paper, we give a distributed algorithm that can correctly simulate sequential single-site Metropolis chains without any bias in a fully asynchronous message-passing model. Furthermore, if a natural Lipschitz condition is satisfied by the Metropolis filters, our algorithm can simulate $N$-step Metropolis chains within $O(N/n+\log n)$ rounds of asynchronous communications, where $n$ is the number of variables. For sequential single-site dynamics, whose mixing requires $\Omega(n\log n)$ steps, this achieves an optimal linear speedup. For several well-studied important graphical models, including proper graph coloring, hardcore model, and Ising model, our condition for linear speedup is weaker than the respective uniqueness (mixing) conditions. The novel idea in our algorithm is to resolve updates in advance: the local Metropolis filters can often be executed correctly before the full information about neighboring spins is available. This achieves optimal parallelism without introducing any bias.
Tasks
Published	2019-04-01
URL	https://arxiv.org/abs/1904.00943v2
PDF	https://arxiv.org/pdf/1904.00943v2.pdf
PWC	https://paperswithcode.com/paper/fully-asynchronous-distributed-metropolis
Repo
Framework

Trouble on the Horizon: Forecasting the Derailment of Online Conversations as they Develop


Title	Trouble on the Horizon: Forecasting the Derailment of Online Conversations as they Develop
Authors	Jonathan P. Chang, Cristian Danescu-Niculescu-Mizil
Abstract	Online discussions often derail into toxic exchanges between participants. Recent efforts mostly focused on detecting antisocial behavior after the fact, by analyzing single comments in isolation. To provide more timely notice to human moderators, a system needs to preemptively detect that a conversation is heading towards derailment before it actually turns toxic. This means modeling derailment as an emerging property of a conversation rather than as an isolated utterance-level event. Forecasting emerging conversational properties, however, poses several inherent modeling challenges. First, since conversations are dynamic, a forecasting model needs to capture the flow of the discussion, rather than properties of individual comments. Second, real conversations have an unknown horizon: they can end or derail at any time; thus a practical forecasting model needs to assess the risk in an online fashion, as the conversation develops. In this work we introduce a conversational forecasting model that learns an unsupervised representation of conversational dynamics and exploits it to predict future derailment as the conversation develops. By applying this model to two new diverse datasets of online conversations with labels for antisocial events, we show that it outperforms state-of-the-art systems at forecasting derailment.
Tasks
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01362v1
PDF	https://arxiv.org/pdf/1909.01362v1.pdf
PWC	https://paperswithcode.com/paper/trouble-on-the-horizon-forecasting-the
Repo
Framework

Denoising Gravitational Waves with Enhanced Deep Recurrent Denoising Auto-Encoders


Title	Denoising Gravitational Waves with Enhanced Deep Recurrent Denoising Auto-Encoders
Authors	Hongyu Shen, Daniel George, E. A. Huerta, Zhizhen Zhao
Abstract	Denoising of time domain data is a crucial task for many applications such as communication, translation, virtual assistants etc. For this task, a combination of a recurrent neural net (RNNs) with a Denoising Auto-Encoder (DAEs) has shown promising results. However, this combined model is challenged when operating with low signal-to-noise ratio (SNR) data embedded in non-Gaussian and non-stationary noise. To address this issue, we design a novel model, referred to as ‘Enhanced Deep Recurrent Denoising Auto-Encoder’ (EDRDAE), that incorporates a signal amplifier layer, and applies curriculum learning by first denoising high SNR signals, before gradually decreasing the SNR until the signals become noise dominated. We showcase the performance of EDRDAE using time-series data that describes gravitational waves embedded in very noisy backgrounds. In addition, we show that EDRDAE can accurately denoise signals whose topology is significantly more complex than those used for training, demonstrating that our model generalizes to new classes of gravitational waves that are beyond the scope of established denoising algorithms.
Tasks	Denoising, Time Series
Published	2019-03-06
URL	http://arxiv.org/abs/1903.03105v1
PDF	http://arxiv.org/pdf/1903.03105v1.pdf
PWC	https://paperswithcode.com/paper/denoising-gravitational-waves-with-enhanced
Repo
Framework

Shadowing Properties of Optimization Algorithms


Title	Shadowing Properties of Optimization Algorithms
Authors	Antonio Orvieto, Aurelien Lucchi
Abstract	Ordinary differential equation (ODE) models of gradient-based optimization methods can provide insights into the dynamics of learning and inspire the design of new algorithms. Unfortunately, this thought-provoking perspective is weakened by the fact that, in the worst case, the error between the algorithm steps and its ODE approximation grows exponentially with the number of iterations. In an attempt to encourage the use of continuous-time methods in optimization, we show that, if some additional regularity on the objective is assumed, the ODE representations of Gradient Descent and Heavy-ball do not suffer from the aforementioned problem, once we allow for a small perturbation on the algorithm initial condition. In the dynamical systems literature, this phenomenon is called shadowing. Our analysis relies on the concept of hyperbolicity, as well as on tools from numerical analysis.
Tasks
Published	2019-11-12
URL	https://arxiv.org/abs/1911.05206v1
PDF	https://arxiv.org/pdf/1911.05206v1.pdf
PWC	https://paperswithcode.com/paper/shadowing-properties-of-optimization-1
Repo
Framework

Adversarial Risk Bounds for Neural Networks through Sparsity based Compression


Title	Adversarial Risk Bounds for Neural Networks through Sparsity based Compression
Authors	Emilio Rafael Balda, Arash Behboodi, Niklas Koep, Rudolf Mathar
Abstract	Neural networks have been shown to be vulnerable against minor adversarial perturbations of their inputs, especially for high dimensional data under $\ell_\infty$ attacks. To combat this problem, techniques like adversarial training have been employed to obtain models which are robust on the training set. However, the robustness of such models against adversarial perturbations may not generalize to unseen data. To study how robustness generalizes, recent works assume that the inputs have bounded $\ell_2$-norm in order to bound the adversarial risk for $\ell_\infty$ attacks with no explicit dimension dependence. In this work we focus on $\ell_\infty$ attacks on $\ell_\infty$ bounded inputs and prove margin-based bounds. Specifically, we use a compression based approach that relies on efficiently compressing the set of tunable parameters without distorting the adversarial risk. To achieve this, we apply the concept of effective sparsity and effective joint sparsity on the weight matrices of neural networks. This leads to bounds with no explicit dependence on the input dimension, neither on the number of classes. Our results show that neural networks with approximately sparse weight matrices not only enjoy enhanced robustness, but also better generalization.
Tasks
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00698v1
PDF	https://arxiv.org/pdf/1906.00698v1.pdf
PWC	https://paperswithcode.com/paper/190600698
Repo
Framework

Real-Time Variational Fisheye Stereo without Rectification and Undistortion


Title	Real-Time Variational Fisheye Stereo without Rectification and Undistortion
Authors	Menandro Roxas, Takeshi Oishi
Abstract	Dense 3D maps from wide-angle cameras is beneficial to robotics applications such as navigation and autonomous driving. In this work, we propose a real-time dense 3D mapping method for fisheye cameras without explicit rectification and undistortion. We extend the conventional variational stereo method by constraining the correspondence search along the epipolar curve using a trajectory field induced by camera motion. We also propose a fast way of generating the trajectory field without increasing the processing time compared to conventional rectified methods. With our implementation, we were able to achieve real-time processing using modern GPUs. Our results show the advantages of our non-rectified dense mapping approach compared to rectified variational methods and non-rectified discrete stereo matching methods.
Tasks	Autonomous Driving, Stereo Matching, Stereo Matching Hand
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07545v1
PDF	https://arxiv.org/pdf/1909.07545v1.pdf
PWC	https://paperswithcode.com/paper/real-time-variational-fisheye-stereo-without
Repo
Framework

Sampler for Composition Ratio by Markov Chain Monte Carlo


Title	Sampler for Composition Ratio by Markov Chain Monte Carlo
Authors	Yachiko Obara, Tetsuro Morimura, Hiroki Yanagisawa
Abstract	Invention involves combination, or more precisely, ratios of composition. According to Thomas Edison, “Genius is one percent inspiration and 99 percent perspiration” is an example. In many situations, researchers and inventors already have a variety of data and manage to create something new by using it, but the key problem is how to select and combine knowledge. In this paper, we propose a new Markov chain Monte Carlo (MCMC) algorithm to generate composition ratios, nonnegative-integer-valued vectors with two properties: (i) the sum of the elements of each vector is constant, and (ii) only a small number of elements is nonzero. These constraints make it difficult for existing MCMC algorithms to sample composition ratios. The key points of our approach are (1) designing an appropriate target distribution by using a condition on the number of nonzero elements, and (2) changing values only between a certain pair of elements in each iteration. Through an experiment on creating a new cocktail, we show that the combination of the proposed method with supervised learning can solve a creative problem.
Tasks
Published	2019-06-16
URL	https://arxiv.org/abs/1906.06663v2
PDF	https://arxiv.org/pdf/1906.06663v2.pdf
PWC	https://paperswithcode.com/paper/sampler-for-composition-ratio-by-markov-chain
Repo
Framework

Online Active Learning of Reject Option Classifiers


Title	Online Active Learning of Reject Option Classifiers
Authors	Kulin Shah, Naresh Manwani
Abstract	Active learning is an important technique to reduce the number of labeled examples in supervised learning. Active learning for binary classification has been well addressed. However, active learning of reject option classifier is still an unsolved problem. In this paper, we propose novel algorithms for active learning of reject option classifiers. We develop an active learning algorithm using double ramp loss function. We provide mistake bounds for this algorithm. We also propose a new loss function called double sigmoid loss function for reject option and corresponding active learning algorithm. We provide extensive experimental results to show the effectiveness of the proposed algorithms. The proposed algorithms efficiently reduce the number of label examples required.
Tasks	Active Learning
Published	2019-06-14
URL	https://arxiv.org/abs/1906.06166v1
PDF	https://arxiv.org/pdf/1906.06166v1.pdf
PWC	https://paperswithcode.com/paper/online-active-learning-of-reject-option
Repo
Framework

Sequential Evaluation and Generation Framework for Combinatorial Recommender System


Title	Sequential Evaluation and Generation Framework for Combinatorial Recommender System
Authors	Fan Wang, Xiaomin Fang, Lihang Liu, Yaxue Chen, Jiucheng Tao, Zhiming Peng, Cihang Jin, Hao Tian
Abstract	In the combinatorial recommender systems, multiple items are fed to the user at one time in the result page, where the correlations among the items have impact on the user behavior. In this work, we model the combinatorial recommendation as the problem of generating a sequence(ordered list) of items from a candidate set, with the target of maximizing the expected overall utility(e.g. total clicks) of the sequence. Toward solving this problem, we propose the Evaluation-Generation framework. On the one hand of this framework, an evaluation model is trained to evaluate the expected overall utility, by fully considering the user, item information and the correlations among the co-exposed items. On the other hand, generation policies based on heuristic searching or reinforcement learning are devised to generate potential high-quality sequences, from which the evaluation model select one to expose. We propose effective model architectures and learning metrics under this framework. We also offer series of offline tests to thoroughly investigate the performance of the proposed framework, as supplements to the online experiments. Our results show obvious increase in performance compared with the previous solutions.
Tasks	Recommendation Systems
Published	2019-02-01
URL	https://arxiv.org/abs/1902.00245v3
PDF	https://arxiv.org/pdf/1902.00245v3.pdf
PWC	https://paperswithcode.com/paper/sequential-evaluation-and-generation
Repo
Framework

An uncertainty principle for neural coding: Conjugate representations of position and velocity are mapped onto firing rates and co-firing rates of neural spike trains


Title	An uncertainty principle for neural coding: Conjugate representations of position and velocity are mapped onto firing rates and co-firing rates of neural spike trains
Authors	Ryan Grgurich, Hugh T. Blair
Abstract	The hippocampal system contains neural populations that encode an animal’s position and velocity as it navigates through space. Here, we show that such populations can embed two codes within their spike trains: a firing rate code (R) conveyed by within-cell spike intervals, and a co-firing rate code (R’) conveyed by between-cell spike intervals. These two codes behave as conjugates of one another, obeying an analog of the uncertainty principle from physics: information conveyed in R comes at the expense of information in R’, and vice versa. An exception to this trade-off occurs when spike trains encode a pair of conjugate variables, such as position and velocity, which do not compete for capacity across R and R’. To illustrate this, we describe two biologically inspired methods for decoding R and R’, referred to as sigma and sigma-chi decoding, respectively. Simulations of head direction (HD) and grid cells show that if firing rates are tuned for position (but not velocity), then position is recovered by sigma decoding, whereas velocity is recovered by sigma-chi decoding. Conversely, simulations of oscillatory interference among theta-modulated “speed cells” show that if co-firing rates are tuned for position (but not velocity), then position is recovered by sigma-chi decoding, whereas velocity is recovered by sigma decoding. Between these two extremes, information about both variables can be distributed across both channels, and partially recovered by both decoders. These results suggest that neurons with different spatial and temporal tuning properties-such as speed versus grid cells-might not encode different information, but rather, distribute similar information about position and velocity in different ways across R and R’.
Tasks
Published	2019-12-23
URL	https://arxiv.org/abs/1912.11126v1
PDF	https://arxiv.org/pdf/1912.11126v1.pdf
PWC	https://paperswithcode.com/paper/an-uncertainty-principle-for-neural-coding
Repo
Framework

Linear Lower Bounds and Conditioning of Differentiable Games


Title	Linear Lower Bounds and Conditioning of Differentiable Games
Authors	Adam Ibrahim, Waïss Azizian, Gauthier Gidel, Ioannis Mitliagkas
Abstract	Recent successes of game-theoretic formulations in ML have caused a resurgence of research interest in differentiable games. Overwhelmingly, that research focuses on methods and upper bounds. In this work, we approach the question of fundamental iteration complexity by providing lower bounds to complement the linear (i.e. geometric) upper bounds observed in the literature on a wide class of problems. We cast saddle-point and min-max problems as 2-player games. We leverage tools from single-objective convex optimisation to propose new linear lower bounds for convex-concave games. Notably, we give a linear lower bound for $n$-player differentiable games, by using the spectral properties of the update operator. We then propose a new definition of the condition number arising from our lower bound analysis. Unlike past definitions, our condition number captures the fact that linear rates are possible in games, even in the absence of strong convex-concavity.
Tasks
Published	2019-06-17
URL	https://arxiv.org/abs/1906.07300v2
PDF	https://arxiv.org/pdf/1906.07300v2.pdf
PWC	https://paperswithcode.com/paper/lower-bounds-and-conditioning-of
Repo
Framework