April 2, 2020

2923 words 14 mins read

Paper Group ANR 224

Normalizing Flows on Tori and Spheres. Provably Efficient Adaptive Approximate Policy Iteration. How Much Position Information Do Convolutional Neural Networks Encode?. Prior-enlightened and Motion-robust Video Deblurring. Gender Genetic Algorithm in the Dynamic Optimization Problem. Computer-inspired Quantum Experiments. Real-World Human-Robot Col …

Normalizing Flows on Tori and Spheres


Title	Normalizing Flows on Tori and Spheres
Authors	Danilo Jimenez Rezende, George Papamakarios, Sébastien Racanière, Michael S. Albergo, Gurtej Kanwar, Phiala E. Shanahan, Kyle Cranmer
Abstract	Normalizing flows are a powerful tool for building expressive distributions in high dimensions. So far, most of the literature has concentrated on learning flows on Euclidean spaces. Some problems however, such as those involving angles, are defined on spaces with more complex geometries, such as tori or spheres. In this paper, we propose and compare expressive and numerically stable flows on such spaces. Our flows are built recursively on the dimension of the space, starting from flows on circles, closed intervals or spheres.
Tasks
Published	2020-02-06
URL	https://arxiv.org/abs/2002.02428v1
PDF	https://arxiv.org/pdf/2002.02428v1.pdf
PWC	https://paperswithcode.com/paper/normalizing-flows-on-tori-and-spheres
Repo
Framework

Provably Efficient Adaptive Approximate Policy Iteration


Title	Provably Efficient Adaptive Approximate Policy Iteration
Authors	Botao Hao, Nevena Lazic, Yasin Abbasi-Yadkori, Pooria Joulani, Csaba Szepesvari
Abstract	Model-free reinforcement learning algorithms combined with value function approximation have recently achieved impressive performance in a variety of application domains, including games and robotics. However, the theoretical understanding of such algorithms is limited, and existing results are largely focused on episodic or discounted Markov decision processes (MDPs). In this work, we present adaptive approximate policy iteration (AAPI), a learning scheme which enjoys a O(T^{2/3}) regret bound for undiscounted, continuing learning in uniformly ergodic MDPs. This is an improvement over the best existing bound of O(T^{3/4}) for the average-reward case with function approximation. Our algorithm and analysis rely on adversarial online learning techniques, where value functions are treated as losses. The main technical novelty is the use of a data-dependent adaptive learning rate coupled with a so-called optimistic prediction of upcoming losses. In addition to theoretical guarantees, we demonstrate the advantages of our approach empirically on several environments.
Tasks
Published	2020-02-08
URL	https://arxiv.org/abs/2002.03069v3
PDF	https://arxiv.org/pdf/2002.03069v3.pdf
PWC	https://paperswithcode.com/paper/provably-efficient-adaptive-approximate
Repo
Framework

How Much Position Information Do Convolutional Neural Networks Encode?


Title	How Much Position Information Do Convolutional Neural Networks Encode?
Authors	Md Amirul Islam, Sen Jia, Neil D. B. Bruce
Abstract	In contrast to fully connected networks, Convolutional Neural Networks (CNNs) achieve efficiency by learning weights associated with local filters with a finite spatial extent. An implication of this is that a filter may know what it is looking at, but not where it is positioned in the image. Information concerning absolute position is inherently useful, and it is reasonable to assume that deep CNNs may implicitly learn to encode this information if there is a means to do so. In this paper, we test this hypothesis revealing the surprising degree of absolute position information that is encoded in commonly used neural networks. A comprehensive set of experiments show the validity of this hypothesis and shed light on how and where this information is represented while offering clues to where positional information is derived from in deep CNNs.
Tasks
Published	2020-01-22
URL	https://arxiv.org/abs/2001.08248v1
PDF	https://arxiv.org/pdf/2001.08248v1.pdf
PWC	https://paperswithcode.com/paper/how-much-position-information-do-1
Repo
Framework

Prior-enlightened and Motion-robust Video Deblurring


Title	Prior-enlightened and Motion-robust Video Deblurring
Authors	Ya Zhou, Jianfeng Xu, Kazuyuki Tasaka, Zhibo Chen, Weiping Li
Abstract	Various blur distortions in video will cause negative impact on both human viewing and video-based applications, which makes motion-robust deblurring methods urgently needed. Most existing works have strong dataset dependency and limited generalization ability in handling challenging scenarios, like blur in low contrast or severe motion areas, and non-uniform blur. Therefore, we propose a PRiOr-enlightened and MOTION-robust video deblurring model (PROMOTION) suitable for challenging blurs. On the one hand, we use 3D group convolution to efficiently encode heterogeneous prior information, explicitly enhancing the scenes’ perception while mitigating the output’s artifacts. On the other hand, we design the priors representing blur distribution, to better handle non-uniform blur in spatio-temporal domain. Besides the classical camera shake caused global blurry, we also prove the generalization for the downstream task suffering from local blur. Extensive experiments demonstrate we can achieve the state-of-the-art performance on well-known REDS and GoPro datasets, and bring machine task gain.
Tasks	Deblurring
Published	2020-03-25
URL	https://arxiv.org/abs/2003.11209v2
PDF	https://arxiv.org/pdf/2003.11209v2.pdf
PWC	https://paperswithcode.com/paper/prior-enlightened-and-motion-robust-video
Repo
Framework

Gender Genetic Algorithm in the Dynamic Optimization Problem


Title	Gender Genetic Algorithm in the Dynamic Optimization Problem
Authors	P. A. Golovinski, S. A. Kolodyazhnyi
Abstract	A general approach to optimizing fast processes using a gender genetic algorithm is described. Its difference from the more traditional genetic algorithm it contains division the artificial population into two sexes. Male subpopulations undergo large mutations and more strong selection compared to female individuals from another subset. This separation allows combining the rapid adaptability of the entire population to changes due to the variation of the male subpopulation with fixation of adaptability in the female part. The advantage of the effect of additional individual learning in the form of Boldwin effect in finding optimal solutions is observed in comparison with the usual gender genetic algorithm. As a promising application of the gender genetic algorithm with the Boldwin effect, the dynamics of extinguishing natural fires is pointed.
Tasks
Published	2020-02-14
URL	https://arxiv.org/abs/2002.05882v1
PDF	https://arxiv.org/pdf/2002.05882v1.pdf
PWC	https://paperswithcode.com/paper/gender-genetic-algorithm-in-the-dynamic
Repo
Framework

Computer-inspired Quantum Experiments


Title	Computer-inspired Quantum Experiments
Authors	Mario Krenn, Manuel Erhard, Anton Zeilinger
Abstract	The design of new devices and experiments in science and engineering has historically relied on the intuitions of human experts. This credo, however, has changed. In many disciplines, computer-inspired design processes, also known as inverse-design, have augmented the capability of scientists. Here we visit different fields of physics in which computer-inspired designs are applied. We will meet vastly diverse computational approaches based on topological optimization, evolutionary strategies, deep learning, reinforcement learning or automated reasoning. Then we draw our attention specifically on quantum physics. In the quest for designing new quantum experiments, we face two challenges: First, quantum phenomena are unintuitive. Second, the number of possible configurations of quantum experiments explodes combinatorially. To overcome these challenges, physicists began to use algorithms for computer-designed quantum experiments. We focus on the most mature and \textit{practical} approaches that scientists used to find new complex quantum experiments, which experimentalists subsequently have realized in the laboratories. The underlying idea is a highly-efficient topological search, which allows for scientific interpretability. In that way, some of the computer-designs have led to the discovery of new scientific concepts and ideas – demonstrating how computer algorithm can genuinely contribute to science by providing unexpected inspirations. We discuss several extensions and alternatives based on optimization and machine learning techniques, with the potential of accelerating the discovery of practical computer-inspired experiments or concepts in the future. Finally, we discuss what we can learn from the different approaches in the fields of physics, and raise several fascinating possibilities for future research.
Tasks
Published	2020-02-23
URL	https://arxiv.org/abs/2002.09970v1
PDF	https://arxiv.org/pdf/2002.09970v1.pdf
PWC	https://paperswithcode.com/paper/computer-inspired-quantum-experiments
Repo
Framework

Real-World Human-Robot Collaborative Reinforcement Learning


Title	Real-World Human-Robot Collaborative Reinforcement Learning
Authors	Ali Shafti, Jonas Tjomsland, William Dudley, A. Aldo Faisal
Abstract	The intuitive collaboration of humans and intelligent robots (embodied AI) in the real-world is an essential objective for many desirable applications of robotics. Whilst there is much research regarding explicit communication, we focus on how humans and robots interact implicitly, on motor adaptation level. We present a real-world setup of a human-robot collaborative maze game, designed to be non-trivial and only solvable through collaboration, by limiting the actions to rotations of two orthogonal axes, and assigning each axes to one player. This results in neither the human nor the agent being able to solve the game on their own. We use a state-of-the-art reinforcement learning algorithm for the robotic agent, and achieve results within 30 minutes of real-world play, without any type of pre-training. We then use this system to perform systematic experiments on human/agent behaviour and adaptation when co-learning a policy for the collaborative game. We present results on how co-policy learning occurs over time between the human and the robotic agent resulting in each participant’s agent serving as a representation of how they would play the game. This allows us to relate a person’s success when playing with different agents than their own, by comparing the policy of the agent with that of their own agent.
Tasks
Published	2020-03-02
URL	https://arxiv.org/abs/2003.01156v1
PDF	https://arxiv.org/pdf/2003.01156v1.pdf
PWC	https://paperswithcode.com/paper/real-world-human-robot-collaborative
Repo
Framework

Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild


Title	Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild
Authors	Umar Iqbal, Pavlo Molchanov, Jan Kautz
Abstract	One major challenge for monocular 3D human pose estimation in-the-wild is the acquisition of training data that contains unconstrained images annotated with accurate 3D poses. In this paper, we address this challenge by proposing a weakly-supervised approach that does not require 3D annotations and learns to estimate 3D poses from unlabeled multi-view data, which can be acquired easily in in-the-wild environments. We propose a novel end-to-end learning framework that enables weakly-supervised training using multi-view consistency. Since multi-view consistency is prone to degenerated solutions, we adopt a 2.5D pose representation and propose a novel objective function that can only be minimized when the predictions of the trained model are consistent and plausible across all camera views. We evaluate our proposed approach on two large scale datasets (Human3.6M and MPII-INF-3DHP) where it achieves state-of-the-art performance among semi-/weakly-supervised methods.
Tasks	3D Human Pose Estimation, Pose Estimation
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07581v1
PDF	https://arxiv.org/pdf/2003.07581v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-3d-human-pose-learning-via
Repo
Framework

BP-DIP: A Backprojection based Deep Image Prior


Title	BP-DIP: A Backprojection based Deep Image Prior
Authors	Jenny Zukerman, Tom Tirer, Raja Giryes
Abstract	Deep neural networks are a very powerful tool for many computer vision tasks, including image restoration, exhibiting state-of-the-art results. However, the performance of deep learning methods tends to drop once the observation model used in training mismatches the one in test time. In addition, most deep learning methods require vast amounts of training data, which are not accessible in many applications. To mitigate these disadvantages, we propose to combine two image restoration approaches: (i) Deep Image Prior (DIP), which trains a convolutional neural network (CNN) from scratch in test time using the given degraded image. It does not require any training data and builds on the implicit prior imposed by the CNN architecture; and (ii) a backprojection (BP) fidelity term, which is an alternative to the standard least squares loss that is usually used in previous DIP works. We demonstrate the performance of the proposed method, termed BP-DIP, on the deblurring task and show its advantages over the plain DIP, with both higher PSNR values and better inference run-time.
Tasks	Deblurring, Image Restoration
Published	2020-03-11
URL	https://arxiv.org/abs/2003.05417v1
PDF	https://arxiv.org/pdf/2003.05417v1.pdf
PWC	https://paperswithcode.com/paper/bp-dip-a-backprojection-based-deep-image
Repo
Framework

Defending Adversarial Attacks via Semantic Feature Manipulation


Title	Defending Adversarial Attacks via Semantic Feature Manipulation
Authors	Shuo Wang, Tianle Chen, Surya Nepal, Carsten Rudolph, Marthie Grobler, Shangyu Chen
Abstract	Machine learning models have demonstrated vulnerability to adversarial attacks, more specifically misclassification of adversarial examples. In this paper, we propose a one-off and attack-agnostic Feature Manipulation (FM)-Defense to detect and purify adversarial examples in an interpretable and efficient manner. The intuition is that the classification result of a normal image is generally resistant to non-significant intrinsic feature changes, e.g., varying thickness of handwritten digits. In contrast, adversarial examples are sensitive to such changes since the perturbation lacks transferability. To enable manipulation of features, a combo-variational autoencoder is applied to learn disentangled latent codes that reveal semantic features. The resistance to classification change over the morphs, derived by varying and reconstructing latent codes, is used to detect suspicious inputs. Further, combo-VAE is enhanced to purify the adversarial examples with good quality by considering both class-shared and class-unique features. We empirically demonstrate the effectiveness of detection and the quality of purified instance. Our experiments on three datasets show that FM-Defense can detect nearly $100%$ of adversarial examples produced by different state-of-the-art adversarial attacks. It achieves more than $99%$ overall purification accuracy on the suspicious instances that close the manifold of normal examples.
Tasks
Published	2020-02-03
URL	https://arxiv.org/abs/2002.02007v1
PDF	https://arxiv.org/pdf/2002.02007v1.pdf
PWC	https://paperswithcode.com/paper/defending-adversarial-attacks-via-semantic
Repo
Framework

Maximum Entropy on the Mean: A Paradigm Shift for Regularization in Image Deblurring


Title	Maximum Entropy on the Mean: A Paradigm Shift for Regularization in Image Deblurring
Authors	Gabriel Rioux, Rustum Choksi, Tim Hoheisel, Christopher Scarvelis
Abstract	Image deblurring is a notoriously challenging ill-posed inverse problem. In recent years, a wide variety of approaches have been proposed based upon regularization at the level of the image or on techniques from machine learning. We propose an alternative approach, shifting the paradigm towards regularization at the level of the probability distribution on the space of images. Our method is based upon the idea of maximum entropy on the mean wherein we work at the level of the probability density function of the image whose expectation is our estimate of the ground truth. Using techniques from convex analysis and probability theory, we show that the method is computationally feasible and amenable to very large blurs. Moreover, when images are imbedded with symbology (a known pattern), we show how our method can be applied to approximate the unknown blur kernel with remarkable effects. While our method is stable with respect to small amounts of noise, it does not actively denoise. However, for moderate to large amounts of noise, it performs well by preconditioned denoising with a state of the art method.
Tasks	Deblurring, Denoising
Published	2020-02-24
URL	https://arxiv.org/abs/2002.10434v1
PDF	https://arxiv.org/pdf/2002.10434v1.pdf
PWC	https://paperswithcode.com/paper/maximum-entropy-on-the-mean-a-paradigm-shift
Repo
Framework

Beyond Camera Motion Removing: How to Handle Outliers in Deblurring


Title	Beyond Camera Motion Removing: How to Handle Outliers in Deblurring
Authors	Chenwei Yang, Meng Chang, Huajun Feng, Zhihai Xu, Qi Li
Abstract	Performing camera motion deblurring is an important low-level vision task for achieving better imaging quality. When a scene has outliers such as saturated pixels and salt-and pepper noise, the image becomes more difficult to restore. In this paper, we propose an edge-aware scalerecurrent network (EASRN) to conduct camera motion deblurring. EASRN has a separate deblurring module that removes blur at multiple scales and an upsampling module that fuses different input scales. We propose a salient edge detection network to supervise the training process and solve the outlier problem by proposing a novel method of dataset generation. Light streaks are printed on the sharp image to simulate the cutoff effect from saturation. We evaluate our method on the standard deblurring datasets. Both objective evaluation indexes and subjective visualization show that our method results in better deblurring quality than the other state-of-the-art approaches.
Tasks	Deblurring, Edge Detection
Published	2020-02-24
URL	https://arxiv.org/abs/2002.10201v1
PDF	https://arxiv.org/pdf/2002.10201v1.pdf
PWC	https://paperswithcode.com/paper/beyond-camera-motion-removing-how-to-handle
Repo
Framework

A Novel Learnable Gradient Descent Type Algorithm for Non-convex Non-smooth Inverse Problems


Title	A Novel Learnable Gradient Descent Type Algorithm for Non-convex Non-smooth Inverse Problems
Authors	Qingchao Zhang, Xiaojing Ye, Hongcheng Liu, Yunmei Chen
Abstract	Optimization algorithms for solving nonconvex inverse problem have attracted significant interests recently. However, existing methods require the nonconvex regularization to be smooth or simple to ensure convergence. In this paper, we propose a novel gradient descent type algorithm, by leveraging the idea of residual learning and Nesterov’s smoothing technique, to solve inverse problems consisting of general nonconvex and nonsmooth regularization with provable convergence. Moreover, we develop a neural network architecture intimating this algorithm to learn the nonlinear sparsity transformation adaptively from training data, which also inherits the convergence to accommodate the general nonconvex structure of this learned transformation. Numerical results demonstrate that the proposed network outperforms the state-of-the-art methods on a variety of different image reconstruction problems in terms of efficiency and accuracy.
Tasks	Image Reconstruction
Published	2020-03-15
URL	https://arxiv.org/abs/2003.06748v2
PDF	https://arxiv.org/pdf/2003.06748v2.pdf
PWC	https://paperswithcode.com/paper/a-novel-learnable-gradient-descent-type
Repo
Framework

Common Conversational Community Prototype: Scholarly Conversational Assistant


Title	Common Conversational Community Prototype: Scholarly Conversational Assistant
Authors	Krisztian Balog, Lucie Flekova, Matthias Hagen, Rosie Jones, Martin Potthast, Filip Radlinski, Mark Sanderson, Svitlana Vakulenko, Hamed Zamani
Abstract	This paper discusses the potential for creating academic resources (tools, data, and evaluation approaches) to support research in conversational search, by focusing on realistic information needs and conversational interactions. Specifically, we propose to develop and operate a prototype conversational search system for scholarly activities. This Scholarly Conversational Assistant would serve as a useful tool, a means to create datasets, and a platform for running evaluation challenges by groups across the community. This article results from discussions of a working group at Dagstuhl Seminar 19461 on Conversational Search.
Tasks
Published	2020-01-19
URL	https://arxiv.org/abs/2001.06910v1
PDF	https://arxiv.org/pdf/2001.06910v1.pdf
PWC	https://paperswithcode.com/paper/common-conversational-community-prototype
Repo
Framework

Matching Text with Deep Mutual Information Estimation


Title	Matching Text with Deep Mutual Information Estimation
Authors	Xixi Zhou, Chengxi Li, Jiajun Bu, Chengwei Yao, Keyue Shi, Zhi Yu, Zhou Yu
Abstract	Text matching is a core natural language processing research problem. How to retain sufficient information on both content and structure information is one important challenge. In this paper, we present a neural approach for general-purpose text matching with deep mutual information estimation incorporated. Our approach, Text matching with Deep Info Max (TIM), is integrated with a procedure of unsupervised learning of representations by maximizing the mutual information between text matching neural network’s input and output. We use both global and local mutual information to learn text representations. We evaluate our text matching approach on several tasks including natural language inference, paraphrase identification, and answer selection. Compared to the state-of-the-art approaches, the experiments show that our method integrated with mutual information estimation learns better text representation and achieves better experimental results of text matching tasks without exploiting pretraining on external data.
Tasks	Answer Selection, Natural Language Inference, Paraphrase Identification, Text Matching
Published	2020-03-09
URL	https://arxiv.org/abs/2003.11521v1
PDF	https://arxiv.org/pdf/2003.11521v1.pdf
PWC	https://paperswithcode.com/paper/matching-text-with-deep-mutual-information
Repo
Framework