April 2, 2020

2955 words 14 mins read

Paper Group ANR 204

Learning Memory-guided Normality for Anomaly Detection. LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units. Online Semantic Exploration of Indoor Maps. A Unifying Network Architecture for Semi-Structured Deep Distributional Learning. Reward Design for Driver Repositioning Using Multi …

Learning Memory-guided Normality for Anomaly Detection


Title	Learning Memory-guided Normality for Anomaly Detection
Authors	Hyunjong Park, Jongyoun Noh, Bumsub Ham
Abstract	We address the problem of anomaly detection, that is, detecting anomalous events in a video sequence. Anomaly detection methods based on convolutional neural networks (CNNs) typically leverage proxy tasks, such as reconstructing input video frames, to learn models describing normality without seeing anomalous samples at training time, and quantify the extent of abnormalities using the reconstruction error at test time. The main drawbacks of these approaches are that they do not consider the diversity of normal patterns explicitly, and the powerful representation capacity of CNNs allows to reconstruct abnormal video frames. To address this problem, we present an unsupervised learning approach to anomaly detection that considers the diversity of normal patterns explicitly, while lessening the representation capacity of CNNs. To this end, we propose to use a memory module with a new update scheme where items in the memory record prototypical patterns of normal data. We also present novel feature compactness and separateness losses to train the memory, boosting the discriminative power of both memory items and deeply learned features from normal data. Experimental results on standard benchmarks demonstrate the effectiveness and efficiency of our approach, which outperforms the state of the art.
Tasks	Anomaly Detection
Published	2020-03-30
URL	https://arxiv.org/abs/2003.13228v1
PDF	https://arxiv.org/pdf/2003.13228v1.pdf
PWC	https://paperswithcode.com/paper/learning-memory-guided-normality-for-anomaly
Repo
Framework

LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units


Title	LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units
Authors	Guangli Li, Lei Liu, Xueying Wang, Xiu Ma, Xiaobing Feng
Abstract	Accelerating deep convolutional neural networks has become an active topic and sparked an interest in academia and industry. In this paper, we propose an efficient low-precision quantized Winograd convolution algorithm, called LANCE, which combines the advantages of fast convolution and quantization techniques. By embedding linear quantization operations into the Winograd-domain, the fast convolution can be performed efficiently under low-precision computation on graphics processing units. We test neural network models with LANCE on representative image classification datasets, including SVHN, CIFAR, and ImageNet. The experimental results show that our 8-bit quantized Winograd convolution improves the performance by up to 2.40x over the full-precision convolution with trivial accuracy loss.
Tasks	Image Classification, Quantization
Published	2020-03-19
URL	https://arxiv.org/abs/2003.08646v2
PDF	https://arxiv.org/pdf/2003.08646v2.pdf
PWC	https://paperswithcode.com/paper/lance-efficient-low-precision-quantized
Repo
Framework

Online Semantic Exploration of Indoor Maps


Title	Online Semantic Exploration of Indoor Maps
Authors	Ziyuan Liu, Dong Chen, Georg von Wichert
Abstract	In this paper we propose a method to extract an abstracted floor plan from typical grid maps using Bayesian reasoning. The result of this procedure is a probabilistic generative model of the environment defined over abstract concepts. It is well suited for higher-level reasoning and communication purposes. We demonstrate the effectiveness of the approach through real-world experiments.
Tasks
Published	2020-02-21
URL	https://arxiv.org/abs/2002.10939v1
PDF	https://arxiv.org/pdf/2002.10939v1.pdf
PWC	https://paperswithcode.com/paper/online-semantic-exploration-of-indoor-maps
Repo
Framework

A Unifying Network Architecture for Semi-Structured Deep Distributional Learning


Title	A Unifying Network Architecture for Semi-Structured Deep Distributional Learning
Authors	David Rügamer, Chris Kolb, Nadja Klein
Abstract	We propose a unifying network architecture for deep distributional learning in which entire distributions can be learned in a general framework of interpretable regression models and deep neural networks. Previous approaches that try to combine advanced statistical models and deep neural networks embed the neural network part as a predictor in an additive regression model. In contrast, our approach estimates the statistical model part within a unifying neural network by projecting the deep learning model part into the orthogonal complement of the regression model predictor. This facilitates both estimation and interpretability in high-dimensional settings. We identify appropriate default penalties that can also be treated as prior distribution assumptions in the Bayesian version of our network architecture. We consider several use-cases in experiments with synthetic data and real world applications to demonstrate the full efficacy of our approach.
Tasks
Published	2020-02-13
URL	https://arxiv.org/abs/2002.05777v1
PDF	https://arxiv.org/pdf/2002.05777v1.pdf
PWC	https://paperswithcode.com/paper/a-unifying-network-architecture-for-semi
Repo
Framework

Reward Design for Driver Repositioning Using Multi-Agent Reinforcement Learning


Title	Reward Design for Driver Repositioning Using Multi-Agent Reinforcement Learning
Authors	Zhenyu Shou, Xuan Di
Abstract	A large portion of passenger requests is reportedly unserviced, partially due to vacant for-hire drivers’ cruising behavior during the passenger seeking process. This paper aims to model the multi-driver repositioning task through a mean field multi-agent reinforcement learning (MARL) approach that captures competition among multiple agents. Because the direct application of MARL to the multi-driver system under a given reward mechanism will likely yield a suboptimal equilibrium due to the selfishness of drivers, this study proposes an reward design scheme with which a more desired equilibrium can be reached. To effectively solve the bilevel optimization problem with upper level as the reward design and the lower level as a multi-agent system, a Bayesian optimization (BO) algorithm is adopted to speed up the learning process. We then apply the bilevel optimization model to two case studies, namely, e-hailing driver repositioning under service charge and multiclass taxi driver repositioning under NYC congestion pricing. In the first case study, the model is validated by the agreement between the derived optimal control from BO and that from an analytical solution. With a simple piecewise linear service charge, the objective of the e-hailing platform can be increased by 4.0%. In the second case study, an optimal toll charge of $5.1 is solved using BO, which improves the objective of city planners by 7.9%, compared to that without any toll charge. Under this optimal toll charge, the number of taxis in the NYC central business district is decreased, indicating a better traffic condition, without substantially increasing the crowdedness of the subway system.
Tasks	bilevel optimization, Multi-agent Reinforcement Learning
Published	2020-02-17
URL	https://arxiv.org/abs/2002.06723v2
PDF	https://arxiv.org/pdf/2002.06723v2.pdf
PWC	https://paperswithcode.com/paper/reward-design-for-driver-repositioning-using
Repo
Framework

Combining Progressive Rethinking and Collaborative Learning: A Deep Framework for In-Loop Filtering


Title	Combining Progressive Rethinking and Collaborative Learning: A Deep Framework for In-Loop Filtering
Authors	Dezhao Wang, Sifeng Xia, Wenhan Yang, Jiaying Liu
Abstract	In this paper, we aim to address two critical issues in deep-learning based in-loop filter of modern codecs: 1) how to model spatial and temporal redundancies more effectively in the coding scenario; 2) what kinds of side information (side-info) can be inferred from the codecs to benefit in-loop filter models and how this side-info is injected. For the first issue, we design a deep network with both progressive rethinking and collaborative learning mechanisms to improve quality of the reconstructed intra-frames and inter-frames, respectively. For intra coding, a Progressive Rethinking Block (PRB) and its stacked Progressive Rethinking Network (PRN) are designed to simulate the human decision mechanism for effective spatial modeling. The typical cascaded deep network utilizes a bottleneck module at the end of each block to reduce the dimension size of the feature to generate the summarization of past experiences. Our designed block rethinks progressively, namely introducing an additional inter-block connection to bypass a high-dimensional informative feature across blocks to review the complete past memorized experiences. For inter coding, the model learns collaboratively for temporal modeling. The current reconstructed frame interacts with reference frames (peak quality frame and the nearest adjacent frame) progressively at the feature level. For the second issue, side-info utilization, we extract both intra-frame and interframe side-info for a better context modeling. A coarse-tofine partition map based on HEVC partition trees is built as the intra-frame side-info. Furthermore, the warped features of the reference frames are offered as the inter-frame side-info. Benefiting from our subtle design, under All-Intra (AI), Low-Delay B (LDB), Low-Delay P (LDP) and Random Access (RA) configuration, our PRNs provide 9.0%, 9.0%, 10.6% and 8.0% BD-rate reduction on average respectively.
Tasks
Published	2020-01-16
URL	https://arxiv.org/abs/2001.05651v2
PDF	https://arxiv.org/pdf/2001.05651v2.pdf
PWC	https://paperswithcode.com/paper/combining-progressive-rethinking-and
Repo
Framework

Learning Structured Communication for Multi-agent Reinforcement Learning


Title	Learning Structured Communication for Multi-agent Reinforcement Learning
Authors	Junjie Sheng, Xiangfeng Wang, Bo Jin, Junchi Yan, Wenhao Li, Tsung-Hui Chang, Jun Wang, Hongyuan Zha
Abstract	This work explores the large-scale multi-agent communication mechanism under a multi-agent reinforcement learning (MARL) setting. We summarize the general categories of topology for communication structures in MARL literature, which are often manually specified. Then we propose a novel framework termed as Learning Structured Communication (LSC) by using a more flexible and efficient communication topology. Our framework allows for adaptive agent grouping to form different hierarchical formations over episodes, which is generated by an auxiliary task combined with a hierarchical routing protocol. Given each formed topology, a hierarchical graph neural network is learned to enable effective message information generation and propagation among inter- and intra-group communications. In contrast to existing communication mechanisms, our method has an explicit while learnable design for hierarchical communication. Experiments on challenging tasks show the proposed LSC enjoys high communication efficiency, scalability, and global cooperation capability.
Tasks	Multi-agent Reinforcement Learning
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04235v1
PDF	https://arxiv.org/pdf/2002.04235v1.pdf
PWC	https://paperswithcode.com/paper/learning-structured-communication-for-multi-1
Repo
Framework

Some Experiments on the influence of Problem Hardness in Morphological Development based Learning of Neural Controllers


Title	Some Experiments on the influence of Problem Hardness in Morphological Development based Learning of Neural Controllers
Authors	M. Naya-Varela, A. Faina, R. J. Duro
Abstract	Natural beings undergo a morphological development process of their bodies while they are learning and adapting to the environments they face from infancy to adulthood. In fact, this is the period where the most important learning pro-cesses, those that will support learning as adults, will take place. However, in artificial systems, this interaction between morphological development and learning, and its possible advantages, have seldom been considered. In this line, this paper seeks to provide some insights into how morphological development can be harnessed in order to facilitate learning in em-bodied systems facing tasks or domains that are hard to learn. In particular, here we will concentrate on whether morphological development can really provide any advantage when learning complex tasks and whether its relevance towards learning in-creases as tasks become harder. To this end, we present the results of some initial experiments on the application of morpho-logical development to learning to walk in three cases, that of a quadruped, a hexapod and that of an octopod. These results seem to confirm that as task learning difficulty increases the application of morphological development to learning becomes more advantageous.
Tasks
Published	2020-03-12
URL	https://arxiv.org/abs/2003.05817v1
PDF	https://arxiv.org/pdf/2003.05817v1.pdf
PWC	https://paperswithcode.com/paper/some-experiments-on-the-influence-of-problem
Repo
Framework

Deep Sets for Generalization in RL


Title	Deep Sets for Generalization in RL
Authors	Tristan Karch, Cédric Colas, Laetitia Teodorescu, Clément Moulin-Frier, Pierre-Yves Oudeyer
Abstract	This paper investigates the idea of encoding object-centered representations in the design of the reward function and policy architectures of a language-guided reinforcement learning agent. This is done using a combination of object-wise permutation invariant networks inspired from Deep Sets and gated-attention mechanisms. In a 2D procedurally-generated world where agents targeting goals in natural language navigate and interact with objects, we show that these architectures demonstrate strong generalization capacities to out-of-distribution goals. We study the generalization to varying numbers of objects at test time and further extend the object-centered architectures to goals involving relational reasoning.
Tasks	Relational Reasoning
Published	2020-03-20
URL	https://arxiv.org/abs/2003.09443v1
PDF	https://arxiv.org/pdf/2003.09443v1.pdf
PWC	https://paperswithcode.com/paper/deep-sets-for-generalization-in-rl
Repo
Framework

A model of figure ground organization incorporating local and global cues


Title	A model of figure ground organization incorporating local and global cues
Authors	Sudarshan Ramenahalli
Abstract	Figure Ground Organization (FGO) – inferring spatial depth ordering of objects in a visual scene – involves determining which side of an occlusion boundary is figure (closer to the observer) and which is ground (further away from the observer). A combination of global cues, like convexity, and local cues, like T-junctions are involved in this process. We present a biologically motivated, feed forward computational model of FGO incorporating convexity, surroundedness, parallelism as global cues and Spectral Anisotropy (SA), T-junctions as local cues. While SA is computed in a biologically plausible manner, the inclusion of T-Junctions is biologically motivated. The model consists of three independent feature channels, Color, Intensity and Orientation, but SA and T-Junctions are introduced only in the Orientation channel as these properties are specific to that feature of objects. We study the effect of adding each local cue independently and both of them simultaneously to the model with no local cues. We evaluate model performance based on figure-ground classification accuracy (FGCA) at every border location using the BSDS 300 figure-ground dataset. Each local cue, when added alone, gives statistically significant improvement in the FGCA of the model suggesting its usefulness as an independent FGO cue. The model with both local cues achieves higher FGCA than the models with individual cues, indicating SA and T-Junctions are not mutually contradictory. Compared to the model with no local cues, the feed-forward model with both local cues achieves $\geq 8.78$% improvement in terms of FGCA.
Tasks
Published	2020-03-15
URL	https://arxiv.org/abs/2003.06731v1
PDF	https://arxiv.org/pdf/2003.06731v1.pdf
PWC	https://paperswithcode.com/paper/a-model-of-figure-ground-organization
Repo
Framework

Lagrangian Decomposition for Neural Network Verification


Title	Lagrangian Decomposition for Neural Network Verification
Authors	Rudy Bunel, Alessandro De Palma, Alban Desmaison, Krishnamurthy Dvijotham, Pushmeet Kohli, Philip H. S. Torr, M. Pawan Kumar
Abstract	A fundamental component of neural network verification is the computation of bounds on the values their outputs can take. Previous methods have either used off-the-shelf solvers, discarding the problem structure, or relaxed the problem even further, making the bounds unnecessarily loose. We propose a novel approach based on Lagrangian Decomposition. Our formulation admits an efficient supergradient ascent algorithm, as well as an improved proximal algorithm. Both the algorithms offer three advantages: (i) they yield bounds that are provably at least as tight as previous dual algorithms relying on Lagrangian relaxations; (ii) they are based on operations analogous to forward/backward pass of neural networks layers and are therefore easily parallelizable, amenable to GPU implementation and able to take advantage of the convolutional structure of problems; and (iii) they allow for anytime stopping while still providing valid bounds. Empirically, we show that we obtain bounds comparable with off-the-shelf solvers in a fraction of their running time, and obtain tighter bounds in the same time as previous dual algorithms. This results in an overall speed-up when employing the bounds for formal verification.
Tasks
Published	2020-02-24
URL	https://arxiv.org/abs/2002.10410v1
PDF	https://arxiv.org/pdf/2002.10410v1.pdf
PWC	https://paperswithcode.com/paper/lagrangian-decomposition-for-neural-network
Repo
Framework

Learning Bijective Feature Maps for Linear ICA


Title	Learning Bijective Feature Maps for Linear ICA
Authors	Alexander Camuto, Matthew Willetts, Brooks Paige, Chris Holmes, Stephen Roberts
Abstract	Separating high-dimensional data like images into independent latent factors remains an open research problem. Here we develop a method that jointly learns a linear independent component analysis (ICA) model with non-linear bijective feature maps. By combining these two methods, ICA can learn interpretable latent structure for images. For non-square ICA, where we assume the number of sources is less than the dimensionality of data, we achieve better unsupervised latent factor discovery than flow-based models and linear ICA. This performance scales to large image datasets such as CelebA.
Tasks
Published	2020-02-18
URL	https://arxiv.org/abs/2002.07766v2
PDF	https://arxiv.org/pdf/2002.07766v2.pdf
PWC	https://paperswithcode.com/paper/learning-bijective-feature-maps-for-linear
Repo
Framework

Towards an information-theory for hierarchical partitions


Title	Towards an information-theory for hierarchical partitions
Authors	Juan I. Perotti, Nahuel Almeira, Fabio Saracco
Abstract	Complex systems often require descriptions covering a wide range of scales and organization levels, where a hierarchical decomposition of their description into components and sub-components is often convenient. To better understand the hierarchical decomposition of complex systems, in this work we prove a few essential results that contribute to the development of an information-theory for hierarchical-partitions.
Tasks
Published	2020-02-27
URL	https://arxiv.org/abs/2003.02911v1
PDF	https://arxiv.org/pdf/2003.02911v1.pdf
PWC	https://paperswithcode.com/paper/towards-an-information-theory-for
Repo
Framework

Semi-automatic methods for adding words to the dictionary of VepKar corpus based on inflectional rules extracted from Wiktionary


Title	Semi-automatic methods for adding words to the dictionary of VepKar corpus based on inflectional rules extracted from Wiktionary
Authors	Natalia Krizhanovsky, Andrew Krizhanovsky
Abstract	The article describes a technique for using English Wiktionary inflection tables for generating word forms for Veps verbs and nominals in the Open corpus of Veps and Karelian languages. The information concerning Karelian and Veps Wiktionary entries with inflection tables is given. The operating principle of the Wiktionary static and dynamic templates is explained with the use of the jogi (river) dictionary entry as an example. The method of constructing the inflection table in the dictionary of the VepKar corpus according to the data of the dynamic template of the English Wiktionary is presented.
Tasks
Published	2020-01-14
URL	https://arxiv.org/abs/2001.04719v1
PDF	https://arxiv.org/pdf/2001.04719v1.pdf
PWC	https://paperswithcode.com/paper/semi-automatic-methods-for-adding-words-to
Repo
Framework

Enhancement of shock-capturing methods via machine learning


Title	Enhancement of shock-capturing methods via machine learning
Authors	Ben Stevens, Tim Colonius
Abstract	In recent years, machine learning has been used to create data-driven solutions to problems for which an algorithmic solution is intractable, as well as fine-tuning existing algorithms. This research applies machine learning to the development of an improved finite-volume method for simulating PDEs with discontinuous solutions. Shock capturing methods make use of nonlinear switching functions that are not guaranteed to be optimal. Because data can be used to learn nonlinear relationships, we train a neural network to improve the results of a fifth-order WENO method. We post-process the outputs of the neural network to guarantee that the method is consistent. The training data consists of the exact mapping between cell averages and interpolated values for a set of integrable functions that represent waveforms we would expect to see while simulating a PDE. We demonstrate our method on linear advection of a discontinuous function, the inviscid Burgers’ equation, and the 1-D Euler equations. For the latter, we examine the Shu-Osher model problem for turbulence-shockwave interactions. We find that our method outperforms WENO in simulations where the numerical solution becomes overly diffused due to numerical viscosity.
Tasks
Published	2020-02-06
URL	https://arxiv.org/abs/2002.02521v1
PDF	https://arxiv.org/pdf/2002.02521v1.pdf
PWC	https://paperswithcode.com/paper/enhancement-of-shock-capturing-methods-via
Repo
Framework