October 21, 2019

3355 words 16 mins read

Paper Group AWR 45

FastDeRain: A Novel Video Rain Streak Removal Method Using Directional Gradient Priors. Large scale evaluation of local image feature detectors on homography datasets. A generic framework for privacy preserving deep learning. Building Generalizable Agents with a Realistic and Rich 3D Environment. Negative Update Intervals in Deep Multi-Agent Reinfo …

FastDeRain: A Novel Video Rain Streak Removal Method Using Directional Gradient Priors


Title	FastDeRain: A Novel Video Rain Streak Removal Method Using Directional Gradient Priors
Authors	Tai-Xiang Jiang, Ting-Zhu Huang, Xi-Le Zhao, Liang-Jian Deng, Yao Wang
Abstract	Rain streak removal is an important issue in outdoor vision systems and has recently been investigated extensively. In this paper, we propose a novel video rain streak removal approach FastDeRain, which fully considers the discriminative characteristics of rain streaks and the clean video in the gradient domain. Specifically, on the one hand, rain streaks are sparse and smooth along the direction of the raindrops, whereas on the other hand, clean videos exhibit piecewise smoothness along the rain-perpendicular direction and continuity along the temporal direction. Theses smoothness and continuity results in the sparse distribution in the different directional gradient domain, respectively. Thus, we minimize 1) the $\ell_1$ norm to enhance the sparsity of the underlying rain streaks, 2) two $\ell_1$ norm of unidirectional Total Variation (TV) regularizers to guarantee the anisotropic spatial smoothness, and 3) an $\ell_1$ norm of the time-directional difference operator to characterize the temporal continuity. A split augmented Lagrangian shrinkage algorithm (SALSA) based algorithm is designed to solve the proposed minimization model. Experiments conducted on synthetic and real data demonstrate the effectiveness and efficiency of the proposed method. According to comprehensive quantitative performance measures, our approach outperforms other state-of-the-art methods especially on account of the running time. The code of FastDeRain can be downloaded at https://github.com/TaiXiangJiang/FastDeRain.
Tasks
Published	2018-03-20
URL	http://arxiv.org/abs/1803.07487v3
PDF	http://arxiv.org/pdf/1803.07487v3.pdf
PWC	https://paperswithcode.com/paper/fastderain-a-novel-video-rain-streak-removal
Repo	https://github.com/uestctensorgroup/FastDeRain
Framework	none

Large scale evaluation of local image feature detectors on homography datasets


Title	Large scale evaluation of local image feature detectors on homography datasets
Authors	Karel Lenc, Andrea Vedaldi
Abstract	We present a large scale benchmark for the evaluation of local feature detectors. Our key innovation is the introduction of a new evaluation protocol which extends and improves the standard detection repeatability measure. The new protocol is better for assessment on a large number of images and reduces the dependency of the results on unwanted distractors such as the number of detected features and the feature magnification factor. Additionally, our protocol provides a comprehensive assessment of the expected performance of detectors under several practical scenarios. Using images from the recently-introduced HPatches dataset, we evaluate a range of state-of-the-art local feature detectors on two main tasks: viewpoint and illumination invariant detection. Contrary to previous detector evaluations, our study contains an order of magnitude more image sequences, resulting in a quantitative evaluation significantly more robust to over-fitting. We also show that traditional detectors are still very competitive when compared to recent deep-learning alternatives.
Tasks
Published	2018-07-20
URL	http://arxiv.org/abs/1807.07939v1
PDF	http://arxiv.org/pdf/1807.07939v1.pdf
PWC	https://paperswithcode.com/paper/large-scale-evaluation-of-local-image-feature
Repo	https://github.com/lenck/vlb-deteval
Framework	none

A generic framework for privacy preserving deep learning


Title	A generic framework for privacy preserving deep learning
Authors	Theo Ryffel, Andrew Trask, Morten Dahl, Bobby Wagner, Jason Mancuso, Daniel Rueckert, Jonathan Passerat-Palmbach
Abstract	We detail a new framework for privacy preserving deep learning and discuss its assets. The framework puts a premium on ownership and secure processing of data and introduces a valuable representation based on chains of commands and tensors. This abstraction allows one to implement complex privacy preserving constructs such as Federated Learning, Secure Multiparty Computation, and Differential Privacy while still exposing a familiar deep learning API to the end-user. We report early results on the Boston Housing and Pima Indian Diabetes datasets. While the privacy features apart from Differential Privacy do not impact the prediction accuracy, the current implementation of the framework introduces a significant overhead in performance, which will be addressed at a later stage of the development. We believe this work is an important milestone introducing the first reliable, general framework for privacy preserving deep learning.
Tasks	Privacy Preserving Deep Learning
Published	2018-11-09
URL	http://arxiv.org/abs/1811.04017v2
PDF	http://arxiv.org/pdf/1811.04017v2.pdf
PWC	https://paperswithcode.com/paper/a-generic-framework-for-privacy-preserving
Repo	https://github.com/ainetlabs/pysyft
Framework	pytorch

Building Generalizable Agents with a Realistic and Rich 3D Environment


Title	Building Generalizable Agents with a Realistic and Rich 3D Environment
Authors	Yi Wu, Yuxin Wu, Georgia Gkioxari, Yuandong Tian
Abstract	Teaching an agent to navigate in an unseen 3D environment is a challenging task, even in the event of simulated environments. To generalize to unseen environments, an agent needs to be robust to low-level variations (e.g. color, texture, object changes), and also high-level variations (e.g. layout changes of the environment). To improve overall generalization, all types of variations in the environment have to be taken under consideration via different level of data augmentation steps. To this end, we propose House3D, a rich, extensible and efficient environment that contains 45,622 human-designed 3D scenes of visually realistic houses, ranging from single-room studios to multi-storied houses, equipped with a diverse set of fully labeled 3D objects, textures and scene layouts, based on the SUNCG dataset (Song et.al.). The diversity in House3D opens the door towards scene-level augmentation, while the label-rich nature of House3D enables us to inject pixel- & task-level augmentations such as domain randomization (Toubin et. al.) and multi-task training. Using a subset of houses in House3D, we show that reinforcement learning agents trained with an enhancement of different levels of augmentations perform much better in unseen environments than our baselines with raw RGB input by over 8% in terms of navigation success rate. House3D is publicly available at http://github.com/facebookresearch/House3D.
Tasks	Data Augmentation
Published	2018-01-07
URL	http://arxiv.org/abs/1801.02209v2
PDF	http://arxiv.org/pdf/1801.02209v2.pdf
PWC	https://paperswithcode.com/paper/building-generalizable-agents-with-a
Repo	https://github.com/kibeomKim/House3D_baseline
Framework	pytorch

Negative Update Intervals in Deep Multi-Agent Reinforcement Learning


Title	Negative Update Intervals in Deep Multi-Agent Reinforcement Learning
Authors	Gregory Palmer, Rahul Savani, Karl Tuyls
Abstract	In Multi-Agent Reinforcement Learning (MA-RL), independent cooperative learners must overcome a number of pathologies to learn optimal joint policies. Addressing one pathology often leaves approaches vulnerable towards others. For instance, hysteretic Q-learning addresses miscoordination while leaving agents vulnerable towards misleading stochastic rewards. Other methods, such as leniency, have proven more robust when dealing with multiple pathologies simultaneously. However, leniency has predominately been studied within the context of strategic form games (bimatrix games) and fully observable Markov games consisting of a small number of probabilistic state transitions. This raises the question of whether these findings scale to more complex domains. For this purpose we implement a temporally extend version of the Climb Game, within which agents must overcome multiple pathologies simultaneously, including relative overgeneralisation, stochasticity, the alter-exploration and moving target problems, while learning from a large observation space. We find that existing lenient and hysteretic approaches fail to consistently learn near optimal joint-policies in this environment. To address these pathologies we introduce Negative Update Intervals-DDQN (NUI-DDQN), a Deep MA-RL algorithm which discards episodes yielding cumulative rewards outside the range of expanding intervals. NUI-DDQN consistently gravitates towards optimal joint-policies in our environment, overcoming the outlined pathologies.
Tasks	Multi-agent Reinforcement Learning, Q-Learning
Published	2018-09-13
URL	https://arxiv.org/abs/1809.05096v3
PDF	https://arxiv.org/pdf/1809.05096v3.pdf
PWC	https://paperswithcode.com/paper/negative-update-intervals-in-deep-multi-agent
Repo	https://github.com/gjp1203/nui_in_madrl
Framework	none

Sample-Efficient Imitation Learning via Generative Adversarial Nets


Title	Sample-Efficient Imitation Learning via Generative Adversarial Nets
Authors	Lionel Blondé, Alexandros Kalousis
Abstract	GAIL is a recent successful imitation learning architecture that exploits the adversarial training procedure introduced in GANs. Albeit successful at generating behaviours similar to those demonstrated to the agent, GAIL suffers from a high sample complexity in the number of interactions it has to carry out in the environment in order to achieve satisfactory performance. We dramatically shrink the amount of interactions with the environment necessary to learn well-behaved imitation policies, by up to several orders of magnitude. Our framework, operating in the model-free regime, exhibits a significant increase in sample-efficiency over previous methods by simultaneously a) learning a self-tuned adversarially-trained surrogate reward and b) leveraging an off-policy actor-critic architecture. We show that our approach is simple to implement and that the learned agents remain remarkably stable, as shown in our experiments that span a variety of continuous control tasks. Video visualisations available at: \url{https://youtu.be/-nCsqUJnRKU}.
Tasks	Continuous Control, Imitation Learning
Published	2018-09-06
URL	http://arxiv.org/abs/1809.02064v3
PDF	http://arxiv.org/pdf/1809.02064v3.pdf
PWC	https://paperswithcode.com/paper/sample-efficient-imitation-learning-via
Repo	https://github.com/lionelblonde/sam-pytorch
Framework	pytorch

Representation Learning of Entities and Documents from Knowledge Base Descriptions


Title	Representation Learning of Entities and Documents from Knowledge Base Descriptions
Authors	Ikuya Yamada, Hiroyuki Shindo, Yoshiyasu Takefuji
Abstract	In this paper, we describe TextEnt, a neural network model that learns distributed representations of entities and documents directly from a knowledge base (KB). Given a document in a KB consisting of words and entity annotations, we train our model to predict the entity that the document describes and map the document and its target entity close to each other in a continuous vector space. Our model is trained using a large number of documents extracted from Wikipedia. The performance of the proposed model is evaluated using two tasks, namely fine-grained entity typing and multiclass text classification. The results demonstrate that our model achieves state-of-the-art performance on both tasks. The code and the trained representations are made available online for further academic research.
Tasks	Entity Typing, Representation Learning, Text Classification
Published	2018-06-08
URL	http://arxiv.org/abs/1806.02960v1
PDF	http://arxiv.org/pdf/1806.02960v1.pdf
PWC	https://paperswithcode.com/paper/representation-learning-of-entities-and
Repo	https://github.com/wikipedia2vec/wikipedia2vec
Framework	none

Unsupervised Predictive Memory in a Goal-Directed Agent


Title	Unsupervised Predictive Memory in a Goal-Directed Agent
Authors	Greg Wayne, Chia-Chun Hung, David Amos, Mehdi Mirza, Arun Ahuja, Agnieszka Grabska-Barwinska, Jack Rae, Piotr Mirowski, Joel Z. Leibo, Adam Santoro, Mevlana Gemici, Malcolm Reynolds, Tim Harley, Josh Abramson, Shakir Mohamed, Danilo Rezende, David Saxton, Adam Cain, Chloe Hillier, David Silver, Koray Kavukcuoglu, Matt Botvinick, Demis Hassabis, Timothy Lillicrap
Abstract	Animals execute goal-directed behaviours despite the limited range and scope of their sensors. To cope, they explore environments and store memories maintaining estimates of important information that is not presently available. Recently, progress has been made with artificial intelligence (AI) agents that learn to perform tasks from sensory input, even at a human level, by merging reinforcement learning (RL) algorithms with deep neural networks, and the excitement surrounding these results has led to the pursuit of related ideas as explanations of non-human animal learning. However, we demonstrate that contemporary RL algorithms struggle to solve simple tasks when enough information is concealed from the sensors of the agent, a property called “partial observability”. An obvious requirement for handling partially observed tasks is access to extensive memory, but we show memory is not enough; it is critical that the right information be stored in the right format. We develop a model, the Memory, RL, and Inference Network (MERLIN), in which memory formation is guided by a process of predictive modeling. MERLIN facilitates the solution of tasks in 3D virtual reality environments for which partial observability is severe and memories must be maintained over long durations. Our model demonstrates a single learning agent architecture that can solve canonical behavioural tasks in psychology and neurobiology without strong simplifying assumptions about the dimensionality of sensory input or the duration of experiences.
Tasks
Published	2018-03-28
URL	http://arxiv.org/abs/1803.10760v1
PDF	http://arxiv.org/pdf/1803.10760v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-predictive-memory-in-a-goal
Repo	https://github.com/yosider/merlin
Framework	none

Sampling strategies in Siamese Networks for unsupervised speech representation learning


Title	Sampling strategies in Siamese Networks for unsupervised speech representation learning
Authors	Rachid Riad, Corentin Dancette, Julien Karadayi, Neil Zeghidour, Thomas Schatz, Emmanuel Dupoux
Abstract	Recent studies have investigated siamese network architectures for learning invariant speech representations using same-different side information at the word level. Here we investigate systematically an often ignored component of siamese networks: the sampling procedure (how pairs of same vs. different tokens are selected). We show that sampling strategies taking into account Zipf’s Law, the distribution of speakers and the proportions of same and different pairs of words significantly impact the performance of the network. In particular, we show that word frequency compression improves learning across a large range of variations in number of training pairs. This effect does not apply to the same extent to the fully unsupervised setting, where the pairs of same-different words are obtained by spoken term discovery. We apply these results to pairs of words discovered using an unsupervised algorithm and show an improvement on state-of-the-art in unsupervised representation learning using siamese networks.
Tasks	Representation Learning, Unsupervised Representation Learning
Published	2018-04-30
URL	http://arxiv.org/abs/1804.11297v2
PDF	http://arxiv.org/pdf/1804.11297v2.pdf
PWC	https://paperswithcode.com/paper/sampling-strategies-in-siamese-networks-for
Repo	https://github.com/bootphon/abnet3
Framework	pytorch

Jointly Embedding Entities and Text with Distant Supervision


Title	Jointly Embedding Entities and Text with Distant Supervision
Authors	Denis Newman-Griffis, Albert M. Lai, Eric Fosler-Lussier
Abstract	Learning representations for knowledge base entities and concepts is becoming increasingly important for NLP applications. However, recent entity embedding methods have relied on structured resources that are expensive to create for new domains and corpora. We present a distantly-supervised method for jointly learning embeddings of entities and text from an unnanotated corpus, using only a list of mappings between entities and surface forms. We learn embeddings from open-domain and biomedical corpora, and compare against prior methods that rely on human-annotated text or large knowledge graph structure. Our embeddings capture entity similarity and relatedness better than prior work, both in existing biomedical datasets and a new Wikipedia-based dataset that we release to the community. Results on analogy completion and entity sense disambiguation indicate that entities and words capture complementary information that can be effectively combined for downstream use.
Tasks
Published	2018-07-09
URL	http://arxiv.org/abs/1807.03399v1
PDF	http://arxiv.org/pdf/1807.03399v1.pdf
PWC	https://paperswithcode.com/paper/jointly-embedding-entities-and-text-with
Repo	https://github.com/OSU-slatelab/WikiSRS
Framework	none

Emotion Representation Mapping for Automatic Lexicon Construction (Mostly) Performs on Human Level


Title	Emotion Representation Mapping for Automatic Lexicon Construction (Mostly) Performs on Human Level
Authors	Sven Buechel, Udo Hahn
Abstract	Emotion Representation Mapping (ERM) has the goal to convert existing emotion ratings from one representation format into another one, e.g., mapping Valence-Arousal-Dominance annotations for words or sentences into Ekman’s Basic Emotions and vice versa. ERM can thus not only be considered as an alternative to Word Emotion Induction (WEI) techniques for automatic emotion lexicon construction but may also help mitigate problems that come from the proliferation of emotion representation formats in recent years. We propose a new neural network approach to ERM that not only outperforms the previous state-of-the-art. Equally important, we present a refined evaluation methodology and gather strong evidence that our model yields results which are (almost) as reliable as human annotations, even in cross-lingual settings. Based on these results we generate new emotion ratings for 13 typologically diverse languages and claim that they have near-gold quality, at least.
Tasks
Published	2018-06-23
URL	http://arxiv.org/abs/1806.08890v1
PDF	http://arxiv.org/pdf/1806.08890v1.pdf
PWC	https://paperswithcode.com/paper/emotion-representation-mapping-for-automatic
Repo	https://github.com/JULIELab/EmoMap
Framework	none

Orthogonally Decoupled Variational Gaussian Processes


Title	Orthogonally Decoupled Variational Gaussian Processes
Authors	Hugh Salimbeni, Ching-An Cheng, Byron Boots, Marc Deisenroth
Abstract	Gaussian processes (GPs) provide a powerful non-parametric framework for reasoning over functions. Despite appealing theory, its superlinear computational and memory complexities have presented a long-standing challenge. State-of-the-art sparse variational inference methods trade modeling accuracy against complexity. However, the complexities of these methods still scale superlinearly in the number of basis functions, implying that that sparse GP methods are able to learn from large datasets only when a small model is used. Recently, a decoupled approach was proposed that removes the unnecessary coupling between the complexities of modeling the mean and the covariance functions of a GP. It achieves a linear complexity in the number of mean parameters, so an expressive posterior mean function can be modeled. While promising, this approach suffers from optimization difficulties due to ill-conditioning and non-convexity. In this work, we propose an alternative decoupled parametrization. It adopts an orthogonal basis in the mean function to model the residues that cannot be learned by the standard coupled approach. Therefore, our method extends, rather than replaces, the coupled approach to achieve strictly better performance. This construction admits a straightforward natural gradient update rule, so the structure of the information manifold that is lost during decoupling can be leveraged to speed up learning. Empirically, our algorithm demonstrates significantly faster convergence in multiple experiments.
Tasks	Gaussian Processes
Published	2018-09-24
URL	http://arxiv.org/abs/1809.08820v3
PDF	http://arxiv.org/pdf/1809.08820v3.pdf
PWC	https://paperswithcode.com/paper/orthogonally-decoupled-variational-gaussian
Repo	https://github.com/hughsalimbeni/orth_decoupled_var_gps
Framework	tf

A Neural Network Approach to Missing Marker Reconstruction in Human Motion Capture


Title	A Neural Network Approach to Missing Marker Reconstruction in Human Motion Capture
Authors	Taras Kucherenko, Jonas Beskow, Hedvig Kjellström
Abstract	Optical motion capture systems have become a widely used technology in various fields, such as augmented reality, robotics, movie production, etc. Such systems use a large number of cameras to triangulate the position of optical markers.The marker positions are estimated with high accuracy. However, especially when tracking articulated bodies, a fraction of the markers in each timestep is missing from the reconstruction. In this paper, we propose to use a neural network approach to learn how human motion is temporally and spatially correlated, and reconstruct missing markers positions through this model. We experiment with two different models, one LSTM-based and one time-window-based. Both methods produce state-of-the-art results, while working online, as opposed to most of the alternative methods, which require the complete sequence to be known. The implementation is publicly available at https://github.com/Svito-zar/NN-for-Missing-Marker-Reconstruction .
Tasks	3D Reconstruction, Missing Markers Reconstruction, Motion Capture
Published	2018-03-07
URL	http://arxiv.org/abs/1803.02665v4
PDF	http://arxiv.org/pdf/1803.02665v4.pdf
PWC	https://paperswithcode.com/paper/a-neural-network-approach-to-missing-marker
Repo	https://github.com/Svito-zar/NN-for-Missing-Marker-Reconstruction
Framework	tf

Quantification under prior probability shift: the ratio estimator and its extensions


Title	Quantification under prior probability shift: the ratio estimator and its extensions
Authors	Afonso Fernandes Vaz, Rafael Izbicki, Rafael Bassi Stern
Abstract	The quantification problem consists of determining the prevalence of a given label in a target population. However, one often has access to the labels in a sample from the training population but not in the target population. A common assumption in this situation is that of prior probability shift, that is, once the labels are known, the distribution of the features is the same in the training and target populations. In this paper, we derive a new lower bound for the risk of the quantification problem under the prior shift assumption. Complementing this lower bound, we present a new approximately minimax class of estimators, ratio estimators, which generalize several previous proposals in the literature. Using a weaker version of the prior shift assumption, which can be tested, we show that ratio estimators can be used to build confidence intervals for the quantification problem. We also extend the ratio estimator so that it can: (i) incorporate labels from the target population, when they are available and (ii) estimate how the prevalence of positive labels varies according to a function of certain covariates.
Tasks
Published	2018-07-11
URL	http://arxiv.org/abs/1807.03929v2
PDF	http://arxiv.org/pdf/1807.03929v2.pdf
PWC	https://paperswithcode.com/paper/quantification-under-prior-probability-shift
Repo	https://github.com/afonsofvaz/ratio_estimator
Framework	none

An Introduction to Probabilistic Programming


Title	An Introduction to Probabilistic Programming
Authors	Jan-Willem van de Meent, Brooks Paige, Hongseok Yang, Frank Wood
Abstract	This document is designed to be a first-year graduate-level introduction to probabilistic programming. It not only provides a thorough background for anyone wishing to use a probabilistic programming system, but also introduces the techniques needed to design and build these systems. It is aimed at people who have an undergraduate-level understanding of either or, ideally, both probabilistic machine learning and programming languages. We start with a discussion of model-based reasoning and explain why conditioning as a foundational computation is central to the fields of probabilistic machine learning and artificial intelligence. We then introduce a simple first-order probabilistic programming language (PPL) whose programs define static-computation-graph, finite-variable-cardinality models. In the context of this restricted PPL we introduce fundamental inference algorithms and describe how they can be implemented in the context of models denoted by probabilistic programs. In the second part of this document, we introduce a higher-order probabilistic programming language, with a functionality analogous to that of established programming languages. This affords the opportunity to define models with dynamic computation graphs, at the cost of requiring inference methods that generate samples by repeatedly executing the program. Foundational inference algorithms for this kind of probabilistic programming language are explained in the context of an interface between program executions and an inference controller. This document closes with a chapter on advanced topics which we believe to be, at the time of writing, interesting directions for probabilistic programming research; directions that point towards a tight integration with deep neural network research and the development of systems for next-generation artificial intelligence applications.
Tasks	Probabilistic Programming
Published	2018-09-27
URL	http://arxiv.org/abs/1809.10756v1
PDF	http://arxiv.org/pdf/1809.10756v1.pdf
PWC	https://paperswithcode.com/paper/an-introduction-to-probabilistic-programming
Repo	https://github.com/rmascarenhas/foppl
Framework	none