July 30, 2019

3366 words 16 mins read

Paper Group AWR 39

Adaptation to criticality through organizational invariance in embodied agents. Model-Free Renewable Scenario Generation Using Generative Adversarial Networks. Paraphrasing verbal metonymy through computational methods. Multi-Context Attention for Human Pose Estimation. Real-time deep hair matting on mobile devices. Information-Flow Matting. Integr …

Adaptation to criticality through organizational invariance in embodied agents


Title	Adaptation to criticality through organizational invariance in embodied agents
Authors	Miguel Aguilera, Manuel G. Bedia
Abstract	Many biological and cognitive systems do not operate deep within one or other regime of activity. Instead, they are poised at critical points located at phase transitions in their parameter space. The pervasiveness of criticality suggests that there may be general principles inducing this behaviour, yet there is no well-founded theory for understanding how criticality is generated at a wide span of levels and contexts. In order to explore how criticality might emerge from general adaptive mechanisms, we propose a simple learning rule that maintains an internal organizational structure from a specific family of systems at criticality. We implement the mechanism in artificial embodied agents controlled by a neural network maintaining a correlation structure randomly sampled from an Ising model at critical temperature. Agents are evaluated in two classical reinforcement learning scenarios: the Mountain Car and the Acrobot double pendulum. In both cases the neural controller appears to reach a point of criticality, which coincides with a transition point between two regimes of the agent’s behaviour. These results suggest that adaptation to criticality could be used as a general adaptive mechanism in some circumstances, providing an alternative explanation for the pervasive presence of criticality in biological and cognitive systems.
Tasks
Published	2017-12-13
URL	http://arxiv.org/abs/1712.05284v3
PDF	http://arxiv.org/pdf/1712.05284v3.pdf
PWC	https://paperswithcode.com/paper/adaptation-to-criticality-through
Repo	https://github.com/MiguelAguilera/Critical-Learning
Framework	none

Model-Free Renewable Scenario Generation Using Generative Adversarial Networks


Title	Model-Free Renewable Scenario Generation Using Generative Adversarial Networks
Authors	Yize Chen, Yishen Wang, Daniel Kirschen, Baosen Zhang
Abstract	Scenario generation is an important step in the operation and planning of power systems with high renewable penetrations. In this work, we proposed a data-driven approach for scenario generation using generative adversarial networks, which is based on two interconnected deep neural networks. Compared with existing methods based on probabilistic models that are often hard to scale or sample from, our method is data-driven, and captures renewable energy production patterns in both temporal and spatial dimensions for a large number of correlated resources. For validation, we use wind and solar times-series data from NREL integration data sets. We demonstrate that the proposed method is able to generate realistic wind and photovoltaic power profiles with full diversity of behaviors. We also illustrate how to generate scenarios based on different conditions of interest by using labeled data during training. For example, scenarios can be conditioned on weather events~(e.g. high wind day) or time of the year~(e,g. solar generation for a day in July). Because of the feedforward nature of the neural networks, scenarios can be generated extremely efficiently without sophisticated sampling techniques.
Tasks
Published	2017-07-30
URL	http://arxiv.org/abs/1707.09676v2
PDF	http://arxiv.org/pdf/1707.09676v2.pdf
PWC	https://paperswithcode.com/paper/model-free-renewable-scenario-generation
Repo	https://github.com/chwneo7/VAE-code
Framework	none

Paraphrasing verbal metonymy through computational methods


Title	Paraphrasing verbal metonymy through computational methods
Authors	Alberto Morón Hernández
Abstract	Verbal metonymy has received relatively scarce attention in the field of computational linguistics despite the fact that a model to accurately paraphrase metonymy has applications both in academia and the technology sector. The method described in this paper makes use of data from the British National Corpus in order to create word vectors, find instances of verbal metonymy and generate potential paraphrases. Two different ways of creating word vectors are evaluated in this study: Continuous bag of words and Skip-grams. Skip-grams are found to outperform the Continuous bag of words approach. Furthermore, the Skip-gram model is found to operate with better-than-chance accuracy and there is a strong positive relationship (phi coefficient = 0.61) between the model’s classification and human judgement of the ranked paraphrases. This study lends credence to the viability of modelling verbal metonymy through computational methods based on distributional semantics.
Tasks
Published	2017-09-18
URL	http://arxiv.org/abs/1709.06162v1
PDF	http://arxiv.org/pdf/1709.06162v1.pdf
PWC	https://paperswithcode.com/paper/paraphrasing-verbal-metonymy-through
Repo	https://github.com/albertomh/ug-dissertation
Framework	none

Multi-Context Attention for Human Pose Estimation


Title	Multi-Context Attention for Human Pose Estimation
Authors	Xiao Chu, Wei Yang, Wanli Ouyang, Cheng Ma, Alan L. Yuille, Xiaogang Wang
Abstract	In this paper, we propose to incorporate convolutional neural networks with a multi-context attention mechanism into an end-to-end framework for human pose estimation. We adopt stacked hourglass networks to generate attention maps from features at multiple resolutions with various semantics. The Conditional Random Field (CRF) is utilized to model the correlations among neighboring regions in the attention map. We further combine the holistic attention model, which focuses on the global consistency of the full human body, and the body part attention model, which focuses on the detailed description for different body parts. Hence our model has the ability to focus on different granularity from local salient regions to global semantic-consistent spaces. Additionally, we design novel Hourglass Residual Units (HRUs) to increase the receptive field of the network. These units are extensions of residual units with a side branch incorporating filters with larger receptive fields, hence features with various scales are learned and combined within the HRUs. The effectiveness of the proposed multi-context attention mechanism and the hourglass residual units is evaluated on two widely used human pose estimation benchmarks. Our approach outperforms all existing methods on both benchmarks over all the body parts.
Tasks	Pose Estimation
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07432v1
PDF	http://arxiv.org/pdf/1702.07432v1.pdf
PWC	https://paperswithcode.com/paper/multi-context-attention-for-human-pose
Repo	https://github.com/wbenbihi/hourglasstensorlfow
Framework	tf

Real-time deep hair matting on mobile devices


Title	Real-time deep hair matting on mobile devices
Authors	Alex Levinshtein, Cheng Chang, Edmund Phung, Irina Kezele, Wenzhangzhi Guo, Parham Aarabi
Abstract	Augmented reality is an emerging technology in many application domains. Among them is the beauty industry, where live virtual try-on of beauty products is of great importance. In this paper, we address the problem of live hair color augmentation. To achieve this goal, hair needs to be segmented quickly and accurately. We show how a modified MobileNet CNN architecture can be used to segment the hair in real-time. Instead of training this network using large amounts of accurate segmentation data, which is difficult to obtain, we use crowd sourced hair segmentation data. While such data is much simpler to obtain, the segmentations there are noisy and coarse. Despite this, we show how our system can produce accurate and fine-detailed hair mattes, while running at over 30 fps on an iPad Pro tablet.
Tasks
Published	2017-12-19
URL	http://arxiv.org/abs/1712.07168v2
PDF	http://arxiv.org/pdf/1712.07168v2.pdf
PWC	https://paperswithcode.com/paper/real-time-deep-hair-matting-on-mobile-devices
Repo	https://github.com/jtiger958/hair-segmentation-pytorch
Framework	pytorch

Information-Flow Matting


Title	Information-Flow Matting
Authors	Yağız Aksoy, Tunç Ozan Aydın, Marc Pollefeys
Abstract	We present a novel, purely affinity-based natural image matting algorithm. Our method relies on carefully defined pixel-to-pixel connections that enable effective use of information available in the image. We control the information flow from the known-opacity regions into the unknown region, as well as within the unknown region itself, by utilizing multiple definitions of pixel affinities. Among other forms of information flow, we introduce color-mixture flow, which builds upon local linear embedding and effectively encapsulates the relation between different pixel opacities. Our resulting novel linear system formulation can be solved in closed-form and is robust against several fundamental challenges of natural matting such as holes and remote intricate structures. While our method is primarily designed as a standalone matting tool, we show that it can also be used for regularizing mattes obtained by sampling-based methods. The formulation is also extended to layer color estimation and we show that the use of multiple channels of flow increases the layer color quality. We also demonstrate our performance in green-screen keying and analyze the characteristics of the utilized affinities.
Tasks	Image Matting
Published	2017-07-17
URL	http://arxiv.org/abs/1707.05055v2
PDF	http://arxiv.org/pdf/1707.05055v2.pdf
PWC	https://paperswithcode.com/paper/designing-effective-inter-pixel-information
Repo	https://github.com/yaksoy/AffinityBasedMattingToolbox
Framework	none

Integral Human Pose Regression


Title	Integral Human Pose Regression
Authors	Xiao Sun, Bin Xiao, Fangyin Wei, Shuang Liang, Yichen Wei
Abstract	State-of-the-art human pose estimation methods are based on heat map representation. In spite of the good performance, the representation has a few issues in nature, such as not differentiable and quantization error. This work shows that a simple integral operation relates and unifies the heat map representation and joint regression, thus avoiding the above issues. It is differentiable, efficient, and compatible with any heat map based methods. Its effectiveness is convincingly validated via comprehensive ablation experiments under various settings, specifically on 3D pose estimation, for the first time.
Tasks	3D Pose Estimation, Pose Estimation, Quantization
Published	2017-11-22
URL	http://arxiv.org/abs/1711.08229v4
PDF	http://arxiv.org/pdf/1711.08229v4.pdf
PWC	https://paperswithcode.com/paper/integral-human-pose-regression
Repo	https://github.com/strawberryfg/c2f-3dhm-human-caffe
Framework	torch

Future Frame Prediction for Anomaly Detection – A New Baseline


Title	Future Frame Prediction for Anomaly Detection – A New Baseline
Authors	Wen Liu, Weixin Luo, Dongze Lian, Shenghua Gao
Abstract	Anomaly detection in videos refers to the identification of events that do not conform to expected behavior. However, almost all existing methods tackle the problem by minimizing the reconstruction errors of training data, which cannot guarantee a larger reconstruction error for an abnormal event. In this paper, we propose to tackle the anomaly detection problem within a video prediction framework. To the best of our knowledge, this is the first work that leverages the difference between a predicted future frame and its ground truth to detect an abnormal event. To predict a future frame with higher quality for normal events, other than the commonly used appearance (spatial) constraints on intensity and gradient, we also introduce a motion (temporal) constraint in video prediction by enforcing the optical flow between predicted frames and ground truth frames to be consistent, and this is the first work that introduces a temporal constraint into the video prediction task. Such spatial and motion constraints facilitate the future frame prediction for normal events, and consequently facilitate to identify those abnormal events that do not conform the expectation. Extensive experiments on both a toy dataset and some publicly available datasets validate the effectiveness of our method in terms of robustness to the uncertainty in normal events and the sensitivity to abnormal events.
Tasks	Anomaly Detection, Optical Flow Estimation, Video Prediction
Published	2017-12-28
URL	http://arxiv.org/abs/1712.09867v3
PDF	http://arxiv.org/pdf/1712.09867v3.pdf
PWC	https://paperswithcode.com/paper/future-frame-prediction-for-anomaly-detection
Repo	https://github.com/stevenliuwen/ano_pred_cvpr2018
Framework	tf

Deep Reinforcement Learning for List-wise Recommendations


Title	Deep Reinforcement Learning for List-wise Recommendations
Authors	Xiangyu Zhao, Liang Zhang, Long Xia, Zhuoye Ding, Dawei Yin, Jiliang Tang
Abstract	Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users’ personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learning (RL) to automatically learn the optimal strategies via recommending trial-and-error items and receiving reinforcements of these items from users’ feedbacks. In particular, we introduce an online user-agent interacting environment simulator, which can pre-train and evaluate model parameters offline before applying the model online. Moreover, we validate the importance of list-wise recommendations during the interactions between users and agent, and develop a novel approach to incorporate them into the proposed framework LIRD for list-wide recommendations. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.
Tasks	Recommendation Systems
Published	2017-12-30
URL	https://arxiv.org/abs/1801.00209v3
PDF	https://arxiv.org/pdf/1801.00209v3.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-for-list-wise
Repo	https://github.com/xuyuandong/simple-ddpg
Framework	tf

Image Super-resolution via Feature-augmented Random Forest


Title	Image Super-resolution via Feature-augmented Random Forest
Authors	Hailiang Li, Kin-Man Lam, Miaohui Wang
Abstract	Recent random-forest (RF)-based image super-resolution approaches inherit some properties from dictionary-learning-based algorithms, but the effectiveness of the properties in RF is overlooked in the literature. In this paper, we present a novel feature-augmented random forest (FARF) for image super-resolution, where the conventional gradient-based features are augmented with gradient magnitudes and different feature recipes are formulated on different stages in an RF. The advantages of our method are that, firstly, the dictionary-learning-based features are enhanced by adding gradient magnitudes, based on the observation that the non-linear gradient magnitude are with highly discriminative property. Secondly, generalized locality-sensitive hashing (LSH) is used to replace principal component analysis (PCA) for feature dimensionality reduction and original high-dimensional features are employed, instead of the compressed ones, for the leaf-nodes’ regressors, since regressors can benefit from higher dimensional features. This original-compressed coupled feature sets scheme unifies the unsupervised LSH evaluation on both image super-resolution and content-based image retrieval (CBIR). Finally, we present a generalized weighted ridge regression (GWRR) model for the leaf-nodes’ regressors. Experiment results on several public benchmark datasets show that our FARF method can achieve an average gain of about 0.3 dB, compared to traditional RF-based methods. Furthermore, a fine-tuned FARF model can compare to or (in many cases) outperform some recent stateof-the-art deep-learning-based algorithms.
Tasks	Content-Based Image Retrieval, Dictionary Learning, Dimensionality Reduction, Image Retrieval, Image Super-Resolution, Super-Resolution
Published	2017-12-14
URL	http://arxiv.org/abs/1712.05248v1
PDF	http://arxiv.org/pdf/1712.05248v1.pdf
PWC	https://paperswithcode.com/paper/image-super-resolution-via-feature-augmented
Repo	https://github.com/HarleyHK/FARF
Framework	none

An introduction to Topological Data Analysis: fundamental and practical aspects for data scientists


Title	An introduction to Topological Data Analysis: fundamental and practical aspects for data scientists
Authors	Frédéric Chazal, Bertrand Michel
Abstract	Topological Data Analysis (tda) is a recent and fast growing eld providing a set of new topological and geometric tools to infer relevant features for possibly complex data. This paper is a brief introduction, through a few selected topics, to basic fundamental and practical aspects of tda for non experts. 1 Introduction and motivation Topological Data Analysis (tda) is a recent eld that emerged from various works in applied (algebraic) topology and computational geometry during the rst decade of the century. Although one can trace back geometric approaches for data analysis quite far in the past, tda really started as a eld with the pioneering works of Edelsbrunner et al. (2002) and Zomorodian and Carlsson (2005) in persistent homology and was popularized in a landmark paper in 2009 Carlsson (2009). tda is mainly motivated by the idea that topology and geometry provide a powerful approach to infer robust qualitative, and sometimes quantitative, information about the structure of data-see, e.g. Chazal (2017). tda aims at providing well-founded mathematical, statistical and algorithmic methods to infer, analyze and exploit the complex topological and geometric structures underlying data that are often represented as point clouds in Euclidean or more general metric spaces. During the last few years, a considerable eort has been made to provide robust and ecient data structures and algorithms for tda that are now implemented and available and easy to use through standard libraries such as the Gudhi library (C++ and Python) Maria et al. (2014) and its R software interface Fasy et al. (2014a). Although it is still rapidly evolving, tda now provides a set of mature and ecient tools that can be used in combination or complementary to other data sciences tools. The tdapipeline. tda has recently known developments in various directions and application elds. There now exist a large variety of methods inspired by topological and geometric approaches. Providing a complete overview of all these existing approaches is beyond the scope of this introductory survey. However, most of them rely on the following basic and standard pipeline that will serve as the backbone of this paper: 1. The input is assumed to be a nite set of points coming with a notion of distance-or similarity between them. This distance can be induced by the metric in the ambient space (e.g. the Euclidean metric when the data are embedded in R d) or come as an intrinsic metric dened by a pairwise distance matrix. The denition of the metric on the data is usually given as an input or guided by the application. It is however important to notice that the choice of the metric may be critical to reveal interesting topological and geometric features of the data.
Tasks	Topological Data Analysis
Published	2017-10-11
URL	http://arxiv.org/abs/1710.04019v1
PDF	http://arxiv.org/pdf/1710.04019v1.pdf
PWC	https://paperswithcode.com/paper/an-introduction-to-topological-data-analysis
Repo	https://github.com/qthinhbui/TDA-Biomedicine
Framework	none

Supervised Infinite Feature Selection


Title	Supervised Infinite Feature Selection
Authors	Sadegh Eskandari, Emre Akbas
Abstract	In this paper, we present a new feature selection method that is suitable for both unsupervised and supervised problems. We build upon the recently proposed Infinite Feature Selection (IFS) method where feature subsets of all sizes (including infinity) are considered. We extend IFS in two ways. First, we propose a supervised version of it. Second, we propose new ways of forming the feature adjacency matrix that perform better for unsupervised problems. We extensively evaluate our methods on many benchmark datasets, including large image-classification datasets (PASCAL VOC), and show that our methods outperform both the IFS and the widely used “minimum-redundancy maximum-relevancy (mRMR)” feature selection algorithm.
Tasks	Feature Selection, Image Classification
Published	2017-04-09
URL	http://arxiv.org/abs/1704.02665v3
PDF	http://arxiv.org/pdf/1704.02665v3.pdf
PWC	https://paperswithcode.com/paper/supervised-infinite-feature-selection
Repo	https://github.com/Sadegh28/SIFS
Framework	none

Sketching Linear Classifiers over Data Streams


Title	Sketching Linear Classifiers over Data Streams
Authors	Kai Sheng Tai, Vatsal Sharan, Peter Bailis, Gregory Valiant
Abstract	We introduce a new sub-linear space sketch—the Weight-Median Sketch—for learning compressed linear classifiers over data streams while supporting the efficient recovery of large-magnitude weights in the model. This enables memory-limited execution of several statistical analyses over streams, including online feature selection, streaming data explanation, relative deltoid detection, and streaming estimation of pointwise mutual information. Unlike related sketches that capture the most frequently-occurring features (or items) in a data stream, the Weight-Median Sketch captures the features that are most discriminative of one stream (or class) compared to another. The Weight-Median Sketch adopts the core data structure used in the Count-Sketch, but, instead of sketching counts, it captures sketched gradient updates to the model parameters. We provide a theoretical analysis that establishes recovery guarantees for batch and online learning, and demonstrate empirical improvements in memory-accuracy trade-offs over alternative memory-budgeted methods, including count-based sketches and feature hashing.
Tasks	Feature Selection
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02305v2
PDF	http://arxiv.org/pdf/1711.02305v2.pdf
PWC	https://paperswithcode.com/paper/sketching-linear-classifiers-over-data
Repo	https://github.com/stanford-futuredata/wmsketch
Framework	none

Hierarchical Text Generation and Planning for Strategic Dialogue


Title	Hierarchical Text Generation and Planning for Strategic Dialogue
Authors	Denis Yarats, Mike Lewis
Abstract	End-to-end models for goal-orientated dialogue are challenging to train, because linguistic and strategic aspects are entangled in latent state vectors. We introduce an approach to learning representations of messages in dialogues by maximizing the likelihood of subsequent sentences and actions, which decouples the semantics of the dialogue utterance from its linguistic realization. We then use these latent sentence representations for hierarchical language generation, planning and reinforcement learning. Experiments show that our approach increases the end-task reward achieved by the model, improves the effectiveness of long-term planning using rollouts, and allows self-play reinforcement learning to improve decision making without diverging from human language. Our hierarchical latent-variable model outperforms previous work both linguistically and strategically.
Tasks	Decision Making, Text Generation
Published	2017-12-15
URL	http://arxiv.org/abs/1712.05846v2
PDF	http://arxiv.org/pdf/1712.05846v2.pdf
PWC	https://paperswithcode.com/paper/hierarchical-text-generation-and-planning-for
Repo	https://github.com/facebookresearch/end-to-end-negotiator
Framework	pytorch

DeepFaceLIFT: Interpretable Personalized Models for Automatic Estimation of Self-Reported Pain


Title	DeepFaceLIFT: Interpretable Personalized Models for Automatic Estimation of Self-Reported Pain
Authors	Dianbo Liu, Fengjiao Peng, Andrew Shea, Ognjen, Rudovic, Rosalind Picard
Abstract	Previous research on automatic pain estimation from facial expressions has focused primarily on “one-size-fits-all” metrics (such as PSPI). In this work, we focus on directly estimating each individual’s self-reported visual-analog scale (VAS) pain metric, as this is considered the gold standard for pain measurement. The VAS pain score is highly subjective and context-dependent, and its range can vary significantly among different persons. To tackle these issues, we propose a novel two-stage personalized model, named DeepFaceLIFT, for automatic estimation of VAS. This model is based on (1) Neural Network and (2) Gaussian process regression models, and is used to personalize the estimation of self-reported pain via a set of hand-crafted personal features and multi-task learning. We show on the benchmark dataset for pain analysis (The UNBC-McMaster Shoulder Pain Expression Archive) that the proposed personalized model largely outperforms the traditional, unpersonalized models: the intra-class correlation improves from a baseline performance of 19% to a personalized performance of 35% while also providing confidence in the model\textquotesingle s estimates – in contrast to existing models for the target task. Additionally, DeepFaceLIFT automatically discovers the pain-relevant facial regions for each person, allowing for an easy interpretation of the pain-related facial cues.
Tasks	Multi-Task Learning
Published	2017-08-09
URL	http://arxiv.org/abs/1708.04670v1
PDF	http://arxiv.org/pdf/1708.04670v1.pdf
PWC	https://paperswithcode.com/paper/deepfacelift-interpretable-personalized
Repo	https://github.com/jcheong0428/Papers
Framework	none