January 25, 2020

3091 words 15 mins read

Paper Group ANR 1648

A Stochastic Proximal Point Algorithm for Saddle-Point Problems. 3D Graph Embedding Learning with a Structure-aware Loss Function for Point Cloud Semantic Instance Segmentation. Few-shot Learning with Contextual Cueing for Object Recognition in Complex Scenes. Space-adaptive anisotropic bivariate Laplacian regularization for image restoration. Sola …

A Stochastic Proximal Point Algorithm for Saddle-Point Problems


Title	A Stochastic Proximal Point Algorithm for Saddle-Point Problems
Authors	Luo Luo, Cheng Chen, Yujun Li, Guangzeng Xie, Zhihua Zhang
Abstract	We consider saddle point problems which objective functions are the average of $n$ strongly convex-concave individual components. Recently, researchers exploit variance reduction methods to solve such problems and achieve linear-convergence guarantees. However, these methods have a slow convergence when the condition number of the problem is very large. In this paper, we propose a stochastic proximal point algorithm, which accelerates the variance reduction method SAGA for saddle point problems. Compared with the catalyst framework, our algorithm reduces a logarithmic term of condition number for the iteration complexity. We adopt our algorithm to policy evaluation and the empirical results show that our method is much more efficient than state-of-the-art methods.
Tasks
Published	2019-09-13
URL	https://arxiv.org/abs/1909.06946v1
PDF	https://arxiv.org/pdf/1909.06946v1.pdf
PWC	https://paperswithcode.com/paper/a-stochastic-proximal-point-algorithm-for
Repo
Framework

3D Graph Embedding Learning with a Structure-aware Loss Function for Point Cloud Semantic Instance Segmentation


Title	3D Graph Embedding Learning with a Structure-aware Loss Function for Point Cloud Semantic Instance Segmentation
Authors	Zhidong Liang, Ming Yang, Chunxiang Wang
Abstract	This paper introduces a novel approach for 3D semantic instance segmentation on point clouds. A 3D convolutional neural network called submanifold sparse convolutional network is used to generate semantic predictions and instance embeddings simultaneously. To obtain discriminative embeddings for each 3D instance, a structure-aware loss function is proposed which considers both the structure information and the embedding information. To get more consistent embeddings for each 3D instance, attention-based k nearest neighbour (KNN) is proposed to assign different weights for different neighbours. Based on the attention-based KNN, we add a graph convolutional network after the sparse convolutional network to get refined embeddings. Our network can be trained end-to-end. A simple mean-shift algorithm is utilized to cluster refined embeddings to get final instance predictions. As a result, our framework can output both the semantic prediction and the instance prediction. Experiments show that our approach outperforms all state-of-art methods on ScanNet benchmark and NYUv2 dataset.
Tasks	3D Semantic Instance Segmentation, Graph Embedding, Instance Segmentation, Semantic Segmentation
Published	2019-02-14
URL	http://arxiv.org/abs/1902.05247v1
PDF	http://arxiv.org/pdf/1902.05247v1.pdf
PWC	https://paperswithcode.com/paper/3d-graph-embedding-learning-with-a-structure
Repo
Framework

Few-shot Learning with Contextual Cueing for Object Recognition in Complex Scenes


Title	Few-shot Learning with Contextual Cueing for Object Recognition in Complex Scenes
Authors	Mathieu Pagé Fortin, Brahim Chaib-draa
Abstract	Few-shot Learning aims to recognize new concepts from a small number of training examples. Recent work mainly tackle this problem by improving visual features, feature transfer and meta-training algorithms. In this work, we propose to explore a complementary direction by using scene context semantics to learn and recognize new concepts more easily. Whereas a few visual examples cannot cover all intra-class variations, contextual cueing offers a complementary signal to classify instances with unseen features or ambiguous objects. More specifically, we propose a Class-conditioned Context Attention Module (CCAM) that learns to weight the most important context elements while learning a particular concept. We additionally propose a flexible gating mechanism to ground visual class representations in context semantics. We conduct extensive experiments on Visual Genome dataset, and we show that compared to a visual-only baseline, our model improves top-1 accuracy by 20.47% and 9.13% in 5-way 1-shot and 5-way 5-shot, respectively; and by 20.42% and 12.45% in 20-way 1-shot and 20-way 5-shot, respectively.
Tasks	Few-Shot Learning, Object Recognition
Published	2019-12-13
URL	https://arxiv.org/abs/1912.06679v2
PDF	https://arxiv.org/pdf/1912.06679v2.pdf
PWC	https://paperswithcode.com/paper/few-shot-learning-with-contextual-cueing-for
Repo
Framework

Space-adaptive anisotropic bivariate Laplacian regularization for image restoration


Title	Space-adaptive anisotropic bivariate Laplacian regularization for image restoration
Authors	Luca Calatroni, Alessandro Lanza, Monica Pragliola, Fiorella Sgallari
Abstract	In this paper we present a new regularization term for variational image restoration which can be regarded as a space-variant anisotropic extension of the classical isotropic Total Variation (TV) regularizer. The proposed regularizer comes from the statistical assumption that the gradients of the target image distribute locally according to space-variant bivariate Laplacian distributions. The highly flexible variational structure of the corresponding regularizer encodes several free parameters which hold the potential for faithfully modelling the local geometry in the image and describing local orientation preferences. For an automatic estimation of such parameters, we design a robust maximum likelihood approach and report results on its reliability on synthetic data and natural images. A minimization algorithm based on the Alternating Direction Method of Multipliers (ADMM) is presented for the efficient numerical solution of the proposed variational model. Some experimental results are reported which demonstrate the high-quality of restorations achievable by the proposed model, in particular with respect to classical Total Variation regularization.
Tasks	Image Restoration
Published	2019-08-02
URL	https://arxiv.org/abs/1908.00801v1
PDF	https://arxiv.org/pdf/1908.00801v1.pdf
PWC	https://paperswithcode.com/paper/space-adaptive-anisotropic-bivariate
Repo
Framework

Solar Image Restoration with the Cycle-GAN Based on Multi-Fractal Properties of Texture Features


Title	Solar Image Restoration with the Cycle-GAN Based on Multi-Fractal Properties of Texture Features
Authors	Peng Jia, Yi Huang, Bojun Cai, Dongmei Cai
Abstract	Texture is one of the most obvious characteristics in solar images and it is normally described by texture features. Because textures from solar images of the same wavelength are similar, we assume texture features of solar images are multi-fractals. Based on this assumption, we propose a pure data-based image restoration method: with several high resolution solar images as references, we use the Cycle-Consistent Adversarial Network to restore burred images of the same steady physical process, in the same wavelength obtained by the same telescope. We test our method with simulated and real observation data and find that our method can improve the spatial resolution of solar images, without loss of any frames. Because our method does not need paired training set or additional instruments, it can be used as a post-processing method for solar images obtained by either seeing limited telescopes or telescopes with ground layer adaptive optic system.
Tasks	Image Restoration
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12192v2
PDF	https://arxiv.org/pdf/1907.12192v2.pdf
PWC	https://paperswithcode.com/paper/solar-image-restoration-with-the-cycle-gan
Repo
Framework

Stacked Wasserstein Autoencoder


Title	Stacked Wasserstein Autoencoder
Authors	Wenju Xu, Shawn Keshmiri, Guanghui Wang
Abstract	Approximating distributions over complicated manifolds, such as natural images, are conceptually attractive. The deep latent variable model, trained using variational autoencoders and generative adversarial networks, is now a key technique for representation learning. However, it is difficult to unify these two models for exact latent-variable inference and parallelize both reconstruction and sampling, partly due to the regularization under the latent variables, to match a simple explicit prior distribution. These approaches are prone to be oversimplified, and can only characterize a few modes of the true distribution. Based on the recently proposed Wasserstein autoencoder (WAE) with a new regularization as an optimal transport. The paper proposes a stacked Wasserstein autoencoder (SWAE) to learn a deep latent variable model. SWAE is a hierarchical model, which relaxes the optimal transport constraints at two stages. At the first stage, the SWAE flexibly learns a representation distribution, i.e., the encoded prior; and at the second stage, the encoded representation distribution is approximated with a latent variable model under the regularization encouraging the latent distribution to match the explicit prior. This model allows us to generate natural textual outputs as well as perform manipulations in the latent space to induce changes in the output space. Both quantitative and qualitative results demonstrate the superior performance of SWAE compared with the state-of-the-art approaches in terms of faithful reconstruction and generation quality.
Tasks	Representation Learning
Published	2019-10-04
URL	https://arxiv.org/abs/1910.02560v1
PDF	https://arxiv.org/pdf/1910.02560v1.pdf
PWC	https://paperswithcode.com/paper/stacked-wasserstein-autoencoder
Repo
Framework

Low-pass filtering as Bayesian inference


Title	Low-pass filtering as Bayesian inference
Authors	Cristobal Valenzuela, Felipe Tobar
Abstract	We propose a Bayesian nonparametric method for low-pass filtering that can naturally handle unevenly-sampled and noise-corrupted observations. The proposed model is constructed as a latent-factor model for time series, where the latent factors are Gaussian processes with non-overlapping spectra. With this construction, the low-pass version of the time series can be identified as the low-frequency latent component, and therefore it can be found by means of Bayesian inference. We show that the model admits exact training and can be implemented with minimal numerical approximations. Finally, the proposed model is validated against standard linear filters on synthetic and real-world time series.
Tasks	Bayesian Inference, Gaussian Processes, Time Series
Published	2019-02-09
URL	http://arxiv.org/abs/1902.03427v1
PDF	http://arxiv.org/pdf/1902.03427v1.pdf
PWC	https://paperswithcode.com/paper/low-pass-filtering-as-bayesian-inference
Repo
Framework

Production Ranking Systems: A Review


Title	Production Ranking Systems: A Review
Authors	Murium Iqbal, Nishan Subedi, Kamelia Aryafar
Abstract	The problem of ranking is a multi-billion dollar problem. In this paper we present an overview of several production quality ranking systems. We show that due to conflicting goals of employing the most effective machine learning models and responding to users in real time, ranking systems have evolved into a system of systems, where each subsystem can be viewed as a component layer. We view these layers as being data processing, representation learning, candidate selection and online inference. Each layer employs different algorithms and tools, with every end-to-end ranking system spanning multiple architectures. Our goal is to familiarize the general audience with a working knowledge of ranking at scale, the tools and algorithms employed and the challenges introduced by adopting a layered approach.
Tasks	Representation Learning
Published	2019-07-24
URL	https://arxiv.org/abs/1907.12372v1
PDF	https://arxiv.org/pdf/1907.12372v1.pdf
PWC	https://paperswithcode.com/paper/production-ranking-systems-a-review
Repo
Framework

Distributed Edge Caching via Reinforcement Learning in Fog Radio Access Networks


Title	Distributed Edge Caching via Reinforcement Learning in Fog Radio Access Networks
Authors	Liuyang Lu, Yanxiang Jiang, Mehdi Bennis, Zhiguo Ding, Fu-Chun Zheng, Xiaohu You
Abstract	In this paper, the distributed edge caching problem in fog radio access networks (F-RANs) is investigated. By considering the unknown spatio-temporal content popularity and user preference, a user request model based on hidden Markov process is proposed to characterize the fluctuant spatio-temporal traffic demands in F-RANs. Then, the Q-learning method based on the reinforcement learning (RL) framework is put forth to seek the optimal caching policy in a distributed manner, which enables fog access points (F-APs) to learn and track the potential dynamic process without extra communications cost. Furthermore, we propose a more efficient Q-learning method with value function approximation (Q-VFA-learning) to reduce complexity and accelerate convergence. Simulation results show that the performance of our proposed method is superior to those of the traditional methods.
Tasks	Q-Learning
Published	2019-02-27
URL	http://arxiv.org/abs/1902.10574v1
PDF	http://arxiv.org/pdf/1902.10574v1.pdf
PWC	https://paperswithcode.com/paper/distributed-edge-caching-via-reinforcement
Repo
Framework

Throttling Malware Families in 2D


Title	Throttling Malware Families in 2D
Authors	Mohamed Nassar, Haidar Safa
Abstract	Malicious software are categorized into families based on their static and dynamic characteristics, infection methods, and nature of threat. Visual exploration of malware instances and families in a low dimensional space helps in giving a first overview about dependencies and relationships among these instances, detecting their groups and isolating outliers. Furthermore, visual exploration of different sets of features is useful in assessing the quality of these sets to carry a valid abstract representation, which can be later used in classification and clustering algorithms to achieve a high accuracy. In this paper, we investigate one of the best dimensionality reduction techniques known as t-SNE to reduce the malware representation from a high dimensional space consisting of thousands of features to a low dimensional space. We experiment with different feature sets and depict malware clusters in 2-D. Surprisingly, t-SNE does not only provide nice 2-D drawings, but also dramatically increases the generalization power of SVM classifiers. Moreover, obtained results showed that cross-validation accuracy is much better using the 2-D embedded representation of samples than using the original high-dimensional representation.
Tasks	Dimensionality Reduction
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10590v1
PDF	http://arxiv.org/pdf/1901.10590v1.pdf
PWC	https://paperswithcode.com/paper/throttling-malware-families-in-2d
Repo
Framework

ECG Identification under Exercise and Rest Situations via Various Learning Methods


Title	ECG Identification under Exercise and Rest Situations via Various Learning Methods
Authors	Zihan Wang, Yaoguang Li, Wei Cui
Abstract	As the advancement of information security, human recognition as its core technology, has absorbed an increasing amount of attention in the past few years. A myriad of biometric features including fingerprint, face, iris, have been applied to security systems, which are occasionally considered vulnerable to forgery and spoofing attacks. Due to the difficulty of being fabricated, electrocardiogram (ECG) has attracted much attention. Though many works have shown the excellent human identification provided by ECG, most current ECG human identification (ECGID) researches only focus on rest situation. In this manuscript, we overcome the oversimplification of previous researches and evaluate the performance under both exercise and rest situations, especially the influence of exercise on ECGID. By applying various existing learning methods to our ECG dataset, we find that current methods which can well support the identification of individuals under rests, do not suffice to present satisfying ECGID performance under exercise situations, therefore exposing the deficiency of existing ECG identification methods.
Tasks
Published	2019-05-11
URL	https://arxiv.org/abs/1905.04442v1
PDF	https://arxiv.org/pdf/1905.04442v1.pdf
PWC	https://paperswithcode.com/paper/ecg-identification-under-exercise-and-rest
Repo
Framework

Who Will Win It? An In-game Win Probability Model for Football


Title	Who Will Win It? An In-game Win Probability Model for Football
Authors	Pieter Robberechts, Jan Van Haaren, Jesse Davis
Abstract	In-game win probability is a statistical metric that provides a sports team’s likelihood of winning at any given point in a game, based on the performance of historical teams in the same situation. In-game win-probability models have been extensively studied in baseball, basketball and American football. These models serve as a tool to enhance the fan experience, evaluate in game-decision making and measure the risk-reward balance for coaching decisions. In contrast, they have received less attention in association football, because its low-scoring nature makes it far more challenging to analyze. In this paper, we build an in-game win probability model for football. Specifically, we first show that porting existing approaches, both in terms of the predictive models employed and the features considered, does not yield good in-game win-probability estimates for football. Second, we introduce our own Bayesian statistical model that utilizes a set of eight variables to predict the running win, tie and loss probabilities for the home team. We train our model using event data from the last four seasons of the major European football competitions. Our results indicate that our model provides well-calibrated probabilities. Finally, we elaborate on two use cases for our win probability metric: enhancing the fan experience and evaluating performance in crucial situations.
Tasks	Decision Making
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05029v1
PDF	https://arxiv.org/pdf/1906.05029v1.pdf
PWC	https://paperswithcode.com/paper/who-will-win-it-an-in-game-win-probability
Repo
Framework

AI-Skin : Skin Disease Recognition based on Self-learning and Wide Data Collection through a Closed Loop Framework


Title	AI-Skin : Skin Disease Recognition based on Self-learning and Wide Data Collection through a Closed Loop Framework
Authors	Min Chen, Ping Zhou, Di Wu, Long Hu, Mohammad Mehedi Hassan, Atif Alamri
Abstract	There are a lot of hidden dangers in the change of human skin conditions, such as the sunburn caused by long-time exposure to ultraviolet radiation, which not only has aesthetic impact causing psychological depression and lack of self-confidence, but also may even be life-threatening due to skin canceration. Current skin disease researches adopt the auto-classification system for improving the accuracy rate of skin disease classification. However, the excessive dependence on the image sample database is unable to provide individualized diagnosis service for different population groups. To overcome this problem, a medical AI framework based on data width evolution and self-learning is put forward in this paper to provide skin disease medical service meeting the requirement of real time, extendibility and individualization. First, the wide collection of data in the close-loop information flow of user and remote medical data center is discussed. Next, a data set filter algorithm based on information entropy is given, to lighten the load of edge node and meanwhile improve the learning ability of remote cloud analysis model. In addition, the framework provides an external algorithm load module, which can be compatible with the application requirements according to the model selected. Three kinds of deep learning model, i.e. LeNet-5, AlexNet and VGG16, are loaded and compared, which have verified the universality of the algorithm load module. The experiment platform for the proposed real-time, individualized and extensible skin disease recognition system is built. And the system’s computation and communication delay under the interaction scenario between tester and remote data center are analyzed. It is demonstrated that the system we put forward is reliable and effective.
Tasks
Published	2019-06-05
URL	https://arxiv.org/abs/1906.01895v1
PDF	https://arxiv.org/pdf/1906.01895v1.pdf
PWC	https://paperswithcode.com/paper/ai-skin-skin-disease-recognition-based-on
Repo
Framework

Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora


Title	Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora
Authors	Hieu-Thi Luong, Xin Wang, Junichi Yamagishi, Nobuyuki Nishizawa
Abstract	When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead. Many studies have shown that neural multi-speaker TTS model trained with a small amount data from multiple speakers combined can generate synthetic speech with better quality and stability than a speaker-dependent one. However when the amount of data from each speaker is highly unbalanced, the best approach to make use of the excessive data remains unknown. Our experiments showed that simply combining all available data from every speaker to train a multi-speaker model produces better than or at least similar performance to its speaker-dependent counterpart. Moreover by using an ensemble multi-speaker model, in which each subsystem is trained on a subset of available data, we can further improve the quality of the synthetic speech especially for underrepresented speakers whose training data is limited.
Tasks
Published	2019-04-01
URL	http://arxiv.org/abs/1904.00771v2
PDF	http://arxiv.org/pdf/1904.00771v2.pdf
PWC	https://paperswithcode.com/paper/training-multi-speaker-neural-text-to-speech
Repo
Framework

Meta-learners’ learning dynamics are unlike learners’


Title	Meta-learners’ learning dynamics are unlike learners’
Authors	Neil C. Rabinowitz
Abstract	Meta-learning is a tool that allows us to build sample-efficient learning systems. Here we show that, once meta-trained, LSTM Meta-Learners aren’t just faster learners than their sample-inefficient deep learning (DL) and reinforcement learning (RL) brethren, but that they actually pursue fundamentally different learning trajectories. We study their learning dynamics on three sets of structured tasks for which the corresponding learning dynamics of DL and RL systems have been previously described: linear regression (Saxe et al., 2013), nonlinear regression (Rahaman et al., 2018; Xu et al., 2018), and contextual bandits (Schaul et al., 2019). In each case, while sample-inefficient DL and RL Learners uncover the task structure in a staggered manner, meta-trained LSTM Meta-Learners uncover almost all task structure concurrently, congruent with the patterns expected from Bayes-optimal inference algorithms. This has implications for research areas wherever the learning behaviour itself is of interest, such as safety, curriculum design, and human-in-the-loop machine learning.
Tasks	Meta-Learning, Multi-Armed Bandits
Published	2019-05-03
URL	https://arxiv.org/abs/1905.01320v1
PDF	https://arxiv.org/pdf/1905.01320v1.pdf
PWC	https://paperswithcode.com/paper/meta-learners-learning-dynamics-are-unlike
Repo
Framework