October 19, 2019

3071 words 15 mins read

Paper Group ANR 252

A Performance Evaluation of Convolutional Neural Networks for Face Anti Spoofing. Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms. Tracking Multiple Moving Objects Using Unscented Kalman Filtering Techniques. Superensemble Classifier for Improving Predictions in Imbalanced Datasets. Multi-Taskin …

A Performance Evaluation of Convolutional Neural Networks for Face Anti Spoofing


Title	A Performance Evaluation of Convolutional Neural Networks for Face Anti Spoofing
Authors	Chaitanya Nagpal, Shiv Ram Dubey
Abstract	In the current era, biometric based access control is becoming more popular due to its simplicity and ease to use by the users. It reduces the manual work of identity recognition and facilitates the automatic processing. The face is one of the most important biometric visual information that can be easily captured without user cooperation in an uncontrolled environment. Precise detection of spoofed faces should be on the high priority to make face based identity recognition and access control robust against possible attacks. The recently evolved Convolutional Neural Network (CNN) based deep learning technique has proven as one of the excellent method to deal with the visual information very effectively. The CNN learns the hierarchical features at intermediate layers automatically from the data. Several CNN based methods such as Inception and ResNet have shown outstanding performance for image classification problem. This paper does a performance evaluation of CNNs for face anti-spoofing. The Inception and ResNet CNN architectures are used in this study. The results are computed over benchmark MSU Mobile Face Spoofing Database. The experiments are done by considering the different aspects such as the depth of the model, random weight initialization vs weight transfer, fine tuning vs training from scratch and different learning rate. The favorable results are obtained using these CNN architectures for face anti-spoofing in different settings.
Tasks	Face Anti-Spoofing, Image Classification
Published	2018-05-08
URL	http://arxiv.org/abs/1805.04176v2
PDF	http://arxiv.org/pdf/1805.04176v2.pdf
PWC	https://paperswithcode.com/paper/a-performance-evaluation-of-convolutional
Repo
Framework

Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms


Title	Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms
Authors	Junhong Lin, Volkan Cevher
Abstract	We study generalization properties of distributed algorithms in the setting of nonparametric regression over a reproducing kernel Hilbert space (RKHS). We first investigate distributed stochastic gradient methods (SGM), with mini-batches and multi-passes over the data. We show that optimal generalization error bounds can be retained for distributed SGM provided that the partition level is not too large. We then extend our results to spectral-regularization algorithms (SRA), including kernel ridge regression (KRR), kernel principal component analysis, and gradient methods. Our results are superior to the state-of-the-art theory. Particularly, our results show that distributed SGM has a smaller theoretical computational complexity, compared with distributed KRR and classic SGM. Moreover, even for non-distributed SRA, they provide the first optimal, capacity-dependent convergence rates, considering the case that the regression function may not be in the RKHS.
Tasks
Published	2018-01-22
URL	http://arxiv.org/abs/1801.07226v2
PDF	http://arxiv.org/pdf/1801.07226v2.pdf
PWC	https://paperswithcode.com/paper/optimal-convergence-for-distributed-learning
Repo
Framework

Tracking Multiple Moving Objects Using Unscented Kalman Filtering Techniques


Title	Tracking Multiple Moving Objects Using Unscented Kalman Filtering Techniques
Authors	Xi Chen, Xiao Wang, Jianhua Xuan
Abstract	It is an important task to reliably detect and track multiple moving objects for video surveillance and monitoring. However, when occlusion occurs in nonlinear motion scenarios, many existing methods often fail to continuously track multiple moving objects of interest. In this paper we propose an effective approach for detection and tracking of multiple moving objects with occlusion. Moving targets are initially detected using a simple yet efficient block matching technique, providing rough location information for multiple object tracking. More accurate location information is then estimated for each moving object by a nonlinear tracking algorithm. Considering the ambiguity caused by the occlusion among multiple moving objects, we apply an unscented Kalman filtering (UKF) technique for reliable object detection and tracking. Different from conventional Kalman filtering (KF), which cannot achieve the optimal estimation in nonlinear tracking scenarios, UKF can be used to track both linear and nonlinear motions due to the unscented transform. Further, it estimates the velocity information for each object to assist to the object detection algorithm, effectively delineating multiple moving objects of occlusion. The experimental results demonstrate that the proposed method can correctly detect and track multiple moving objects with nonlinear motion patterns and occlusions.
Tasks	Multiple Object Tracking, Object Detection, Object Tracking
Published	2018-02-05
URL	http://arxiv.org/abs/1802.01235v1
PDF	http://arxiv.org/pdf/1802.01235v1.pdf
PWC	https://paperswithcode.com/paper/tracking-multiple-moving-objects-using
Repo
Framework

Superensemble Classifier for Improving Predictions in Imbalanced Datasets


Title	Superensemble Classifier for Improving Predictions in Imbalanced Datasets
Authors	Tanujit Chakraborty, Ashis Kumar Chakraborty
Abstract	Learning from an imbalanced dataset is a tricky proposition. Because these datasets are biased towards one class, most existing classifiers tend not to perform well on minority class examples. Conventional classifiers usually aim to optimize the overall accuracy without considering the relative distribution of each class. This article presents a superensemble classifier, to tackle and improve predictions in imbalanced classification problems, that maps Hellinger distance decision trees (HDDT) into radial basis function network (RBFN) framework. Regularity conditions for universal consistency and the idea of parameter optimization of the proposed model are provided. The proposed distribution-free model can be applied for feature selection cum imbalanced classification problems. We have also provided enough numerical evidence using various real-life data sets to assess the performance of the proposed model. Its effectiveness and competitiveness with respect to different state-of-the-art models are shown.
Tasks	Feature Selection
Published	2018-10-25
URL	http://arxiv.org/abs/1810.11317v1
PDF	http://arxiv.org/pdf/1810.11317v1.pdf
PWC	https://paperswithcode.com/paper/superensemble-classifier-for-improving
Repo
Framework

Multi-Tasking Genetic Algorithm (MTGA) for Fuzzy System Optimization


Title	Multi-Tasking Genetic Algorithm (MTGA) for Fuzzy System Optimization
Authors	Dongrui Wu, Xianfeng Tan
Abstract	Multi-task learning uses auxiliary data or knowledge from relevant tasks to facilitate the learning in a new task. Multi-task optimization applies multi-task learning to optimization to study how to effectively and efficiently tackle multiple optimization problems simultaneously. Evolutionary multi-tasking, or multi-factorial optimization, is an emerging subfield of multi-task optimization, which integrates evolutionary computation and multi-task learning. This paper proposes a novel and easy-to-implement multi-tasking genetic algorithm (MTGA), which copes well with significantly different optimization tasks by estimating and using the bias among them. Comparative studies with eight state-of-the-art single- and multi-task approaches in the literature on nine benchmarks demonstrated that on average the MTGA outperformed all of them, and had lower computational cost than six of them. Based on the MTGA, a simultaneous optimization strategy for fuzzy system design is also proposed. Experiments on simultaneous optimization of type-1 and interval type-2 fuzzy logic controllers for couple-tank water level control demonstrated that the MTGA can find better fuzzy logic controllers than other approaches.
Tasks	Multi-Task Learning
Published	2018-12-15
URL	https://arxiv.org/abs/1812.06303v2
PDF	https://arxiv.org/pdf/1812.06303v2.pdf
PWC	https://paperswithcode.com/paper/multi-tasking-evolutionary-algorithm-mtea-for
Repo
Framework

Learning to Reconstruct Shapes from Unseen Classes


Title	Learning to Reconstruct Shapes from Unseen Classes
Authors	Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang, Joshua B. Tenenbaum, William T. Freeman, Jiajun Wu
Abstract	From a single image, humans are able to perceive the full 3D shape of an object by exploiting learned shape priors from everyday life. Contemporary single-image 3D reconstruction algorithms aim to solve this task in a similar fashion, but often end up with priors that are highly biased by training classes. Here we present an algorithm, Generalizable Reconstruction (GenRe), designed to capture more generic, class-agnostic shape priors. We achieve this with an inference network and training procedure that combine 2.5D representations of visible surfaces (depth and silhouette), spherical shape representations of both visible and non-visible surfaces, and 3D voxel-based representations, in a principled manner that exploits the causal structure of how 3D shapes give rise to 2D images. Experiments demonstrate that GenRe performs well on single-view shape reconstruction, and generalizes to diverse novel objects from categories not seen during training.
Tasks	3D Reconstruction
Published	2018-12-28
URL	http://arxiv.org/abs/1812.11166v1
PDF	http://arxiv.org/pdf/1812.11166v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-reconstruct-shapes-from-unseen
Repo
Framework

From Free Text to Clusters of Content in Health Records: An Unsupervised Graph Partitioning Approach


Title	From Free Text to Clusters of Content in Health Records: An Unsupervised Graph Partitioning Approach
Authors	M. Tarik Altuncu, Erik Mayer, Sophia N. Yaliraki, Mauricio Barahona
Abstract	Electronic Healthcare records contain large volumes of unstructured data in different forms. Free text constitutes a large portion of such data, yet this source of richly detailed information often remains under-used in practice because of a lack of suitable methodologies to extract interpretable content in a timely manner. Here we apply network-theoretical tools to the analysis of free text in Hospital Patient Incident reports in the English National Health Service, to find clusters of reports in an unsupervised manner and at different levels of resolution based directly on the free text descriptions contained within them. To do so, we combine recently developed deep neural network text-embedding methodologies based on paragraph vectors with multi-scale Markov Stability community detection applied to a similarity graph of documents obtained from sparsified text vector similarities. We showcase the approach with the analysis of incident reports submitted in Imperial College Healthcare NHS Trust, London. The multiscale community structure reveals levels of meaning with different resolution in the topics of the dataset, as shown by relevant descriptive terms extracted from the groups of records, as well as by comparing a posteriori against hand-coded categories assigned by healthcare personnel. Our content communities exhibit good correspondence with well-defined hand-coded categories, yet our results also provide further medical detail in certain areas as well as revealing complementary descriptors of incidents beyond the external classification. We also discuss how the method can be used to monitor reports over time and across different healthcare providers, and to detect emerging trends that fall outside of pre-existing categories.
Tasks	Community Detection, graph partitioning
Published	2018-11-14
URL	http://arxiv.org/abs/1811.05711v1
PDF	http://arxiv.org/pdf/1811.05711v1.pdf
PWC	https://paperswithcode.com/paper/from-free-text-to-clusters-of-content-in
Repo
Framework

Generating Interpretable Fuzzy Controllers using Particle Swarm Optimization and Genetic Programming


Title	Generating Interpretable Fuzzy Controllers using Particle Swarm Optimization and Genetic Programming
Authors	Daniel Hein, Steffen Udluft, Thomas A. Runkler
Abstract	Autonomously training interpretable control strategies, called policies, using pre-existing plant trajectory data is of great interest in industrial applications. Fuzzy controllers have been used in industry for decades as interpretable and efficient system controllers. In this study, we introduce a fuzzy genetic programming (GP) approach called fuzzy GP reinforcement learning (FGPRL) that can select the relevant state features, determine the size of the required fuzzy rule set, and automatically adjust all the controller parameters simultaneously. Each GP individual’s fitness is computed using model-based batch reinforcement learning (RL), which first trains a model using available system samples and subsequently performs Monte Carlo rollouts to predict each policy candidate’s performance. We compare FGPRL to an extended version of a related method called fuzzy particle swarm reinforcement learning (FPSRL), which uses swarm intelligence to tune the fuzzy policy parameters. Experiments using an industrial benchmark show that FGPRL is able to autonomously learn interpretable fuzzy policies with high control performance.
Tasks
Published	2018-04-29
URL	http://arxiv.org/abs/1804.10960v1
PDF	http://arxiv.org/pdf/1804.10960v1.pdf
PWC	https://paperswithcode.com/paper/generating-interpretable-fuzzy-controllers
Repo
Framework

Excavate Condition-invariant Space by Intrinsic Encoder


Title	Excavate Condition-invariant Space by Intrinsic Encoder
Authors	Jian Xu, Chunheng Wang, Cunzhao Shi, Baihua Xiao
Abstract	As the human, we can recognize the places across a wide range of changing environmental conditions such as those caused by weathers, seasons, and day-night cycles. We excavate and memorize the stable semantic structure of different places and scenes. For example, we can recognize tree whether the bare tree in winter or lush tree in summer. Therefore, the intrinsic features that are corresponding to specific semantic contents and condition-invariant of appearance changes can be employed to improve the performance of long-term place recognition significantly. In this paper, we propose a novel intrinsic encoder that excavates the condition-invariant latent space of different places under drastic appearance changes. Our method excavates the space of intrinsic structure and semantic information by proposed self-supervised encoder loss. Different from previous learning based place recognition methods that need paired training data of each place with appearance changes, we employ the weakly-supervised strategy to utilize unpaired set-based training data of different environmental conditions. We conduct comprehensive experiments and show that our semi-supervised intrinsic encoder achieves remarkable performance for place recognition under drastic appearance changes. The proposed intrinsic encoder outperforms the state-of-the-art image-level place recognition methods on standard benchmark Nordland.
Tasks
Published	2018-06-29
URL	http://arxiv.org/abs/1806.11306v4
PDF	http://arxiv.org/pdf/1806.11306v4.pdf
PWC	https://paperswithcode.com/paper/excavate-condition-invariant-space-by
Repo
Framework

SHADE: Information-Based Regularization for Deep Learning


Title	SHADE: Information-Based Regularization for Deep Learning
Authors	Michael Blot, Thomas Robert, Nicolas Thome, Matthieu Cord
Abstract	Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define a prior based on conditional entropy, which explicitly decouples the learning of invariant representations in the regularizer and the learning of correlations between inputs and labels in the data fitting term. Our second contribution is to derive a stochastic version of the regularizer compatible with deep learning, resulting in a tractable training scheme. We empirically validate the efficiency of our approach to improve classification performances compared to standard regularization schemes on several standard architectures.
Tasks
Published	2018-05-14
URL	http://arxiv.org/abs/1805.05814v1
PDF	http://arxiv.org/pdf/1805.05814v1.pdf
PWC	https://paperswithcode.com/paper/shade-information-based-regularization-for
Repo
Framework

How Much Reading Does Reading Comprehension Require? A Critical Investigation of Popular Benchmarks


Title	How Much Reading Does Reading Comprehension Require? A Critical Investigation of Popular Benchmarks
Authors	Divyansh Kaushik, Zachary C. Lipton
Abstract	Many recent papers address reading comprehension, where examples consist of (question, passage, answer) tuples. Presumably, a model must combine information from both questions and passages to predict corresponding answers. However, despite intense interest in the topic, with hundreds of published papers vying for leaderboard dominance, basic questions about the difficulty of many popular benchmarks remain unanswered. In this paper, we establish sensible baselines for the bAbI, SQuAD, CBT, CNN, and Who-did-What datasets, finding that question- and passage-only models often perform surprisingly well. On $14$ out of $20$ bAbI tasks, passage-only models achieve greater than $50%$ accuracy, sometimes matching the full model. Interestingly, while CBT provides $20$-sentence stories only the last is needed for comparably accurate prediction. By comparison, SQuAD and CNN appear better-constructed.
Tasks	Reading Comprehension
Published	2018-08-14
URL	http://arxiv.org/abs/1808.04926v2
PDF	http://arxiv.org/pdf/1808.04926v2.pdf
PWC	https://paperswithcode.com/paper/how-much-reading-does-reading-comprehension
Repo
Framework

(Sequential) Importance Sampling Bandits


Title	(Sequential) Importance Sampling Bandits
Authors	Iñigo Urteaga, Chris H. Wiggins
Abstract	This work extends existing multi-armed bandit (MAB) algorithms beyond their original settings by leveraging advances in sequential Monte Carlo (SMC) methods from the approximate inference community. We leverage Monte Carlo estimation and, in particular, the flexibility of (sequential) importance sampling to allow for accurate estimation of the statistics of interest within the MAB problem. The MAB is a sequential allocation task where the goal is to learn a policy that maximizes long term payoff, where only the reward of the executed action is observed; i.e., sequential optimal decisions are made, while simultaneously learning how the world operates. In the stochastic setting, the reward for each action is generated from an unknown distribution. To decide the next optimal action to take, one must compute sufficient statistics of this unknown reward distribution, e.g., upper-confidence bounds (UCB), or expectations in Thompson sampling. Closed-form expressions for these statistics of interest are analytically intractable except for simple cases. By combining SMC methods — which estimate posterior densities and expectations in probabilistic models that are analytically intractable — with Bayesian state-of-the-art MAB algorithms, we extend their applicability to complex models: those for which sampling may be performed even if analytic computation of summary statistics is infeasible — nonlinear reward functions and dynamic bandits. We combine SMC both for Thompson sampling and upper confident bound-based (Bayes-UCB) policies, and study different bandit models: classic Bernoulli and Gaussian distributed cases, as well as dynamic and context dependent linear-Gaussian, logistic and categorical-softmax rewards.
Tasks
Published	2018-08-08
URL	https://arxiv.org/abs/1808.02933v3
PDF	https://arxiv.org/pdf/1808.02933v3.pdf
PWC	https://paperswithcode.com/paper/sequential-importance-sampling-bandits
Repo
Framework

Learning to Play General Video-Games via an Object Embedding Network


Title	Learning to Play General Video-Games via an Object Embedding Network
Authors	William Woof, Ke Chen
Abstract	Deep reinforcement learning (DRL) has proven to be an effective tool for creating general video-game AI. However most current DRL video-game agents learn end-to-end from the video-output of the game, which is superfluous for many applications and creates a number of additional problems. More importantly, directly working on pixel-based raw video data is substantially distinct from what a human player does.In this paper, we present a novel method which enables DRL agents to learn directly from object information. This is obtained via use of an object embedding network (OEN) that compresses a set of object feature vectors of different lengths into a single fixed-length unified feature vector representing the current game-state and fulfills the DRL simultaneously. We evaluate our OEN-based DRL agent by comparing to several state-of-the-art approaches on a selection of games from the GVG-AI Competition. Experimental results suggest that our object-based DRL agent yields performance comparable to that of those approaches used in our comparative study.
Tasks
Published	2018-03-14
URL	http://arxiv.org/abs/1803.05262v2
PDF	http://arxiv.org/pdf/1803.05262v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-play-general-video-games-via-an
Repo
Framework

Playing Soccer without Colors in the SPL: A Convolutional Neural Network Approach


Title	Playing Soccer without Colors in the SPL: A Convolutional Neural Network Approach
Authors	Francisco Leiva, Nicolás Cruz, Ignacio Bugueño, Javier Ruiz-del-Solar
Abstract	The goal of this paper is to propose a vision system for humanoid robotic soccer that does not use any color information. The main features of this system are: (i) real-time operation in the NAO robot, and (ii) the ability to detect the ball, the robots, their orientations, the lines and key field features robustly. Our ball detector, robot detector, and robot’s orientation detector obtain the highest reported detection rates. The proposed vision system is tested in a SPL field with several NAO robots under realistic and highly demanding conditions. The obtained results are: robot detection rate of 94.90%, ball detection rate of 97.10%, and a completely perceived orientation rate of 99.88% when the observed robot is static, and 95.52% when the observed robot is moving.
Tasks
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12493v1
PDF	http://arxiv.org/pdf/1811.12493v1.pdf
PWC	https://paperswithcode.com/paper/playing-soccer-without-colors-in-the-spl-a
Repo
Framework

Computations in Stochastic Acceptors


Title	Computations in Stochastic Acceptors
Authors	Karl-Heinz Zimmermann
Abstract	Machine learning provides algorithms that can learn from data and make inferences or predictions on data. Stochastic acceptors or probabilistic automata are stochastic automata without output that can model components in machine learning scenarios. In this paper, we provide dynamic programming algorithms for the computation of input marginals and the acceptance probabilities in stochastic acceptors. Furthermore, we specify an algorithm for the parameter estimation of the conditional probabilities using the expectation-maximization technique and a more efficient implementation related to the Baum-Welch algorithm.
Tasks
Published	2018-12-23
URL	http://arxiv.org/abs/1812.09687v1
PDF	http://arxiv.org/pdf/1812.09687v1.pdf
PWC	https://paperswithcode.com/paper/computations-in-stochastic-acceptors
Repo
Framework