October 20, 2019

2844 words 14 mins read

Paper Group ANR 70

A Multi-Face Challenging Dataset for Robust Face Recognition. Minimax rates for cost-sensitive learning on manifolds with approximate nearest neighbours. Global Norm-Aware Pooling for Pose-Robust Face Recognition at Low False Positive Rate. Differential Evolution with Better and Nearest Option for Function Optimization. Person Identification using …

A Multi-Face Challenging Dataset for Robust Face Recognition


Title	A Multi-Face Challenging Dataset for Robust Face Recognition
Authors	Shiv Ram Dubey, Snehasis Mukherjee
Abstract	Face recognition in images is an active area of interest among the computer vision researchers. However, recognizing human face in an unconstrained environment, is a relatively less-explored area of research. Multiple face recognition in unconstrained environment is a challenging task, due to the variation of view-point, scale, pose, illumination and expression of the face images. Partial occlusion of faces makes the recognition task even more challenging. The contribution of this paper is two-folds: introducing a challenging multiface dataset (i.e., IIITS MFace Dataset) for face recognition in unconstrained environment and evaluating the performance of state-of-the-art hand-designed and deep learning based face descriptors on the dataset. The proposed IIITS MFace dataset contains faces with challenges like pose variation, occlusion, mask, spectacle, expressions, change of illumination, etc. We experiment with several state-of-the-art face descriptors, including recent deep learning based face descriptors like VGGFace, and compare with the existing benchmark face datasets. Results of the experiments clearly show that the difficulty level of the proposed dataset is much higher compared to the benchmark datasets.
Tasks	Face Recognition, Robust Face Recognition
Published	2018-09-30
URL	http://arxiv.org/abs/1810.01898v2
PDF	http://arxiv.org/pdf/1810.01898v2.pdf
PWC	https://paperswithcode.com/paper/a-multi-face-challenging-dataset-for-robust
Repo
Framework

Minimax rates for cost-sensitive learning on manifolds with approximate nearest neighbours


Title	Minimax rates for cost-sensitive learning on manifolds with approximate nearest neighbours
Authors	Henry WJ Reeve, Gavin Brown
Abstract	We study the approximate nearest neighbour method for cost-sensitive classification on low-dimensional manifolds embedded within a high-dimensional feature space. We determine the minimax learning rates for distributions on a smooth manifold, in a cost-sensitive setting. This generalises a classic result of Audibert and Tsybakov. Building upon recent work of Chaudhuri and Dasgupta we prove that these minimax rates are attained by the approximate nearest neighbour algorithm, where neighbours are computed in a randomly projected low-dimensional space. In addition, we give a bound on the number of dimensions required for the projection which depends solely upon the reach and dimension of the manifold, combined with the regularity of the marginal.
Tasks
Published	2018-03-01
URL	http://arxiv.org/abs/1803.00310v1
PDF	http://arxiv.org/pdf/1803.00310v1.pdf
PWC	https://paperswithcode.com/paper/minimax-rates-for-cost-sensitive-learning-on
Repo
Framework

Global Norm-Aware Pooling for Pose-Robust Face Recognition at Low False Positive Rate


Title	Global Norm-Aware Pooling for Pose-Robust Face Recognition at Low False Positive Rate
Authors	Sheng Chen, Jia Guo, Yang Liu, Xiang Gao, Zhen Han
Abstract	In this paper, we propose a novel Global Norm-Aware Pooling (GNAP) block, which reweights local features in a convolutional neural network (CNN) adaptively according to their L2 norms and outputs a global feature vector with a global average pooling layer. Our GNAP block is designed to give dynamic weights to local features in different spatial positions without losing spatial symmetry. We use a GNAP block in a face feature embedding CNN to produce discriminative face feature vectors for pose-robust face recognition. The GNAP block is of very cheap computational cost, but it is very powerful for frontal-profile face recognition. Under the CFP frontal-profile protocol, the GNAP block can not only reduce EER dramatically but also boost TPR@FPR=0.1% (TPR i.e. True Positive Rate, FPR i.e. False Positive Rate) substantially. Our experiments show that the GNAP block greatly promotes pose-robust face recognition over the base model especially at low false positive rate.
Tasks	Face Recognition, Robust Face Recognition
Published	2018-08-01
URL	http://arxiv.org/abs/1808.00435v1
PDF	http://arxiv.org/pdf/1808.00435v1.pdf
PWC	https://paperswithcode.com/paper/global-norm-aware-pooling-for-pose-robust
Repo
Framework

Differential Evolution with Better and Nearest Option for Function Optimization


Title	Differential Evolution with Better and Nearest Option for Function Optimization
Authors	Haozhen Dong, Liang Gao, Xinyu Li, Haoran Zhong, Bing Zeng
Abstract	Differential evolution(DE) is a conventional algorithm with fast convergence speed. However, DE may be trapped in local optimal solution easily. Many researchers devote themselves to improving DE. In our previously work, whale swarm algorithm have shown its strong searching performance due to its niching based mutation strategy. Based on this fact, we propose a new DE algorithm called DE with Better and Nearest option (NbDE). In order to evaluate the performance of NbDE, NbDE is compared with several meta-heuristic algorithms on nine classical benchmark test functions with different dimensions. The results show that NbDE outperforms other algorithms in convergence speed and accuracy.
Tasks
Published	2018-10-29
URL	https://arxiv.org/abs/1812.07608v2
PDF	https://arxiv.org/pdf/1812.07608v2.pdf
PWC	https://paperswithcode.com/paper/differential-evolution-with-better-and
Repo
Framework

Person Identification using Seismic Signals generated from Footfalls


Title	Person Identification using Seismic Signals generated from Footfalls
Authors	Bodhibrata Mukhopadhyay, Sahil Anchal, Subrat Kar
Abstract	Footfall based biometric system is perhaps the only person identification technique which does not hinder the natural movement of an individual. This is a clear edge over all other biometric systems which require a formidable amount of human intervention and encroach upon an individual’s privacy to some extent or the other. This paper presents a Fog computing architecture for implementing footfall based biometric system using widespread geographically distributed geophones (vibration sensor). Results were stored in an Internet of Things (IoT) cloud. We have tested our biometric system on an indigenous database (created by us) containing 46000 footfall events from 8 individuals and achieved an accuracy of 73%, 90% and 95% in case of 1, 5 and 10 footsteps per sample. We also proposed a basis pursuit based data compression technique DS8BP for wireless transmission of footfall events to the Fog. DS8BP compresses the original footfall events (sampled at 8 kHz) by a factor of 108 and also acts as a smoothing filter. These experimental results depict the high viability of our technique in the realm of person identification and access control systems.
Tasks	Person Identification
Published	2018-09-24
URL	http://arxiv.org/abs/1809.08783v1
PDF	http://arxiv.org/pdf/1809.08783v1.pdf
PWC	https://paperswithcode.com/paper/person-identification-using-seismic-signals
Repo
Framework

Formal Security Analysis of Neural Networks using Symbolic Intervals


Title	Formal Security Analysis of Neural Networks using Symbolic Intervals
Authors	Shiqi Wang, Kexin Pei, Justin Whitehouse, Junfeng Yang, Suman Jana
Abstract	Due to the increasing deployment of Deep Neural Networks (DNNs) in real-world security-critical domains including autonomous vehicles and collision avoidance systems, formally checking security properties of DNNs, especially under different attacker capabilities, is becoming crucial. Most existing security testing techniques for DNNs try to find adversarial examples without providing any formal security guarantees about the non-existence of such adversarial examples. Recently, several projects have used different types of Satisfiability Modulo Theory (SMT) solvers to formally check security properties of DNNs. However, all of these approaches are limited by the high overhead caused by the solver. In this paper, we present a new direction for formally checking security properties of DNNs without using SMT solvers. Instead, we leverage interval arithmetic to compute rigorous bounds on the DNN outputs. Our approach, unlike existing solver-based approaches, is easily parallelizable. We further present symbolic interval analysis along with several other optimizations to minimize overestimations of output bounds. We design, implement, and evaluate our approach as part of ReluVal, a system for formally checking security properties of Relu-based DNNs. Our extensive empirical results show that ReluVal outperforms Reluplex, a state-of-the-art solver-based system, by 200 times on average. On a single 8-core machine without GPUs, within 4 hours, ReluVal is able to verify a security property that Reluplex deemed inconclusive due to timeout after running for more than 5 days. Our experiments demonstrate that symbolic interval analysis is a promising new direction towards rigorously analyzing different security properties of DNNs.
Tasks	Autonomous Vehicles
Published	2018-04-28
URL	http://arxiv.org/abs/1804.10829v3
PDF	http://arxiv.org/pdf/1804.10829v3.pdf
PWC	https://paperswithcode.com/paper/formal-security-analysis-of-neural-networks
Repo
Framework

A Probabilistic Model of Cardiac Physiology and Electrocardiograms


Title	A Probabilistic Model of Cardiac Physiology and Electrocardiograms
Authors	Andrew C. Miller, Ziad Obermeyer, David M. Blei, John P. Cunningham, Sendhil Mullainathan
Abstract	An electrocardiogram (EKG) is a common, non-invasive test that measures the electrical activity of a patient’s heart. EKGs contain useful diagnostic information about patient health that may be absent from other electronic health record (EHR) data. As multi-dimensional waveforms, they could be modeled using generic machine learning tools, such as a linear factor model or a variational autoencoder. We take a different approach:~we specify a model that directly represents the underlying electrophysiology of the heart and the EKG measurement process. We apply our model to two datasets, including a sample of emergency department EKG reports with missing data. We show that our model can more accurately reconstruct missing data (measured by test reconstruction error) than a standard baseline when there is significant missing data. More broadly, this physiological representation of heart function may be useful in a variety of settings, including prediction, causal analysis, and discovery.
Tasks
Published	2018-12-01
URL	http://arxiv.org/abs/1812.00209v1
PDF	http://arxiv.org/pdf/1812.00209v1.pdf
PWC	https://paperswithcode.com/paper/a-probabilistic-model-of-cardiac-physiology
Repo
Framework

An Incremental Boolean Tensor Factorization approach to model Change Patterns of Objects in Images


Title	An Incremental Boolean Tensor Factorization approach to model Change Patterns of Objects in Images
Authors	S Saritha, G Santhosh Kumar
Abstract	Change detection process has recently progressed from a post-classification method to an expert knowledge interpretation process of the time-series data. The technique finds applications mainly in remote sensing images and can be utilized to analyze urbanization and monitor forest regions. In this paper, a framework to perform a knowledge based interpretation of the changes/no changes observed in a spatiotemporal domain using tensor based approaches is presented. An incremental approach to Boolean Tensor Factorization method is proposed in this work, which is adopted to model the change patterns of objects/classes as well as their associated features. The framework is evaluated under different datasets to visualize the performance for the dependency factors. The algorithm is also validated in comparison with the tradition Boolean Tensor Factorization method and the results are substantial.
Tasks	Time Series
Published	2018-03-23
URL	http://arxiv.org/abs/1803.08696v1
PDF	http://arxiv.org/pdf/1803.08696v1.pdf
PWC	https://paperswithcode.com/paper/an-incremental-boolean-tensor-factorization
Repo
Framework

Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification


Title	Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification
Authors	Jia Li, Yafei Song, Jianfeng Zhu, Lele Cheng, Ying Su, Lin Ye, Pengcheng Yuan, Shumin Han
Abstract	Many advances of deep learning techniques originate from the efforts of addressing the image classification task on large-scale datasets. However, the construction of such clean datasets is costly and time-consuming since the Internet is overwhelmed by noisy images with inadequate and inaccurate tags. In this paper, we propose a Ubiquitous Reweighting Network (URNet) that learns an image classification model from large-scale noisy data. By observing the web data, we find that there are five key challenges, i.e., imbalanced class sizes, high intra-classes diversity and inter-class similarity, imprecise instances, insufficient representative instances, and ambiguous class labels. To alleviate these challenges, we assume that every training instance has the potential to contribute positively by alleviating the data bias and noise via reweighting the influence of each instance according to different class sizes, large instance clusters, its confidence, small instance bags and the labels. In this manner, the influence of bias and noise in the web data can be gradually alleviated, leading to the steadily improving performance of URNet. Experimental results in the WebVision 2018 challenge with 16 million noisy training images from 5000 classes show that our approach outperforms state-of-the-art models and ranks the first place in the image classification task.
Tasks	Image Classification
Published	2018-11-02
URL	http://arxiv.org/abs/1811.00700v2
PDF	http://arxiv.org/pdf/1811.00700v2.pdf
PWC	https://paperswithcode.com/paper/learning-from-large-scale-noisy-web-data-with
Repo
Framework

Knowledge-Aware Conversational Semantic Parsing Over Web Tables


Title	Knowledge-Aware Conversational Semantic Parsing Over Web Tables
Authors	Yibo Sun, Duyu Tang, Nan Duan, Jingjing Xu, Xiaocheng Feng, Bing Qin
Abstract	Conversational semantic parsing over tables requires knowledge acquiring and reasoning abilities, which have not been well explored by current state-of-the-art approaches. Motivated by this fact, we propose a knowledge-aware semantic parser to improve parsing performance by integrating various types of knowledge. In this paper, we consider three types of knowledge, including grammar knowledge, expert knowledge, and external resource knowledge. First, grammar knowledge empowers the model to effectively replicate previously generated logical form, which effectively handles the co-reference and ellipsis phenomena in conversation Second, based on expert knowledge, we propose a decomposable model, which is more controllable compared with traditional end-to-end models that put all the burdens of learning on trial-and-error in an end-to-end way. Third, external resource knowledge, i.e., provided by a pre-trained language model or an entity typing model, is used to improve the representation of question and table for a better semantic understanding. We conduct experiments on the SequentialQA dataset. Results show that our knowledge-aware model outperforms the state-of-the-art approaches. Incremental experimental results also prove the usefulness of various knowledge. Further analysis shows that our approach has the ability to derive the meaning representation of a context-dependent utterance by leveraging previously generated outcomes.
Tasks	Entity Typing, Language Modelling, Semantic Parsing
Published	2018-09-12
URL	http://arxiv.org/abs/1809.04271v1
PDF	http://arxiv.org/pdf/1809.04271v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-aware-conversational-semantic
Repo
Framework

Coarse-to-fine volumetric segmentation of teeth in Cone-Beam CT


Title	Coarse-to-fine volumetric segmentation of teeth in Cone-Beam CT
Authors	Matvey Ezhov, Adel Zakirov, Maxim Gusarev
Abstract	We consider the problem of localizing and segmenting individual teeth inside 3D Cone-Beam Computed Tomography (CBCT) images. To handle large image sizes we approach this task with a coarse-to-fine framework, where the whole volume is first analyzed as a 33-class semantic segmentation (adults have up to 32 teeth) in coarse resolution, followed by binary semantic segmentation of the cropped region of interest in original resolution. To improve the performance of the challenging 33-class segmentation, we first train the Coarse step model on a large weakly labeled dataset, then fine-tune it on a smaller precisely labeled dataset. The Fine step model is trained with precise labels only. Experiments using our in-house dataset show significant improvement for both weakly-supervised pretraining and for the addition of the Fine step. Empirically, this framework yields precise teeth masks with low localization errors sufficient for many real-world applications.
Tasks	Semantic Segmentation
Published	2018-10-24
URL	http://arxiv.org/abs/1810.10293v1
PDF	http://arxiv.org/pdf/1810.10293v1.pdf
PWC	https://paperswithcode.com/paper/coarse-to-fine-volumetric-segmentation-of
Repo
Framework

Accurate Building Detection in VHR Remote Sensing Images using Geometric Saliency


Title	Accurate Building Detection in VHR Remote Sensing Images using Geometric Saliency
Authors	Jin Huang, Gui-Song Xia, Fan Hu, Liangpei Zhang
Abstract	This paper aims to address the problem of detecting buildings from remote sensing images with very high resolution (VHR). Inspired by the observation that buildings are always more distinguishable in geometries than in texture or spectral, we propose a new geometric building index (GBI) for accurate building detection, which relies on the geometric saliency of building structures. The geometric saliency of buildings is derived from a mid-level geometric representations based on meaningful junctions that can locally describe anisotropic geometrical structures of images. The resulting GBI is measured by integrating the derived geometric saliency of buildings. Experiments on three public datasets demonstrate that the proposed GBI achieves very promising performance, and meanwhile shows impressive generalization capability.
Tasks
Published	2018-06-04
URL	http://arxiv.org/abs/1806.00908v2
PDF	http://arxiv.org/pdf/1806.00908v2.pdf
PWC	https://paperswithcode.com/paper/accurate-building-detection-in-vhr-remote
Repo
Framework

How Many Machines Can We Use in Parallel Computing for Kernel Ridge Regression?


Title	How Many Machines Can We Use in Parallel Computing for Kernel Ridge Regression?
Authors	Meimei Liu, Zuofeng Shang, Guang Cheng
Abstract	This paper aims to solve a basic problem in distributed statistical inference: how many machines can we use in parallel computing? In kernel ridge regression, we address this question in two important settings: nonparametric estimation and hypothesis testing. Specifically, we find a range for the number of machines under which optimal estimation/testing is achievable. The employed empirical processes method provides a unified framework, that allows us to handle various regression problems (such as thin-plate splines and nonparametric additive regression) under different settings (such as univariate, multivariate and diverging-dimensional designs). It is worth noting that the upper bounds of the number of machines are proven to be un-improvable (upto a logarithmic factor) in two important cases: smoothing spline regression and Gaussian RKHS regression. Our theoretical findings are backed by thorough numerical studies.
Tasks
Published	2018-05-25
URL	http://arxiv.org/abs/1805.09948v3
PDF	http://arxiv.org/pdf/1805.09948v3.pdf
PWC	https://paperswithcode.com/paper/how-many-machines-can-we-use-in-parallel
Repo
Framework

On the use of FHT, its modification for practical applications and the structure of Hough image


Title	On the use of FHT, its modification for practical applications and the structure of Hough image
Authors	M. Aliev, E. I. Ershov, D. P. Nikolaev
Abstract	This work focuses on the Fast Hough Transform (FHT) algorithm proposed by M.L. Brady. We propose how to modify the standard FHT to calculate sums along lines within any given range of their inclination angles. We also describe a new way to visualise Hough-image based on regrouping of accumulator space around its center. Finally, we prove that using Brady parameterization transforms any line into a figure of type “angle”.
Tasks
Published	2018-11-14
URL	http://arxiv.org/abs/1811.06378v1
PDF	http://arxiv.org/pdf/1811.06378v1.pdf
PWC	https://paperswithcode.com/paper/on-the-use-of-fht-its-modification-for
Repo
Framework

Learning SMaLL Predictors


Title	Learning SMaLL Predictors
Authors	Vikas K. Garg, Ofer Dekel, Lin Xiao
Abstract	We present a new machine learning technique for training small resource-constrained predictors. Our algorithm, the Sparse Multiprototype Linear Learner (SMaLL), is inspired by the classic machine learning problem of learning $k$-DNF Boolean formulae. We present a formal derivation of our algorithm and demonstrate the benefits of our approach with a detailed empirical study.
Tasks
Published	2018-03-06
URL	http://arxiv.org/abs/1803.02388v1
PDF	http://arxiv.org/pdf/1803.02388v1.pdf
PWC	https://paperswithcode.com/paper/learning-small-predictors
Repo
Framework