January 31, 2020

3252 words 16 mins read

Paper Group ANR 59

Mean Estimation from One-Bit Measurements. Online Graph-Based Change-Point Detection for High Dimensional Data. Appearance-Based Gaze Estimation Using Dilated-Convolutions. Purifying Naturalistic Images through a Real-time Style Transfer Semantics Network. DF-SLAM: A Deep-Learning Enhanced Visual SLAM System based on Deep Local Features. Location A …

Mean Estimation from One-Bit Measurements


Title	Mean Estimation from One-Bit Measurements
Authors	Alon Kipnis, John C. Duchi
Abstract	We consider the problem of estimating the mean of a symmetric log-concave distribution under the constraint that only a single bit per sample from this distribution is available to the estimator. We study the mean squared error as a function of the sample size (and hence the number of bits). We consider three settings: first, a centralized setting, where an encoder may release $n$ bits given a sample of size $n$, and for which there is no asymptotic penalty for quantization; second, an adaptive setting in which each bit is a function of the current observation and previously recorded bits, where we show that the optimal relative efficiency compared to the sample mean is precisely the efficiency of the median; lastly, we show that in a distributed setting where each bit is only a function of a local sample, no estimator can achieve optimal efficiency uniformly over the parameter space. We additionally complement our results in the adaptive setting by showing that \emph{one} round of adaptivity is sufficient to achieve optimal mean-square error.
Tasks	Quantization
Published	2019-01-10
URL	https://arxiv.org/abs/1901.03403v2
PDF	https://arxiv.org/pdf/1901.03403v2.pdf
PWC	https://paperswithcode.com/paper/mean-estimation-from-one-bit-measurements
Repo
Framework

Online Graph-Based Change-Point Detection for High Dimensional Data


Title	Online Graph-Based Change-Point Detection for High Dimensional Data
Authors	Yang-Wen Sun, Katerina Papagiannouli, Vladmir Spokoiny
Abstract	Online change-point detection (OCPD) is important for application in various areas such as finance, biology, and the Internet of Things (IoT). However, OCPD faces major challenges due to high-dimensionality, and it is still rarely studied in literature. In this paper, we propose a novel, online, graph-based, change-point detection algorithm to detect change of distribution in low- to high-dimensional data. We introduce a similarity measure, which is derived from the graph-spanning ratio, to test statistically if a change occurs. Through numerical study using artificial online datasets, our data-driven approach demonstrates high detection power for high-dimensional data, while the false alarm rate (type I error) is controlled at a nominal significant level. In particular, our graph-spanning approach has desirable power with small and multiple scanning window, which allows timely detection of change-point in the online setting.
Tasks	Change Point Detection
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03001v1
PDF	https://arxiv.org/pdf/1906.03001v1.pdf
PWC	https://paperswithcode.com/paper/online-graph-based-change-point-detection-for
Repo
Framework

Appearance-Based Gaze Estimation Using Dilated-Convolutions


Title	Appearance-Based Gaze Estimation Using Dilated-Convolutions
Authors	Zhaokang Chen, Bertram E. Shi
Abstract	Appearance-based gaze estimation has attracted more and more attention because of its wide range of applications. The use of deep convolutional neural networks has improved the accuracy significantly. In order to improve the estimation accuracy further, we focus on extracting better features from eye images. Relatively large changes in gaze angles may result in relatively small changes in eye appearance. We argue that current architectures for gaze estimation may not be able to capture such small changes, as they apply multiple pooling layers or other downsampling layers so that the spatial resolution of the high-level layers is reduced significantly. To evaluate whether the use of features extracted at high resolution can benefit gaze estimation, we adopt dilated-convolutions to extract high-level features without reducing spatial resolution. In cross-subject experiments on the Columbia Gaze dataset for eye contact detection and the MPIIGaze dataset for 3D gaze vector regression, the resulting Dilated-Nets achieve significant (up to 20.8%) gains when compared to similar networks without dilated-convolutions. Our proposed Dilated-Net achieves state-of-the-art results on both the Columbia Gaze and the MPIIGaze datasets.
Tasks	Gaze Estimation
Published	2019-03-18
URL	http://arxiv.org/abs/1903.07296v1
PDF	http://arxiv.org/pdf/1903.07296v1.pdf
PWC	https://paperswithcode.com/paper/appearance-based-gaze-estimation-using
Repo
Framework

Purifying Naturalistic Images through a Real-time Style Transfer Semantics Network


Title	Purifying Naturalistic Images through a Real-time Style Transfer Semantics Network
Authors	Tongtong Zhao, Yuxiao Yan, Ibrahim Shehi Shehu, Xianping Fu, Huibing Wang
Abstract	Recently, the progress of learning-by-synthesis has proposed a training model for synthetic images, which can effectively reduce the cost of human and material resources. However, due to the different distribution of synthetic images compared to real images, the desired performance cannot still be achieved. Real images consist of multiple forms of light orientation, while synthetic images consist of a uniform light orientation. These features are considered to be characteristic of outdoor and indoor scenes, respectively. To solve this problem, the previous method learned a model to improve the realism of the synthetic image. Different from the previous methods, this paper takes the first step to purify real images. Through the style transfer task, the distribution of outdoor real images is converted into indoor synthetic images, thereby reducing the influence of light. Therefore, this paper proposes a real-time style transfer network that preserves image content information (eg, gaze direction, pupil center position) of an input image (real image) while inferring style information (eg, image color structure, semantic features) of style image (synthetic image). In addition, the network accelerates the convergence speed of the model and adapts to multi-scale images. Experiments were performed using mixed studies (qualitative and quantitative) methods to demonstrate the possibility of purifying real images in complex directions. Qualitatively, it compares the proposed method with the available methods in a series of indoor and outdoor scenarios of the LPW dataset. In quantitative terms, it evaluates the purified image by training a gaze estimation model on the cross data set. The results show a significant improvement over the baseline method compared to the raw real image.
Tasks	Gaze Estimation, Style Transfer
Published	2019-03-14
URL	http://arxiv.org/abs/1903.05820v1
PDF	http://arxiv.org/pdf/1903.05820v1.pdf
PWC	https://paperswithcode.com/paper/purifying-naturalistic-images-through-a-real
Repo
Framework

DF-SLAM: A Deep-Learning Enhanced Visual SLAM System based on Deep Local Features


Title	DF-SLAM: A Deep-Learning Enhanced Visual SLAM System based on Deep Local Features
Authors	Rong Kang, Jieqi Shi, Xueming Li, Yang Liu, Xiao Liu
Abstract	As the foundation of driverless vehicle and intelligent robots, Simultaneous Localization and Mapping(SLAM) has attracted much attention these days. However, non-geometric modules of traditional SLAM algorithms are limited by data association tasks and have become a bottleneck preventing the development of SLAM. To deal with such problems, many researchers seek to Deep Learning for help. But most of these studies are limited to virtual datasets or specific environments, and even sacrifice efficiency for accuracy. Thus, they are not practical enough. We propose DF-SLAM system that uses deep local feature descriptors obtained by the neural network as a substitute for traditional hand-made features. Experimental results demonstrate its improvements in efficiency and stability. DF-SLAM outperforms popular traditional SLAM systems in various scenes, including challenging scenes with intense illumination changes. Its versatility and mobility fit well into the need for exploring new environments. Since we adopt a shallow network to extract local descriptors and remain others the same as original SLAM systems, our DF-SLAM can still run in real-time on GPU.
Tasks	Simultaneous Localization and Mapping
Published	2019-01-22
URL	http://arxiv.org/abs/1901.07223v2
PDF	http://arxiv.org/pdf/1901.07223v2.pdf
PWC	https://paperswithcode.com/paper/df-slam-a-deep-learning-enhanced-visual-slam
Repo
Framework

Location Anomalies Detection for Connected and Autonomous Vehicles


Title	Location Anomalies Detection for Connected and Autonomous Vehicles
Authors	Xiaoyang Wang, Ioannis Mavromatis, Andrea Tassi, Raul Santos-Rodriguez, Robert J. Piechocki
Abstract	Future Connected and Automated Vehicles (CAV), and more generally ITS, will form a highly interconnected system. Such a paradigm is referred to as the Internet of Vehicles (herein Internet of CAVs) and is a prerequisite to orchestrate traffic flows in cities. For optimal decision making and supervision, traffic centres will have access to suitably anonymized CAV mobility information. Safe and secure operations will then be contingent on early detection of anomalies. In this paper, a novel unsupervised learning model based on deep autoencoder is proposed to detect the self-reported location anomaly in CAVs, using vehicle locations and the Received Signal Strength Indicator (RSSI) as features. Quantitative experiments on simulation datasets show that the proposed approach is effective and robust in detecting self-reported location anomalies.
Tasks	Autonomous Vehicles, Decision Making
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00811v1
PDF	https://arxiv.org/pdf/1907.00811v1.pdf
PWC	https://paperswithcode.com/paper/location-anomalies-detection-for-connected
Repo
Framework

Highlight Every Step: Knowledge Distillation via Collaborative Teaching


Title	Highlight Every Step: Knowledge Distillation via Collaborative Teaching
Authors	Haoran Zhao, Xin Sun, Junyu Dong, Changrui Chen, Zihe Dong
Abstract	High storage and computational costs obstruct deep neural networks to be deployed on resource-constrained devices. Knowledge distillation aims to train a compact student network by transferring knowledge from a larger pre-trained teacher model. However, most existing methods on knowledge distillation ignore the valuable information among training process associated with training results. In this paper, we provide a new Collaborative Teaching Knowledge Distillation (CTKD) strategy which employs two special teachers. Specifically, one teacher trained from scratch (i.e., scratch teacher) assists the student step by step using its temporary outputs. It forces the student to approach the optimal path towards the final logits with high accuracy. The other pre-trained teacher (i.e., expert teacher) guides the student to focus on a critical region which is more useful for the task. The combination of the knowledge from two special teachers can significantly improve the performance of the student network in knowledge distillation. The results of experiments on CIFAR-10, CIFAR-100, SVHN and Tiny ImageNet datasets verify that the proposed knowledge distillation method is efficient and achieves state-of-the-art performance.
Tasks
Published	2019-07-23
URL	https://arxiv.org/abs/1907.09643v1
PDF	https://arxiv.org/pdf/1907.09643v1.pdf
PWC	https://paperswithcode.com/paper/highlight-every-step-knowledge-distillation
Repo
Framework

Deep Learning Emulation of Multi-Angle Implementation of Atmospheric Correction (MAIAC)


Title	Deep Learning Emulation of Multi-Angle Implementation of Atmospheric Correction (MAIAC)
Authors	Kate Duffy, Thomas Vandal, Weile Wang, Ramakrishna Nemani, Auroop R. Ganguly
Abstract	New generation geostationary satellites make solar reflectance observations available at a continental scale with unprecedented spatiotemporal resolution and spectral range. Generating quality land monitoring products requires correction of the effects of atmospheric scattering and absorption, which vary in time and space according to geometry and atmospheric composition. Many atmospheric radiative transfer models, including that of Multi-Angle Implementation of Atmospheric Correction (MAIAC), are too computationally complex to be run in real time, and rely on precomputed look-up tables. Additionally, uncertainty in measurements and models for remote sensing receives insufficient attention, in part due to the difficulty of obtaining sufficient ground measurements. In this paper, we present an adaptation of Bayesian Deep Learning (BDL) to emulation of the MAIAC atmospheric correction algorithm. Emulation approaches learn a statistical model as an efficient approximation of a physical model, while machine learning methods have demonstrated performance in extracting spatial features and learning complex, nonlinear mappings. We demonstrate stable surface reflectance retrieval by emulation (R2 between MAIAC and emulator SR are 0.63, 0.75, 0.86, 0.84, 0.95, and 0.91 for Blue, Green, Red, NIR, SWIR1, and SWIR2 bands, respectively), accurate cloud detection (86%), and well-calibrated, geolocated uncertainty estimates. Our results support BDL-based emulation as an accurate and efficient (up to 6x speedup) method for approximation atmospheric correction, where built-in uncertainty estimates stand to open new opportunities for model assessment and support informed use of SR-derived quantities in multiple domains.
Tasks	Cloud Detection
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13408v1
PDF	https://arxiv.org/pdf/1910.13408v1.pdf
PWC	https://paperswithcode.com/paper/191013408
Repo
Framework

A Gegenbauer Neural Network with Regularized Weights Direct Determination for Classification


Title	A Gegenbauer Neural Network with Regularized Weights Direct Determination for Classification
Authors	Jie He, Tao Chen, Zhijun Zhang
Abstract	Single-hidden layer feed forward neural networks (SLFNs) are widely used in pattern classification problems, but a huge bottleneck encountered is the slow speed and poor performance of the traditional iterative gradient-based learning algorithms. Although the famous extreme learning machine (ELM) has successfully addressed the problems of slow convergence, it still has computational robustness problems brought by input weights and biases randomly assigned. Thus, in order to overcome the aforementioned problems, in this paper, a novel type neural network based on Gegenbauer orthogonal polynomials, termed as GNN, is constructed and investigated. This model could overcome the computational robustness problems of ELM, while still has comparable structural simplicity and approximation capability. Based on this, we propose a regularized weights direct determination (R-WDD) based on equality-constrained optimization to determine the optimal output weights. The R-WDD tends to minimize the empirical risks and structural risks of the network, thus to lower the risk of over fitting and improve the generalization ability. This leads us to a the final GNN with R-WDD, which is a unified learning mechanism for binary and multi-class classification problems. Finally, as is verified in the various comparison experiments, GNN with R-WDD tends to have comparable (or even better) generalization performances, computational scalability and efficiency, and classification robustness, compared to least square support vector machine (LS-SVM), ELM with Gaussian kernel.
Tasks
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11552v1
PDF	https://arxiv.org/pdf/1910.11552v1.pdf
PWC	https://paperswithcode.com/paper/a-gegenbauer-neural-network-with-regularized
Repo
Framework

Differentially-Private Two-Party Egocentric Betweenness Centrality


Title	Differentially-Private Two-Party Egocentric Betweenness Centrality
Authors	Leyla Roohi, Benjamin I. P. Rubinstein, Vanessa Teague
Abstract	We describe a novel protocol for computing the egocentric betweenness centrality of a node when relevant edge information is spread between two mutually distrusting parties such as two telecommunications providers. While each node belongs to one network or the other, its ego network might include edges unknown to its network provider. We develop a protocol of differentially-private mechanisms to hide each network’s internal edge structure from the other; and contribute a new two-stage stratified sampler for exponential improvement to time and space efficiency. Empirical results on several open graph data sets demonstrate practical relative error rates while delivering strong privacy guarantees, such as 16% error on a Facebook data set.
Tasks
Published	2019-01-16
URL	http://arxiv.org/abs/1901.05562v1
PDF	http://arxiv.org/pdf/1901.05562v1.pdf
PWC	https://paperswithcode.com/paper/differentially-private-two-party-egocentric
Repo
Framework

How to gamble with non-stationary $\mathcal{X}$-armed bandits and have no regrets


Title	How to gamble with non-stationary $\mathcal{X}$-armed bandits and have no regrets
Authors	Valeriy Avanesov
Abstract	In $\mathcal{X}$-armed bandit problem an agent sequentially interacts with environment which yields a reward based on the vector input the agent provides. The agent’s goal is to maximise the sum of these rewards across some number of time steps. The problem and its variations have been a subject of numerous studies, suggesting sub-linear and some times optimal strategies. The given paper introduces a novel variation of the problem. We consider an environment, which can abruptly change its behaviour an unknown number of times. To that end we propose a novel strategy and prove it attains sub-linear cumulative regret. Moreover, in case of highly smooth relation between an action and the corresponding reward, the method is nearly optimal. The theoretical result are supported by experimental study.
Tasks
Published	2019-08-20
URL	https://arxiv.org/abs/1908.07636v2
PDF	https://arxiv.org/pdf/1908.07636v2.pdf
PWC	https://paperswithcode.com/paper/190807636
Repo
Framework

Learning of Image Dehazing Models for Segmentation Tasks


Title	Learning of Image Dehazing Models for Segmentation Tasks
Authors	Sébastien de Blois, Ihsen Hedhli, Christian Gagné
Abstract	To evaluate their performance, existing dehazing approaches generally rely on distance measures between the generated image and its corresponding ground truth. Despite its ability to produce visually good images, using pixel-based or even perceptual metrics do not guarantee, in general, that the produced image is fit for being used as input for low-level computer vision tasks such as segmentation. To overcome this weakness, we are proposing a novel end-to-end approach for image dehazing, fit for being used as input to an image segmentation procedure, while maintaining the visual quality of the generated images. Inspired by the success of Generative Adversarial Networks (GAN), we propose to optimize the generator by introducing a discriminator network and a loss function that evaluates segmentation quality of dehazed images. In addition, we make use of a supplementary loss function that verifies that the visual and the perceptual quality of the generated image are preserved in hazy conditions. Results obtained using the proposed technique are appealing, with a favorable comparison to state-of-the-art approaches when considering the performance of segmentation algorithms on the hazy images.
Tasks	Image Dehazing, Semantic Segmentation
Published	2019-03-04
URL	https://arxiv.org/abs/1903.01530v2
PDF	https://arxiv.org/pdf/1903.01530v2.pdf
PWC	https://paperswithcode.com/paper/learning-of-image-dehazing-models-for
Repo
Framework

Imitation-Projected Programmatic Reinforcement Learning


Title	Imitation-Projected Programmatic Reinforcement Learning
Authors	Abhinav Verma, Hoang M. Le, Yisong Yue, Swarat Chaudhuri
Abstract	We study the problem of programmatic reinforcement learning, in which policies are represented as short programs in a symbolic language. Programmatic policies can be more interpretable, generalizable, and amenable to formal verification than neural policies; however, designing rigorous learning approaches for such policies remains a challenge. Our approach to this challenge – a meta-algorithm called PROPEL – is based on three insights. First, we view our learning task as optimization in policy space, modulo the constraint that the desired policy has a programmatic representation, and solve this optimization problem using a form of mirror descent that takes a gradient step into the unconstrained policy space and then projects back onto the constrained space. Second, we view the unconstrained policy space as mixing neural and programmatic representations, which enables employing state-of-the-art deep policy gradient approaches. Third, we cast the projection step as program synthesis via imitation learning, and exploit contemporary combinatorial methods for this task. We present theoretical convergence results for PROPEL and empirically evaluate the approach in three continuous control domains. The experiments show that PROPEL can significantly outperform state-of-the-art approaches for learning programmatic policies.
Tasks	Continuous Control, Imitation Learning, Program Synthesis
Published	2019-07-11
URL	https://arxiv.org/abs/1907.05431v3
PDF	https://arxiv.org/pdf/1907.05431v3.pdf
PWC	https://paperswithcode.com/paper/imitation-projected-policy-gradient-for
Repo
Framework

sZoom: A Framework for Automatic Zoom into High Resolution Surveillance Videos


Title	sZoom: A Framework for Automatic Zoom into High Resolution Surveillance Videos
Authors	Mukesh Saini, Benjamin Guthier, Hao Kuang, Dwarikanath Mahapatra, Abdulmotaleb El Saddik
Abstract	Current cameras are capable of recording high resolution video. While viewing on a mobile device, a user can manually zoom into this high resolution video to get more detailed view of objects and activities. However, manual zooming is not suitable for surveillance and monitoring. It is tiring to continuously keep zooming into various regions of the video. Also, while viewing one region, the operator may miss activities in other regions. In this paper, we propose sZoom, a framework to automatically zoom into a high resolution surveillance video. The proposed framework selectively zooms into the sensitive regions of the video to present details of the scene, while still preserving the overall context required for situation assessment. A multi-variate Gaussian penalty is introduced to ensure full coverage of the scene. The method achieves near real-time performance through a number of timing optimizations. An extensive user study shows that, while watching a full HD video on a mobile device, the system enhances the security operator’s efficiency in understanding the details of the scene by 99% on the average compared to a scaled version of the original high resolution video. The produced video achieved 46% higher ratings for usefulness in a surveillance task.
Tasks
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10164v1
PDF	https://arxiv.org/pdf/1909.10164v1.pdf
PWC	https://paperswithcode.com/paper/190910164
Repo
Framework


Title	Variational Regularized Transmission Refinement for Image Dehazing
Authors	Qiaoling Shu, Chuansheng Wu, Zhe Xiao, Ryan Wen Liu
Abstract	High-quality dehazing performance is highly dependent upon the accurate estimation of transmission map. In this work, the coarse estimation version is first obtained by weightedly fusing two different transmission maps, which are generated from foreground and sky regions, respectively. A hybrid variational model with promoted regularization terms is then proposed to assisting in refining transmission map. The resulting complicated optimization problem is effectively solved via an alternating direction algorithm. The final haze-free image can be effectively obtained according to the refined transmission map and atmospheric scattering model. Our dehazing framework has the capacity of preserving important image details while suppressing undesirable artifacts, even for hazy images with large sky regions. Experiments on both synthetic and realistic images have illustrated that the proposed method is competitive with or even outperforms the state-of-the-art dehazing techniques under different imaging conditions.
Tasks	Image Dehazing
Published	2019-02-19
URL	http://arxiv.org/abs/1902.07069v1
PDF	http://arxiv.org/pdf/1902.07069v1.pdf
PWC	https://paperswithcode.com/paper/variational-regularized-transmission
Repo
Framework