July 28, 2019

3037 words 15 mins read

Paper Group ANR 267

Quantum Memristors in Quantum Photonics. Learning a Mixture of Deep Networks for Single Image Super-Resolution. Interpretable & Explorable Approximations of Black Box Models. Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration. AI Oriented Large-Scale Video Management for Smart City: Technologies, Standards …

Quantum Memristors in Quantum Photonics


Title	Quantum Memristors in Quantum Photonics
Authors	M. Sanz, L. Lamata, E. Solano
Abstract	We propose a method to build quantum memristors in quantum photonic platforms. We firstly design an effective beam splitter, which is tunable in real-time, by means of a Mach-Zehnder-type array with two equal 50:50 beam splitters and a tunable retarder, which allows us to control its reflectivity. Then, we show that this tunable beam splitter, when equipped with weak measurements and classical feedback, behaves as a quantum memristor. Indeed, in order to prove its quantumness, we show how to codify quantum information in the coherent beams. Moreover, we estimate the memory capability of the quantum memristor. Finally, we show the feasibility of the proposed setup in integrated quantum photonics.
Tasks
Published	2017-09-22
URL	http://arxiv.org/abs/1709.07808v2
PDF	http://arxiv.org/pdf/1709.07808v2.pdf
PWC	https://paperswithcode.com/paper/quantum-memristors-in-quantum-photonics
Repo
Framework

Learning a Mixture of Deep Networks for Single Image Super-Resolution


Title	Learning a Mixture of Deep Networks for Single Image Super-Resolution
Authors	Ding Liu, Zhaowen Wang, Nasser Nasrabadi, Thomas Huang
Abstract	Single image super-resolution (SR) is an ill-posed problem which aims to recover high-resolution (HR) images from their low-resolution (LR) observations. The crux of this problem lies in learning the complex mapping between low-resolution patches and the corresponding high-resolution patches. Prior arts have used either a mixture of simple regression models or a single non-linear neural network for this propose. This paper proposes the method of learning a mixture of SR inference modules in a unified framework to tackle this problem. Specifically, a number of SR inference modules specialized in different image local patterns are first independently applied on the LR image to obtain various HR estimates, and the resultant HR estimates are adaptively aggregated to form the final HR image. By selecting neural networks as the SR inference module, the whole procedure can be incorporated into a unified network and be optimized jointly. Extensive experiments are conducted to investigate the relation between restoration performance and different network architectures. Compared with other current image SR approaches, our proposed method achieves state-of-the-arts restoration results on a wide range of images consistently while allowing more flexible design choices. The source codes are available in http://www.ifp.illinois.edu/~dingliu2/accv2016.
Tasks	Image Super-Resolution, Super-Resolution
Published	2017-01-03
URL	http://arxiv.org/abs/1701.00823v1
PDF	http://arxiv.org/pdf/1701.00823v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-mixture-of-deep-networks-for
Repo
Framework

Interpretable & Explorable Approximations of Black Box Models


Title	Interpretable & Explorable Approximations of Black Box Models
Authors	Himabindu Lakkaraju, Ece Kamar, Rich Caruana, Jure Leskovec
Abstract	We propose Black Box Explanations through Transparent Approximations (BETA), a novel model agnostic framework for explaining the behavior of any black-box classifier by simultaneously optimizing for fidelity to the original model and interpretability of the explanation. To this end, we develop a novel objective function which allows us to learn (with optimality guarantees), a small number of compact decision sets each of which explains the behavior of the black box model in unambiguous, well-defined regions of feature space. Furthermore, our framework also is capable of accepting user input when generating these approximations, thus allowing users to interactively explore how the black-box model behaves in different subspaces that are of interest to the user. To the best of our knowledge, this is the first approach which can produce global explanations of the behavior of any given black box model through joint optimization of unambiguity, fidelity, and interpretability, while also allowing users to explore model behavior based on their preferences. Experimental evaluation with real-world datasets and user studies demonstrates that our approach can generate highly compact, easy-to-understand, yet accurate approximations of various kinds of predictive models compared to state-of-the-art baselines.
Tasks
Published	2017-07-04
URL	http://arxiv.org/abs/1707.01154v1
PDF	http://arxiv.org/pdf/1707.01154v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-explorable-approximations-of
Repo
Framework

Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration


Title	Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration
Authors	Zheng Tang, Gaoang Wang, Tao Liu, Young-Gun Lee, Adwin Jahn, Xu Liu, Xiaodong He, Jenq-Neng Hwang
Abstract	Tracking of multiple objects is an important application in AI City geared towards solving salient problems related to safety and congestion in an urban environment. Frequent occlusion in traffic surveillance has been a major problem in this research field. In this challenge, we propose a model-based vehicle localization method, which builds a kernel at each patch of the 3D deformable vehicle model and associates them with constraints in 3D space. The proposed method utilizes shape fitness evaluation besides color information to track vehicle objects robustly and efficiently. To build 3D car models in a fully unsupervised manner, we also implement evolutionary camera self-calibration from tracking of walking humans to automatically compute camera parameters. Additionally, the segmented foreground masks which are crucial to 3D modeling and camera self-calibration are adaptively refined by multiple-kernel feedback from tracking. For object detection/classification, the state-of-the-art single shot multibox detector (SSD) is adopted to train and test on the NVIDIA AI City Dataset. To improve the accuracy on categories with only few objects, like bus, bicycle and motorcycle, we also employ the pretrained model from YOLO9000 with multi-scale testing. We combine the results from SSD and YOLO9000 based on ensemble learning. Experiments show that our proposed tracking system outperforms both state-of-the-art of tracking by segmentation and tracking by detection.
Tasks	Calibration, Object Detection
Published	2017-08-22
URL	http://arxiv.org/abs/1708.06831v1
PDF	http://arxiv.org/pdf/1708.06831v1.pdf
PWC	https://paperswithcode.com/paper/multiple-kernel-based-vehicle-tracking-using
Repo
Framework

AI Oriented Large-Scale Video Management for Smart City: Technologies, Standards and Beyond


Title	AI Oriented Large-Scale Video Management for Smart City: Technologies, Standards and Beyond
Authors	Lingyu Duan, Yihang Lou, Shiqi Wang, Wen Gao, Yong Rui
Abstract	Deep learning has achieved substantial success in a series of tasks in computer vision. Intelligent video analysis, which can be broadly applied to video surveillance in various smart city applications, can also be driven by such powerful deep learning engines. To practically facilitate deep neural network models in the large-scale video analysis, there are still unprecedented challenges for the large-scale video data management. Deep feature coding, instead of video coding, provides a practical solution for handling the large-scale video surveillance data. To enable interoperability in the context of deep feature coding, standardization is urgent and important. However, due to the explosion of deep learning algorithms and the particularity of feature coding, there are numerous remaining problems in the standardization process. This paper envisions the future deep feature coding standard for the AI oriented large-scale video management, and discusses existing techniques, standards and possible solutions for these open problems.
Tasks
Published	2017-12-05
URL	http://arxiv.org/abs/1712.01432v1
PDF	http://arxiv.org/pdf/1712.01432v1.pdf
PWC	https://paperswithcode.com/paper/ai-oriented-large-scale-video-management-for
Repo
Framework

Implicit Causal Models for Genome-wide Association Studies


Title	Implicit Causal Models for Genome-wide Association Studies
Authors	Dustin Tran, David M. Blei
Abstract	Progress in probabilistic generative models has accelerated, developing richer models with neural architectures, implicit densities, and with scalable algorithms for their Bayesian inference. However, there has been limited progress in models that capture causal relationships, for example, how individual genetic factors cause major human diseases. In this work, we focus on two challenges in particular: How do we build richer causal models, which can capture highly nonlinear relationships and interactions between multiple causes? How do we adjust for latent confounders, which are variables influencing both cause and effect and which prevent learning of causal relationships? To address these challenges, we synthesize ideas from causality and modern probabilistic modeling. For the first, we describe implicit causal models, a class of causal models that leverages neural architectures with an implicit density. For the second, we describe an implicit causal model that adjusts for confounders by sharing strength across examples. In experiments, we scale Bayesian inference on up to a billion genetic measurements. We achieve state of the art accuracy for identifying causal factors: we significantly outperform existing genetics methods by an absolute difference of 15-45.3%.
Tasks	Bayesian Inference
Published	2017-10-30
URL	http://arxiv.org/abs/1710.10742v1
PDF	http://arxiv.org/pdf/1710.10742v1.pdf
PWC	https://paperswithcode.com/paper/implicit-causal-models-for-genome-wide
Repo
Framework

Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation


Title	Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation
Authors	Albert Gatt, Emiel Krahmer
Abstract	This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input. A survey of NLG is timely in view of the changes that the field has undergone over the past decade or so, especially in relation to new (usually data-driven) methods, as well as new applications of NLG technology. This survey therefore aims to (a) give an up-to-date synthesis of research on the core tasks in NLG and the architectures adopted in which such tasks are organised; (b) highlight a number of relatively recent research topics that have arisen partly as a result of growing synergies between NLG and other areas of artificial intelligence; (c) draw attention to the challenges in NLG evaluation, relating them to similar challenges faced in other areas of Natural Language Processing, with an emphasis on different evaluation methods and the relationships between them.
Tasks	Text Generation
Published	2017-03-29
URL	http://arxiv.org/abs/1703.09902v4
PDF	http://arxiv.org/pdf/1703.09902v4.pdf
PWC	https://paperswithcode.com/paper/survey-of-the-state-of-the-art-in-natural
Repo
Framework

Validity of Clusters Produced By kernel-$k$-means With Kernel-Trick


Title	Validity of Clusters Produced By kernel-$k$-means With Kernel-Trick
Authors	Mieczysław A. Kłopotek
Abstract	This paper corrects the proof of the Theorem 2 from the Gower’s paper \cite[page 5]{Gower:1982} as well as corrects the Theorem 7 from Gower’s paper \cite{Gower:1986}. The first correction is needed in order to establish the existence of the kernel function used commonly in the kernel trick e.g. for $k$-means clustering algorithm, on the grounds of distance matrix. The correction encompasses the missing if-part proof and dropping unnecessary conditions. The second correction deals with transformation of the kernel matrix into a one embeddable in Euclidean space.
Tasks
Published	2017-01-19
URL	http://arxiv.org/abs/1701.05335v3
PDF	http://arxiv.org/pdf/1701.05335v3.pdf
PWC	https://paperswithcode.com/paper/validity-of-clusters-produced-by-kernel-k
Repo
Framework

Spurious Local Minima are Common in Two-Layer ReLU Neural Networks


Title	Spurious Local Minima are Common in Two-Layer ReLU Neural Networks
Authors	Itay Safran, Ohad Shamir
Abstract	We consider the optimization problem associated with training simple ReLU neural networks of the form $\mathbf{x}\mapsto \sum_{i=1}^{k}\max{0,\mathbf{w}_i^\top \mathbf{x}}$ with respect to the squared loss. We provide a computer-assisted proof that even if the input distribution is standard Gaussian, even if the dimension is arbitrarily large, and even if the target values are generated by such a network, with orthonormal parameter vectors, the problem can still have spurious local minima once $6\le k\le 20$. By a concentration of measure argument, this implies that in high input dimensions, \emph{nearly all} target networks of the relevant sizes lead to spurious local minima. Moreover, we conduct experiments which show that the probability of hitting such local minima is quite high, and increasing with the network size. On the positive side, mild over-parameterization appears to drastically reduce such local minima, indicating that an over-parameterization assumption is necessary to get a positive result in this setting.
Tasks
Published	2017-12-24
URL	http://arxiv.org/abs/1712.08968v3
PDF	http://arxiv.org/pdf/1712.08968v3.pdf
PWC	https://paperswithcode.com/paper/spurious-local-minima-are-common-in-two-layer
Repo
Framework

Group Sparse Bayesian Learning for Active Surveillance on Epidemic Dynamics


Title	Group Sparse Bayesian Learning for Active Surveillance on Epidemic Dynamics
Authors	Hongbin Pei, Bo Yang, Jiming Liu, Lei Dong
Abstract	Predicting epidemic dynamics is of great value in understanding and controlling diffusion processes, such as infectious disease spread and information propagation. This task is intractable, especially when surveillance resources are very limited. To address the challenge, we study the problem of active surveillance, i.e., how to identify a small portion of system components as sentinels to effect monitoring, such that the epidemic dynamics of an entire system can be readily predicted from the partial data collected by such sentinels. We propose a novel measure, the gamma value, to identify the sentinels by modeling a sentinel network with row sparsity structure. We design a flexible group sparse Bayesian learning algorithm to mine the sentinel network suitable for handling both linear and non-linear dynamical systems by using the expectation maximization method and variational approximation. The efficacy of the proposed algorithm is theoretically analyzed and empirically validated using both synthetic and real-world data.
Tasks
Published	2017-11-21
URL	http://arxiv.org/abs/1712.00328v1
PDF	http://arxiv.org/pdf/1712.00328v1.pdf
PWC	https://paperswithcode.com/paper/group-sparse-bayesian-learning-for-active
Repo
Framework

Efficient Gender Classification Using a Deep LDA-Pruned Net


Title	Efficient Gender Classification Using a Deep LDA-Pruned Net
Authors	Qing Tian, Tal Arbel, James J. Clark
Abstract	Many real-time tasks, such as human-computer interaction, require fast and efficient facial gender classification. Although deep CNN nets have been very effective for a multitude of classification tasks, their high space and time demands make them impractical for personal computers and mobile devices without a powerful GPU. In this paper, we develop a 16-layer, yet lightweight, neural network which boosts efficiency while maintaining high accuracy. Our net is pruned from the VGG-16 model starting from the last convolutional (conv) layer where we find neuron activations are highly uncorrelated given the gender. Through Fisher’s Linear Discriminant Analysis (LDA), we show that this high decorrelation makes it safe to discard directly last conv layer neurons with high within-class variance and low between-class variance. Combined with either Support Vector Machines (SVM) or Bayesian classification, the reduced CNNs are capable of achieving comparable (or even higher) accuracies on the LFW and CelebA datasets than the original net with fully connected layers. On LFW, only four Conv5_3 neurons are able to maintain a comparably high recognition accuracy, which results in a reduction of total network size by a factor of 70X with a 11 fold speedup. Comparisons with a state-of-the-art pruning method as well as two smaller nets in terms of accuracy loss and convolutional layers pruning rate are also provided.
Tasks
Published	2017-04-20
URL	http://arxiv.org/abs/1704.06305v3
PDF	http://arxiv.org/pdf/1704.06305v3.pdf
PWC	https://paperswithcode.com/paper/efficient-gender-classification-using-a-deep
Repo
Framework


Title	An Online Ride-Sharing Path Planning Strategy for Public Vehicle Systems
Authors	Ming Zhu, Xiao-Yang Liu, Xiaodong Wang
Abstract	As efficient traffic-management platforms, public vehicle (PV) systems are envisioned to be a promising approach to solving traffic congestions and pollutions for future smart cities. PV systems provide online/dynamic peer-to-peer ride-sharing services with the goal of serving sufficient number of customers with minimum number of vehicles and lowest possible cost. A key component of the PV system is the online ride-sharing scheduling strategy. In this paper, we propose an efficient path planning strategy that focuses on a limited potential search area for each vehicle by filtering out the requests that violate passenger service quality level, so that the global search is reduced to local search. We analyze the performance of the proposed solution such as reduction ratio of computational complexity. Simulations based on the Manhattan taxi data set show that, the computing time is reduced by 22% compared with the exhaustive search method under the same service quality performance.
Tasks
Published	2017-12-27
URL	http://arxiv.org/abs/1712.09356v1
PDF	http://arxiv.org/pdf/1712.09356v1.pdf
PWC	https://paperswithcode.com/paper/an-online-ride-sharing-path-planning-strategy
Repo
Framework

Human Pose Estimation using Global and Local Normalization


Title	Human Pose Estimation using Global and Local Normalization
Authors	Ke Sun, Cuiling Lan, Junliang Xing, Wenjun Zeng, Dong Liu, Jingdong Wang
Abstract	In this paper, we address the problem of estimating the positions of human joints, i.e., articulated pose estimation. Recent state-of-the-art solutions model two key issues, joint detection and spatial configuration refinement, together using convolutional neural networks. Our work mainly focuses on spatial configuration refinement by reducing variations of human poses statistically, which is motivated by the observation that the scattered distribution of the relative locations of joints e.g., the left wrist is distributed nearly uniformly in a circular area around the left shoulder) makes the learning of convolutional spatial models hard. We present a two-stage normalization scheme, human body normalization and limb normalization, to make the distribution of the relative joint locations compact, resulting in easier learning of convolutional spatial models and more accurate pose estimation. In addition, our empirical results show that incorporating multi-scale supervision and multi-scale fusion into the joint detection network is beneficial. Experiment results demonstrate that our method consistently outperforms state-of-the-art methods on the benchmarks.
Tasks	Pose Estimation
Published	2017-09-21
URL	http://arxiv.org/abs/1709.07220v1
PDF	http://arxiv.org/pdf/1709.07220v1.pdf
PWC	https://paperswithcode.com/paper/human-pose-estimation-using-global-and-local
Repo
Framework

Underwater object classification using scattering transform of sonar signals


Title	Underwater object classification using scattering transform of sonar signals
Authors	Naoki Saito, David S. Weber
Abstract	In this paper, we apply the scattering transform (ST), a nonlinear map based off of a convolutional neural network (CNN), to classification of underwater objects using sonar signals. The ST formalizes the observation that the filters learned by a CNN have wavelet like structure. We achieve effective binary classification both on a real dataset of Unexploded Ordinance (UXOs), as well as synthetically generated examples. We also explore the effects on the waveforms with respect to changes in the object domain (e.g., translation, rotation, and acoustic impedance, etc.), and examine the consequences coming from theoretical results for the scattering transform. We show that the scattering transform is capable of excellent classification on both the synthetic and real problems, thanks to having more quasi-invariance properties that are well-suited to translation and rotation of the object.
Tasks	Object Classification
Published	2017-07-11
URL	http://arxiv.org/abs/1707.03133v3
PDF	http://arxiv.org/pdf/1707.03133v3.pdf
PWC	https://paperswithcode.com/paper/underwater-object-classification-using
Repo
Framework

Learning with Rethinking: Recurrently Improving Convolutional Neural Networks through Feedback


Title	Learning with Rethinking: Recurrently Improving Convolutional Neural Networks through Feedback
Authors	Xin Li, Zequn Jie, Jiashi Feng, Changsong Liu, Shuicheng Yan
Abstract	Recent years have witnessed the great success of convolutional neural network (CNN) based models in the field of computer vision. CNN is able to learn hierarchically abstracted features from images in an end-to-end training manner. However, most of the existing CNN models only learn features through a feedforward structure and no feedback information from top to bottom layers is exploited to enable the networks to refine themselves. In this paper, we propose a “Learning with Rethinking” algorithm. By adding a feedback layer and producing the emphasis vector, the model is able to recurrently boost the performance based on previous prediction. Particularly, it can be employed to boost any pre-trained models. This algorithm is tested on four object classification benchmark datasets: CIFAR-100, CIFAR-10, MNIST-background-image and ILSVRC-2012 dataset. These results have demonstrated the advantage of training CNN models with the proposed feedback mechanism.
Tasks	Object Classification
Published	2017-08-15
URL	http://arxiv.org/abs/1708.04483v1
PDF	http://arxiv.org/pdf/1708.04483v1.pdf
PWC	https://paperswithcode.com/paper/learning-with-rethinking-recurrently
Repo
Framework