July 27, 2019

2936 words 14 mins read

Paper Group ANR 744

Online Convex Optimization with Stochastic Constraints. ADA: A Game-Theoretic Perspective on Data Augmentation for Object Detection. Predicting Auction Price of Vehicle License Plate with Deep Recurrent Neural Network. Abstract Syntax Networks for Code Generation and Semantic Parsing. DeepFeat: A Bottom Up and Top Down Saliency Model Based on Deep …

Online Convex Optimization with Stochastic Constraints


Title	Online Convex Optimization with Stochastic Constraints
Authors	Hao Yu, Michael J. Neely, Xiaohan Wei
Abstract	This paper considers online convex optimization (OCO) with stochastic constraints, which generalizes Zinkevich’s OCO over a known simple fixed set by introducing multiple stochastic functional constraints that are i.i.d. generated at each round and are disclosed to the decision maker only after the decision is made. This formulation arises naturally when decisions are restricted by stochastic environments or deterministic environments with noisy observations. It also includes many important problems as special cases, such as OCO with long term constraints, stochastic constrained convex optimization, and deterministic constrained convex optimization. To solve this problem, this paper proposes a new algorithm that achieves $O(\sqrt{T})$ expected regret and constraint violations and $O(\sqrt{T}\log(T))$ high probability regret and constraint violations. Experiments on a real-world data center scheduling problem further verify the performance of the new algorithm.
Tasks
Published	2017-08-12
URL	http://arxiv.org/abs/1708.03741v1
PDF	http://arxiv.org/pdf/1708.03741v1.pdf
PWC	https://paperswithcode.com/paper/online-convex-optimization-with-stochastic
Repo
Framework

ADA: A Game-Theoretic Perspective on Data Augmentation for Object Detection


Title	ADA: A Game-Theoretic Perspective on Data Augmentation for Object Detection
Authors	Sima Behpour, Kris M. Kitani, Brian D. Ziebart
Abstract	The use of random perturbations of ground truth data, such as random translation or scaling of bounding boxes, is a common heuristic used for data augmentation that has been shown to prevent overfitting and improve generalization. Since the design of data augmentation is largely guided by reported best practices, it is difficult to understand if those design choices are optimal. To provide a more principled perspective, we develop a game-theoretic interpretation of data augmentation in the context of object detection. We aim to find an optimal adversarial perturbations of the ground truth data (i.e., the worst case perturbations) that forces the object bounding box predictor to learn from the hardest distribution of perturbed examples for better test-time performance. We establish that the game theoretic solution, the Nash equilibrium, provides both an optimal predictor and optimal data augmentation distribution. We show that our adversarial method of training a predictor can significantly improve test time performance for the task of object detection. On the ImageNet object detection task, our adversarial approach improves performance by over 16% compared to the best performing data augmentation method
Tasks	Data Augmentation, Object Detection
Published	2017-10-21
URL	http://arxiv.org/abs/1710.07735v2
PDF	http://arxiv.org/pdf/1710.07735v2.pdf
PWC	https://paperswithcode.com/paper/ada-a-game-theoretic-perspective-on-data
Repo
Framework

Predicting Auction Price of Vehicle License Plate with Deep Recurrent Neural Network


Title	Predicting Auction Price of Vehicle License Plate with Deep Recurrent Neural Network
Authors	Vinci Chow
Abstract	In Chinese societies, superstition is of paramount importance, and vehicle license plates with desirable numbers can fetch very high prices in auctions. Unlike other valuable items, license plates are not allocated an estimated price before auction. I propose that the task of predicting plate prices can be viewed as a natural language processing (NLP) task, as the value depends on the meaning of each individual character on the plate and its semantics. I construct a deep recurrent neural network (RNN) to predict the prices of vehicle license plates in Hong Kong, based on the characters on a plate. I demonstrate the importance of having a deep network and of retraining. Evaluated on 13 years of historical auction prices, the deep RNN’s predictions can explain over 80 percent of price variations, outperforming previous models by a significant margin. I also demonstrate how the model can be extended to become a search engine for plates and to provide estimates of the expected price distribution.
Tasks
Published	2017-01-30
URL	https://arxiv.org/abs/1701.08711v5
PDF	https://arxiv.org/pdf/1701.08711v5.pdf
PWC	https://paperswithcode.com/paper/predicting-auction-price-of-vehicle-license
Repo
Framework

Abstract Syntax Networks for Code Generation and Semantic Parsing


Title	Abstract Syntax Networks for Code Generation and Semantic Parsing
Authors	Maxim Rabinovich, Mitchell Stern, Dan Klein
Abstract	Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs are represented as abstract syntax trees (ASTs) and constructed by a decoder with a dynamically-determined modular structure paralleling the structure of the output tree. On the benchmark Hearthstone dataset for code generation, our model obtains 79.2 BLEU and 22.7% exact match accuracy, compared to previous state-of-the-art values of 67.1 and 6.1%. Furthermore, we perform competitively on the Atis, Jobs, and Geo semantic parsing datasets with no task-specific engineering.
Tasks	Code Generation, Semantic Parsing
Published	2017-04-25
URL	http://arxiv.org/abs/1704.07535v1
PDF	http://arxiv.org/pdf/1704.07535v1.pdf
PWC	https://paperswithcode.com/paper/abstract-syntax-networks-for-code-generation
Repo
Framework

DeepFeat: A Bottom Up and Top Down Saliency Model Based on Deep Features of Convolutional Neural Nets


Title	DeepFeat: A Bottom Up and Top Down Saliency Model Based on Deep Features of Convolutional Neural Nets
Authors	Ali Mahdi, Jun Qin
Abstract	A deep feature based saliency model (DeepFeat) is developed to leverage the understanding of the prediction of human fixations. Traditional saliency models often predict the human visual attention relying on few level image cues. Although such models predict fixations on a variety of image complexities, their approaches are limited to the incorporated features. In this study, we aim to provide an intuitive interpretation of convolu- tional neural network deep features by combining low and high level visual factors. We exploit four evaluation metrics to evaluate the correspondence between the proposed framework and the ground-truth fixations. The key findings of the results demon- strate that the DeepFeat algorithm, incorporation of bottom up and top down saliency maps, outperforms the individual bottom up and top down approach. Moreover, in comparison to nine 9 state-of-the-art saliency models, our proposed DeepFeat model achieves satisfactory performance based on all four evaluation metrics.
Tasks
Published	2017-09-08
URL	http://arxiv.org/abs/1709.02495v1
PDF	http://arxiv.org/pdf/1709.02495v1.pdf
PWC	https://paperswithcode.com/paper/deepfeat-a-bottom-up-and-top-down-saliency
Repo
Framework

Revisiting Spectral Graph Clustering with Generative Community Models


Title	Revisiting Spectral Graph Clustering with Generative Community Models
Authors	Pin-Yu Chen, Lingfei Wu
Abstract	The methodology of community detection can be divided into two principles: imposing a network model on a given graph, or optimizing a designed objective function. The former provides guarantees on theoretical detectability but falls short when the graph is inconsistent with the underlying model. The latter is model-free but fails to provide quality assurance for the detected communities. In this paper, we propose a novel unified framework to combine the advantages of these two principles. The presented method, SGC-GEN, not only considers the detection error caused by the corresponding model mismatch to a given graph, but also yields a theoretical guarantee on community detectability by analyzing Spectral Graph Clustering (SGC) under GENerative community models (GCMs). SGC-GEN incorporates the predictability on correct community detection with a measure of community fitness to GCMs. It resembles the formulation of supervised learning problems by enabling various community detection loss functions and model mismatch metrics. We further establish a theoretical condition for correct community detection using the normalized graph Laplacian matrix under a GCM, which provides a novel data-driven loss function for SGC-GEN. In addition, we present an effective algorithm to implement SGC-GEN, and show that the computational complexity of SGC-GEN is comparable to the baseline methods. Our experiments on 18 real-world datasets demonstrate that SGC-GEN possesses superior and robust performance compared to 6 baseline methods under 7 representative clustering metrics.
Tasks	Community Detection, Graph Clustering, Spectral Graph Clustering
Published	2017-09-14
URL	http://arxiv.org/abs/1709.04594v2
PDF	http://arxiv.org/pdf/1709.04594v2.pdf
PWC	https://paperswithcode.com/paper/revisiting-spectral-graph-clustering-with
Repo
Framework

Practical Attacks Against Graph-based Clustering


Title	Practical Attacks Against Graph-based Clustering
Authors	Yizheng Chen, Yacin Nadji, Athanasios Kountouras, Fabian Monrose, Roberto Perdisci, Manos Antonakakis, Nikolaos Vasiloglou
Abstract	Graph modeling allows numerous security problems to be tackled in a general way, however, little work has been done to understand their ability to withstand adversarial attacks. We design and evaluate two novel graph attacks against a state-of-the-art network-level, graph-based detection system. Our work highlights areas in adversarial machine learning that have not yet been addressed, specifically: graph-based clustering techniques, and a global feature space where realistic attackers without perfect knowledge must be accounted for (by the defenders) in order to be practical. Even though less informed attackers can evade graph clustering with low cost, we show that some practical defenses are possible.
Tasks	Graph Clustering
Published	2017-08-29
URL	http://arxiv.org/abs/1708.09056v1
PDF	http://arxiv.org/pdf/1708.09056v1.pdf
PWC	https://paperswithcode.com/paper/practical-attacks-against-graph-based
Repo
Framework

Counterfactuals, indicative conditionals, and negation under uncertainty: Are there cross-cultural differences?


Title	Counterfactuals, indicative conditionals, and negation under uncertainty: Are there cross-cultural differences?
Authors	Niki Pfeifer, Hiroshi Yama
Abstract	In this paper we study selected argument forms involving counterfactuals and indicative conditionals under uncertainty. We selected argument forms to explore whether people with an Eastern cultural background reason differently about conditionals compared to Westerners, because of the differences in the location of negations. In a 2x2 between-participants design, 63 Japanese university students were allocated to four groups, crossing indicative conditionals and counterfactuals, and each presented in two random task orders. The data show close agreement between the responses of Easterners and Westerners. The modal responses provide strong support for the hypothesis that conditional probability is the best predictor for counterfactuals and indicative conditionals. Finally, the grand majority of the responses are probabilistically coherent, which endorses the psychological plausibility of choosing coherence-based probability logic as a rationality framework for psychological reasoning research.
Tasks
Published	2017-03-09
URL	http://arxiv.org/abs/1703.03255v1
PDF	http://arxiv.org/pdf/1703.03255v1.pdf
PWC	https://paperswithcode.com/paper/counterfactuals-indicative-conditionals-and
Repo
Framework

Accurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regions


Title	Accurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regions
Authors	Jie Chen, Junhui Hou, Yun Ni, Lap-Pui Chau
Abstract	Depth estimation is a fundamental problem for light field photography applications. Numerous methods have been proposed in recent years, which either focus on crafting cost terms for more robust matching, or on analyzing the geometry of scene structures embedded in the epipolar-plane images. Significant improvements have been made in terms of overall depth estimation error; however, current state-of-the-art methods still show limitations in handling intricate occluding structures and complex scenes with multiple occlusions. To address these challenging issues, we propose a very effective depth estimation framework which focuses on regularizing the initial label confidence map and edge strength weights. Specifically, we first detect partially occluded boundary regions (POBR) via superpixel based regularization. Series of shrinkage/reinforcement operations are then applied on the label confidence map and edge strength weights over the POBR. We show that after weight manipulations, even a low-complexity weighted least squares model can produce much better depth estimation than state-of-the-art methods in terms of average disparity error rate, occlusion boundary precision-recall rate, and the preservation of intricate visual features.
Tasks	Depth Estimation
Published	2017-08-07
URL	http://arxiv.org/abs/1708.01964v1
PDF	http://arxiv.org/pdf/1708.01964v1.pdf
PWC	https://paperswithcode.com/paper/accurate-light-field-depth-estimation-with
Repo
Framework

Head Detection with Depth Images in the Wild


Title	Head Detection with Depth Images in the Wild
Authors	Diego Ballotta, Guido Borghi, Roberto Vezzani, Rita Cucchiara
Abstract	Head detection and localization is a demanding task and a key element for many computer vision applications, like video surveillance, Human Computer Interaction and face analysis. The stunning amount of work done for detecting faces on RGB images, together with the availability of huge face datasets, allowed to setup very effective systems on that domain. However, due to illumination issues, infrared or depth cameras may be required in real applications. In this paper, we introduce a novel method for head detection on depth images that exploits the classification ability of deep learning approaches. In addition to reduce the dependency on the external illumination, depth images implicitly embed useful information to deal with the scale of the target objects. Two public datasets have been exploited: the first one, called Pandora, is used to train a deep binary classifier with face and non-face images. The second one, collected by Cornell University, is used to perform a cross-dataset test during daily activities in unconstrained environments. Experimental results show that the proposed method overcomes the performance of state-of-art methods working on depth images.
Tasks	Head Detection
Published	2017-07-21
URL	http://arxiv.org/abs/1707.06786v2
PDF	http://arxiv.org/pdf/1707.06786v2.pdf
PWC	https://paperswithcode.com/paper/head-detection-with-depth-images-in-the-wild
Repo
Framework

Deformable Classifiers


Title	Deformable Classifiers
Authors	Jiajun Shen, Yali Amit
Abstract	Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transformations. In this paper, we design a framework for training deformable classifiers, where latent transformation variables are introduced, and a transformation of the object image to a reference instantiation is computed in terms of the classifier output, separately for each class. The classifier outputs for each class, after transformation, are compared to yield the final decision. As a by-product of the classification this yields a transformation of the input object to a reference pose, which can be used for downstream tasks such as the computation of object support. We apply a two-step training mechanism for our framework, which alternates between optimizing over the latent transformation variables and the classifier parameters to minimize the loss function. We show that multilayer perceptrons, also known as deep networks, are well suited for this approach and achieve state of the art results on the rotated MNIST and the Google Earth dataset, and produce competitive results on MNIST and CIFAR-10 when training on smaller subsets of training data.
Tasks	Object Recognition
Published	2017-12-18
URL	http://arxiv.org/abs/1712.06715v1
PDF	http://arxiv.org/pdf/1712.06715v1.pdf
PWC	https://paperswithcode.com/paper/deformable-classifiers
Repo
Framework

A low cost non-wearable gaze detection system based on infrared image processing


Title	A low cost non-wearable gaze detection system based on infrared image processing
Authors	Ehsan Arbabi, Mohammad Shabani, Ali Yarigholi
Abstract	Human eye gaze detection plays an important role in various fields, including human-computer interaction, virtual reality and cognitive science. Although different relatively accurate systems of eye tracking and gaze detection exist, they are usually either too expensive to be bought for low cost applications or too complex to be implemented easily. In this article, we propose a non-wearable system for eye tracking and gaze detection with low complexity and cost. The proposed system provides a medium accuracy which makes it suitable for general applications in which low cost and easy implementation is more important than achieving very precise gaze detection. The proposed method includes pupil and marker detection using infrared image processing, and gaze evaluation using an interpolation-based strategy. The interpolation-based strategy exploits the positions of the detected pupils and markers in a target captured image and also in some previously captured training images for estimating the position of a point that the user is gazing at. The proposed system has been evaluated by three users in two different lighting conditions. The experimental results show that the accuracy of this low cost system can be between 90% and 100% for finding major gazing directions.
Tasks	Eye Tracking
Published	2017-09-12
URL	http://arxiv.org/abs/1709.03717v1
PDF	http://arxiv.org/pdf/1709.03717v1.pdf
PWC	https://paperswithcode.com/paper/a-low-cost-non-wearable-gaze-detection-system
Repo
Framework

Analog CMOS-based Resistive Processing Unit for Deep Neural Network Training


Title	Analog CMOS-based Resistive Processing Unit for Deep Neural Network Training
Authors	Seyoung Kim, Tayfun Gokmen, Hyung-Min Lee, Wilfried E. Haensch
Abstract	Recently we have shown that an architecture based on resistive processing unit (RPU) devices has potential to achieve significant acceleration in deep neural network (DNN) training compared to today’s software-based DNN implementations running on CPU/GPU. However, currently available device candidates based on non-volatile memory technologies do not satisfy all the requirements to realize the RPU concept. Here, we propose an analog CMOS-based RPU design (CMOS RPU) which can store and process data locally and can be operated in a massively parallel manner. We analyze various properties of the CMOS RPU to evaluate the functionality and feasibility for acceleration of DNN training.
Tasks
Published	2017-06-20
URL	http://arxiv.org/abs/1706.06620v1
PDF	http://arxiv.org/pdf/1706.06620v1.pdf
PWC	https://paperswithcode.com/paper/analog-cmos-based-resistive-processing-unit
Repo
Framework

Distributed Mapper


Title	Distributed Mapper
Authors	Mustafa Hajij, Basem Assiri, Paul Rosen
Abstract	The construction of Mapper has emerged in the last decade as a powerful and effective topological data analysis tool that approximates and generalizes other topological summaries, such as the Reeb graph, the contour tree, split, and joint trees. In this paper we study the parallel analysis of the construction of Mapper. We give a provably correct algorithm to distribute Mapper on a set of processors and discuss the performance results that compare our approach to a reference sequential Mapper implementation. We report the performance experiments that demonstrate the efficiency of our method.
Tasks	Topological Data Analysis
Published	2017-12-11
URL	http://arxiv.org/abs/1712.03660v2
PDF	http://arxiv.org/pdf/1712.03660v2.pdf
PWC	https://paperswithcode.com/paper/distributed-mapper
Repo
Framework

Learning of Human-like Algebraic Reasoning Using Deep Feedforward Neural Networks


Title	Learning of Human-like Algebraic Reasoning Using Deep Feedforward Neural Networks
Authors	Cheng-Hao Cai, Dengfeng Ke, Yanyan Xu, Kaile Su
Abstract	There is a wide gap between symbolic reasoning and deep learning. In this research, we explore the possibility of using deep learning to improve symbolic reasoning. Briefly, in a reasoning system, a deep feedforward neural network is used to guide rewriting processes after learning from algebraic reasoning examples produced by humans. To enable the neural network to recognise patterns of algebraic expressions with non-deterministic sizes, reduced partial trees are used to represent the expressions. Also, to represent both top-down and bottom-up information of the expressions, a centralisation technique is used to improve the reduced partial trees. Besides, symbolic association vectors and rule application records are used to improve the rewriting processes. Experimental results reveal that the algebraic reasoning examples can be accurately learnt only if the feedforward neural network has enough hidden layers. Also, the centralisation technique, the symbolic association vectors and the rule application records can reduce error rates of reasoning. In particular, the above approaches have led to 4.6% error rate of reasoning on a dataset of linear equations, differentials and integrals.
Tasks
Published	2017-04-25
URL	http://arxiv.org/abs/1704.07503v1
PDF	http://arxiv.org/pdf/1704.07503v1.pdf
PWC	https://paperswithcode.com/paper/learning-of-human-like-algebraic-reasoning
Repo
Framework