October 16, 2019

3080 words 15 mins read

Paper Group ANR 976

Learning Deep Sketch Abstraction. Decision Forests Induce Characteristic Kernels. Learning convex polytopes with margin. Fully Convolutional Grasp Detection Network with Oriented Anchor Box. A Robot Localization Framework Using CNNs for Object Detection and Pose Estimation. Building Models for Biopathway Dynamics Using Intrinsic Dimensionality Anal …

Learning Deep Sketch Abstraction


Title	Learning Deep Sketch Abstraction
Authors	Umar Riaz Muhammad, Yongxin Yang, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales
Abstract	Human free-hand sketches have been studied in various contexts including sketch recognition, synthesis and fine-grained sketch-based image retrieval (FG-SBIR). A fundamental challenge for sketch analysis is to deal with drastically different human drawing styles, particularly in terms of abstraction level. In this work, we propose the first stroke-level sketch abstraction model based on the insight of sketch abstraction as a process of trading off between the recognizability of a sketch and the number of strokes used to draw it. Concretely, we train a model for abstract sketch generation through reinforcement learning of a stroke removal policy that learns to predict which strokes can be safely removed without affecting recognizability. We show that our abstraction model can be used for various sketch analysis tasks including: (1) modeling stroke saliency and understanding the decision of sketch recognition models, (2) synthesizing sketches of variable abstraction for a given category, or reference object instance in a photo, and (3) training a FG-SBIR model with photos only, bypassing the expensive photo-sketch pair collection step.
Tasks	Image Retrieval, Sketch-Based Image Retrieval, Sketch Recognition
Published	2018-04-13
URL	http://arxiv.org/abs/1804.04804v1
PDF	http://arxiv.org/pdf/1804.04804v1.pdf
PWC	https://paperswithcode.com/paper/learning-deep-sketch-abstraction
Repo
Framework

Decision Forests Induce Characteristic Kernels


Title	Decision Forests Induce Characteristic Kernels
Authors	Cencheng Shen, Joshua T. Vogelstein
Abstract	Decision forests are popular tools for classification and regression. These forests naturally produce proximity matrices measuring how often each pair of observations lies in the same leaf node. Recently it has been demonstrated that these proximity matrices can be thought of as kernels, connecting the decision forest literature to the extensive kernel machine literature. While other kernels are known to have strong theoretical properties, such as being characteristic kernels, no similar result is available for any decision forest based kernel. We show that a decision forest induced proximity can be made into a characteristic kernel, which can be used within an independence test to obtain a universally consistent test. We therefore empirically evaluate this kernel on a suite of 12 high-dimensional independence test settings: the decision forest induced kernel is shown to typically achieve substantially higher power than other methods.
Tasks
Published	2018-11-30
URL	http://arxiv.org/abs/1812.00029v1
PDF	http://arxiv.org/pdf/1812.00029v1.pdf
PWC	https://paperswithcode.com/paper/decision-forests-induce-characteristic
Repo
Framework

Learning convex polytopes with margin


Title	Learning convex polytopes with margin
Authors	Lee-Ad Gottlieb, Eran Kaufman, Aryeh Kontorovich, Gabriel Nivasch
Abstract	We present an improved algorithm for properly learning convex polytopes in the realizable PAC setting from data with a margin. Our learning algorithm constructs a consistent polytope as an intersection of about $t \log t$ halfspaces with margins in time polynomial in $t$ (where $t$ is the number of halfspaces forming an optimal polytope). We also identify distinct generalizations of the notion of margin from hyperplanes to polytopes and investigate how they relate geometrically; this result may be of interest beyond the learning setting.
Tasks
Published	2018-05-24
URL	http://arxiv.org/abs/1805.09719v2
PDF	http://arxiv.org/pdf/1805.09719v2.pdf
PWC	https://paperswithcode.com/paper/learning-convex-polytopes-with-margin
Repo
Framework

Fully Convolutional Grasp Detection Network with Oriented Anchor Box


Title	Fully Convolutional Grasp Detection Network with Oriented Anchor Box
Authors	Xinwen Zhou, Xuguang Lan, Hanbo Zhang, Zhiqiang Tian, Yang Zhang, Nanning Zheng
Abstract	In this paper, we present a real-time approach to predict multiple grasping poses for a parallel-plate robotic gripper using RGB images. A model with oriented anchor box mechanism is proposed and a new matching strategy is used during the training process. An end-to-end fully convolutional neural network is employed in our work. The network consists of two parts: the feature extractor and multi-grasp predictor. The feature extractor is a deep convolutional neural network. The multi-grasp predictor regresses grasp rectangles from predefined oriented rectangles, called oriented anchor boxes, and classifies the rectangles into graspable and ungraspable. On the standard Cornell Grasp Dataset, our model achieves an accuracy of 97.74% and 96.61% on image-wise split and object-wise split respectively, and outperforms the latest state-of-the-art approach by 1.74% on image-wise split and 0.51% on object-wise split.
Tasks
Published	2018-03-06
URL	http://arxiv.org/abs/1803.02209v1
PDF	http://arxiv.org/pdf/1803.02209v1.pdf
PWC	https://paperswithcode.com/paper/fully-convolutional-grasp-detection-network
Repo
Framework

A Robot Localization Framework Using CNNs for Object Detection and Pose Estimation


Title	A Robot Localization Framework Using CNNs for Object Detection and Pose Estimation
Authors	Lukas Hoyer, Christoph Steup, Sanaz Mostaghim
Abstract	External localization is an essential part for the indoor operation of small or cost-efficient robots, as they are used, for example, in swarm robotics. We introduce a two-stage localization and instance identification framework for arbitrary robots based on convolutional neural networks. Object detection is performed on an external camera image of the operation zone providing robot bounding boxes for an identification and orientation estimation convolutional neural network. Additionally, we propose a process to generate the necessary training data. The framework was evaluated with 3 different robot types and various identification patterns. We have analyzed the main framework hyperparameters providing recommendations for the framework operation settings. We achieved up to 98% mAP@IOU0.5 and only 1.6{\deg} orientation error, running with a frame rate of 50 Hz on a GPU.
Tasks	Object Detection, Pose Estimation
Published	2018-10-03
URL	http://arxiv.org/abs/1810.01665v1
PDF	http://arxiv.org/pdf/1810.01665v1.pdf
PWC	https://paperswithcode.com/paper/a-robot-localization-framework-using-cnns-for
Repo
Framework

Building Models for Biopathway Dynamics Using Intrinsic Dimensionality Analysis


Title	Building Models for Biopathway Dynamics Using Intrinsic Dimensionality Analysis
Authors	Emilia M. Wysocka, Valery Dzutsati, Tirthankar Bandyopadhyay, Laura Condon, Sahil Garg
Abstract	An important task for many if not all the scientific domains is efficient knowledge integration, testing and codification. It is often solved with model construction in a controllable computational environment. In spite of that, the throughput of in-silico simulation-based observations become similarly intractable for thorough analysis. This is especially the case in molecular biology, which served as a subject for this study. In this project, we aimed to test some approaches developed to deal with the curse of dimensionality. Among these we found dimension reduction techniques especially appealing. They can be used to identify irrelevant variability and help to understand critical processes underlying high-dimensional datasets. Additionally, we subjected our data sets to nonlinear time series analysis, as those are well established methods for results comparison. To investigate the usefulness of dimension reduction methods, we decided to base our study on a concrete sample set. The example was taken from the domain of systems biology concerning dynamic evolution of sub-cellular signaling. Particularly, the dataset relates to the yeast pheromone pathway and is studied in-silico with a stochastic model. The model reconstructs signal propagation stimulated by a mating pheromone. In the paper, we elaborate on the reason of multidimensional analysis problem in the context of molecular signaling, and next, we introduce the model of choice, simulation details and obtained time series dynamics. A description of used methods followed by a discussion of results and their biological interpretation finalize the paper.
Tasks	Dimensionality Reduction, Time Series, Time Series Analysis
Published	2018-04-29
URL	http://arxiv.org/abs/1804.11005v3
PDF	http://arxiv.org/pdf/1804.11005v3.pdf
PWC	https://paperswithcode.com/paper/building-models-for-biopathway-dynamics-using
Repo
Framework

Personalized Human Activity Recognition Using Convolutional Neural Networks


Title	Personalized Human Activity Recognition Using Convolutional Neural Networks
Authors	Seyed Ali Rokni, Marjan Nourollahi, Hassan Ghasemzadeh
Abstract	A major barrier to the personalized Human Activity Recognition using wearable sensors is that the performance of the recognition model drops significantly upon adoption of the system by new users or changes in physical/ behavioral status of users. Therefore, the model needs to be retrained by collecting new labeled data in the new context. In this study, we develop a transfer learning framework using convolutional neural networks to build a personalized activity recognition model with minimal user supervision.
Tasks	Activity Recognition, Human Activity Recognition, Transfer Learning
Published	2018-01-25
URL	http://arxiv.org/abs/1801.08252v1
PDF	http://arxiv.org/pdf/1801.08252v1.pdf
PWC	https://paperswithcode.com/paper/personalized-human-activity-recognition-using
Repo
Framework

ViZDoom: DRQN with Prioritized Experience Replay, Double-Q Learning, & Snapshot Ensembling


Title	ViZDoom: DRQN with Prioritized Experience Replay, Double-Q Learning, & Snapshot Ensembling
Authors	Christopher Schulze, Marcus Schulze
Abstract	ViZDoom is a robust, first-person shooter reinforcement learning environment, characterized by a significant degree of latent state information. In this paper, double-Q learning and prioritized experience replay methods are tested under a certain ViZDoom combat scenario using a competitive deep recurrent Q-network (DRQN) architecture. In addition, an ensembling technique known as snapshot ensembling is employed using a specific annealed learning rate to observe differences in ensembling efficacy under these two methods. Annealed learning rates are important in general to the training of deep neural network models, as they shake up the status-quo and counter a model’s tending towards local optima. While both variants show performance exceeding those of built-in AI agents of the game, the known stabilizing effects of double-Q learning are illustrated, and priority experience replay is again validated in its usefulness by showing immediate results early on in agent development, with the caveat that value overestimation is accelerated in this case. In addition, some unique behaviors are observed to develop for priority experience replay (PER) and double-Q (DDQ) variants, and snapshot ensembling of both PER and DDQ proves a valuable method for improving performance of the ViZDoom Marine.
Tasks	Q-Learning
Published	2018-01-03
URL	http://arxiv.org/abs/1801.01000v1
PDF	http://arxiv.org/pdf/1801.01000v1.pdf
PWC	https://paperswithcode.com/paper/vizdoom-drqn-with-prioritized-experience
Repo
Framework

Decentralized Differentially Private Without-Replacement Stochastic Gradient Descent


Title	Decentralized Differentially Private Without-Replacement Stochastic Gradient Descent
Authors	Richeng Jin, Xiaofan He, Huaiyu Dai
Abstract	While machine learning has achieved remarkable results in a wide variety of domains, the training of models often requires large datasets that may need to be collected from different individuals. As sensitive information may be contained in the individual’s dataset, sharing training data may lead to severe privacy concerns. Therefore, there is a compelling need to develop privacy-aware machine learning methods, for which one effective approach is to leverage the generic framework of differential privacy. Considering that stochastic gradient descent (SGD) is one of the mostly adopted methods for large-scale machine learning problems, two decentralized differentially private SGD algorithms are proposed in this work. Particularly, we focus on SGD without replacement due to its favorable structure for practical implementation. In addition, both privacy and convergence analysis are provided for the proposed algorithms. Finally, extensive experiments are performed to verify the theoretical results and demonstrate the effectiveness of the proposed algorithms.
Tasks
Published	2018-09-08
URL	http://arxiv.org/abs/1809.02727v3
PDF	http://arxiv.org/pdf/1809.02727v3.pdf
PWC	https://paperswithcode.com/paper/decentralized-differentially-private-without
Repo
Framework

Expressway visibility estimation based on image entropy and piecewise stationary time series analysis


Title	Expressway visibility estimation based on image entropy and piecewise stationary time series analysis
Authors	Xiaogang Cheng, Guoqing Liu, Anders Hedman, Kun Wang, Haibo Li
Abstract	Vision-based methods for visibility estimation can play a critical role in reducing traffic accidents caused by fog and haze. To overcome the disadvantages of current visibility estimation methods, we present a novel data-driven approach based on Gaussian image entropy and piecewise stationary time series analysis (SPEV). This is the first time that Gaussian image entropy is used for estimating atmospheric visibility. To lessen the impact of landscape and sunshine illuminance on visibility estimation, we used region of interest (ROI) analysis and took into account relative ratios of image entropy, to improve estimation accuracy. We assume fog and haze cause blurred images and that fog and haze can be considered as a piecewise stationary signal. We used piecewise stationary time series analysis to construct the piecewise causal relationship between image entropy and visibility. To obtain a real-world visibility measure during fog and haze, a subjective assessment was established through a study with 36 subjects who performed visibility observations. Finally, a total of two million videos were used for training the SPEV model and validate its effectiveness. The videos were collected from the constantly foggy and hazy Tongqi expressway in Jiangsu, China. The contrast model of visibility estimation was used for algorithm performance comparison, and the validation results of the SPEV model were encouraging as 99.14% of the relative errors were less than 10%.
Tasks	Time Series, Time Series Analysis
Published	2018-04-08
URL	http://arxiv.org/abs/1804.04601v1
PDF	http://arxiv.org/pdf/1804.04601v1.pdf
PWC	https://paperswithcode.com/paper/expressway-visibility-estimation-based-on
Repo
Framework

Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks


Title	Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks
Authors	Shi Yin, Qinmu Peng, Hongming Li, Zhengqiang Zhang, Xinge You, Susan L. Furth, Gregory E. Tasian, Yong Fan
Abstract	It remains challenging to automatically segment kidneys in clinical ultrasound (US) images due to the kidneys’ varied shapes and image intensity distributions, although semi-automatic methods have achieved promising performance. In this study, we propose subsequent boundary distance regression and pixel classification networks to segment the kidneys, informed by the fact that the kidney boundaries have relatively homogenous texture patterns across images. Particularly, we first use deep neural networks pre-trained for classification of natural images to extract high-level image features from US images, then these features are used as input to learn kidney boundary distance maps using a boundary distance regression network, and finally the predicted boundary distance maps are classified as kidney pixels or non-kidney pixels using a pixel classification network in an end-to-end learning fashion. We also adopted a data-augmentation method based on kidney shape registration to generate enriched training data from a small number of US images with manually segmented kidney labels. Experimental results have demonstrated that our method could effectively improve the performance of automatic kidney segmentation, significantly better than deep learning-based pixel classification networks.
Tasks	Data Augmentation
Published	2018-11-12
URL	http://arxiv.org/abs/1811.04815v3
PDF	http://arxiv.org/pdf/1811.04815v3.pdf
PWC	https://paperswithcode.com/paper/subsequent-boundary-distance-regression-and
Repo
Framework

Improved Regularity Model-based EDA for Many-objective Optimization


Title	Improved Regularity Model-based EDA for Many-objective Optimization
Authors	Yanan Sun, Gary G. Yen, Zhang Yi
Abstract	The performance of multi-objective evolutionary algorithms deteriorates appreciably in solving many-objective optimization problems which encompass more than three objectives. One of the known rationales is the loss of selection pressure which leads to the selected parents not generating promising offspring towards Pareto-optimal front with diversity. Estimation of distribution algorithms sample new solutions with a probabilistic model built from the statistics extracting over the existing solutions so as to mitigate the adverse impact of genetic operators. In this paper, an improved regularity-based estimation of distribution algorithm is proposed to effectively tackle unconstrained many-objective optimization problems. In the proposed algorithm, \emph{diversity repairing mechanism} is utilized to mend the areas where need non-dominated solutions with a closer proximity to the Pareto-optimal front. Then \emph{favorable solutions} are generated by the model built from the regularity of the solutions surrounding a group of representatives. These two steps collectively enhance the selection pressure which gives rise to the superior convergence of the proposed algorithm. In addition, dimension reduction technique is employed in the decision space to speed up the estimation search of the proposed algorithm. Finally, by assigning the Pareto-optimal solutions to the uniformly distributed reference vectors, a set of solutions with excellent diversity and convergence is obtained. To measure the performance, NSGA-III, GrEA, MOEA/D, HypE, MBN-EDA, and RM-MEDA are selected to perform comparison experiments over DTLZ and DTLZ$^-$ test suites with $3$-, $5$-, $8$-, $10$-, and $15$-objective. Experimental results quantified by the selected performance metrics reveal that the proposed algorithm shows considerable competitiveness in addressing unconstrained many-objective optimization problems.
Tasks	Dimensionality Reduction
Published	2018-02-24
URL	http://arxiv.org/abs/1802.08788v1
PDF	http://arxiv.org/pdf/1802.08788v1.pdf
PWC	https://paperswithcode.com/paper/improved-regularity-model-based-eda-for-many
Repo
Framework

Efficient Online Portfolio with Logarithmic Regret


Title	Efficient Online Portfolio with Logarithmic Regret
Authors	Haipeng Luo, Chen-Yu Wei, Kai Zheng
Abstract	We study the decades-old problem of online portfolio management and propose the first algorithm with logarithmic regret that is not based on Cover’s Universal Portfolio algorithm and admits much faster implementation. Specifically Universal Portfolio enjoys optimal regret $\mathcal{O}(N\ln T)$ for $N$ financial instruments over $T$ rounds, but requires log-concave sampling and has a large polynomial running time. Our algorithm, on the other hand, ensures a slightly larger but still logarithmic regret of $\mathcal{O}(N^2(\ln T)^4)$, and is based on the well-studied Online Mirror Descent framework with a novel regularizer that can be implemented via standard optimization methods in time $\mathcal{O}(TN^{2.5})$ per round. The regret of all other existing works is either polynomial in $T$ or has a potentially unbounded factor such as the inverse of the smallest price relative.
Tasks
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07430v2
PDF	http://arxiv.org/pdf/1805.07430v2.pdf
PWC	https://paperswithcode.com/paper/efficient-online-portfolio-with-logarithmic
Repo
Framework

Detecting Adversarial Perturbations with Saliency


Title	Detecting Adversarial Perturbations with Saliency
Authors	Chiliang Zhang, Zhimou Yang, Zuochang Ye
Abstract	In this paper we propose a novel method for detecting adversarial examples by training a binary classifier with both origin data and saliency data. In the case of image classification model, saliency simply explain how the model make decisions by identifying significant pixels for prediction. A model shows wrong classification output always learns wrong features and shows wrong saliency as well. Our approach shows good performance on detecting adversarial perturbations. We quantitatively evaluate generalization ability of the detector, showing that detectors trained with strong adversaries perform well on weak adversaries.
Tasks	Image Classification
Published	2018-03-23
URL	http://arxiv.org/abs/1803.08773v1
PDF	http://arxiv.org/pdf/1803.08773v1.pdf
PWC	https://paperswithcode.com/paper/detecting-adversarial-perturbations-with
Repo
Framework

Trajectory-based Radical Analysis Network for Online Handwritten Chinese Character Recognition


Title	Trajectory-based Radical Analysis Network for Online Handwritten Chinese Character Recognition
Authors	Jianshu Zhang, Yixing Zhu, Jun Du, Lirong Dai
Abstract	Recently, great progress has been made for online handwritten Chinese character recognition due to the emergence of deep learning techniques. However, previous research mostly treated each Chinese character as one class without explicitly considering its inherent structure, namely the radical components with complicated geometry. In this study, we propose a novel trajectory-based radical analysis network (TRAN) to firstly identify radicals and analyze two-dimensional structures among radicals simultaneously, then recognize Chinese characters by generating captions of them based on the analysis of their internal radicals. The proposed TRAN employs recurrent neural networks (RNNs) as both an encoder and a decoder. The RNN encoder makes full use of online information by directly transforming handwriting trajectory into high-level features. The RNN decoder aims at generating the caption by detecting radicals and spatial structures through an attention model. The manner of treating a Chinese character as a two-dimensional composition of radicals can reduce the size of vocabulary and enable TRAN to possess the capability of recognizing unseen Chinese character classes, only if the corresponding radicals have been seen. Evaluated on CASIA-OLHWDB database, the proposed approach significantly outperforms the state-of-the-art whole-character modeling approach with a relative character error rate (CER) reduction of 10%. Meanwhile, for the case of recognition of 500 unseen Chinese characters, TRAN can achieve a character accuracy of about 60% while the traditional whole-character method has no capability to handle them.
Tasks
Published	2018-01-22
URL	http://arxiv.org/abs/1801.10109v1
PDF	http://arxiv.org/pdf/1801.10109v1.pdf
PWC	https://paperswithcode.com/paper/trajectory-based-radical-analysis-network-for
Repo
Framework