检索结果-内蒙古大学图书馆

Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation

学校读者我要写书评

暂无评论

Cross-domain Object Detection through Coarse-to-Fine Feature...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yangtao Zheng Di Huang Songtao Liu Yunhong Wang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University State Key Laboratory of Software Development Environment Beihang University School of Computer Science and Engineering Beihang University Beijing China

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Recent years have witnessed great progress in deep learning based object detection. However, due to the domain shift problem, applying off-the-shelf detectors to an unseen domain leads to significant performance drop. To address such an issue, this paper proposes a novel coarse-to-fine feature adaptation approach to cross-domain object detection. At the coarse-grained stage, different from the rough image-level or instance-level feature alignment used in the literature, foreground regions are extracted by adopting the attention mechanism, and aligned according to their marginal distributions via multi-layer adversarial learning in the common feature space. At the fine-grained stage, we conduct conditional distribution alignment of foregrounds by minimizing the distance of global prototypes with the same category but from different domains. Thanks to this coarse-to-fine feature adaptation, domain knowledge in foreground regions can be effectively transferred. Extensive experiments are carried out in various cross-domain detection scenarios. The results are state-of-the-art, which demonstrate the broad applicability and effectiveness of the proposed approach.

关键词： Feature extraction Subspace constraints Object detection Detectors Task analysis Semantics Prototypes

Representation Learning of Graphs Using Graph Convolutional Multilayer Networks Based on Motifs

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xing Wei, Wei Feng, Xiangnan Liu, Xue Zheng, Zhiming School of Mathematical Science Beihang University Beijing China Key Laboratory of Mathematics Informatics Behavioral Semantics Ministry of Education China Peng Cheng Laboratory Shenzhen Guangdong China and Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China School of Mathematical Science Beihang University Beijing China Key Laboratory of Mathematics Informatics Behavioral Semantics Ministry of Education China and Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

The graph structure is a commonly used data storage mode, and it turns out that the low-dimensional embedded representation of nodes in the graph is extremely useful in various typical tasks, such as node classification, link prediction, etc. However, most of the existing approaches start from the binary relationship (i.e., edges) in the graph and have not leveraged the higher order local structure (i.e., motifs) of the graph. Here, we propose mGCMN – a novel framework which utilizes node feature information and the higher order local structure of the graph to effectively generate node embeddings for previously unseen data. Through research we have found that different types of networks have different key motifs. And the advantages of our method over the baseline methods have been demonstrated in a large number of experiments on citation network and social network datasets. At the same time, a positive correlation between increase of the classification accuracy and the clustering coefficient is revealed. It is believed that using high order structural information can truly manifest the potential of the network, which will greatly improve the learning efficiency of the graph neural network and promote a brand-new learning mode establishment. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks

A self-supervised mixed-curvature graph neural network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sun, Li Zhang, Zhongbao Ye, Junda Peng, Hao Zhang, Jiawei Su, Sen Yu, Philip S. School of Control and Computer Engineering North China Electric Power University Beijing102206 China School of Computer Science Beijing University of Posts and Telecommunications China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Ifm Lab Department of Computer Science University of California DavisCA United States Department of Computer Science University of Illinois at Chicago IL United States

Graph representation learning received increasing attentions in recent years. Most of the existing methods ignore the complexity of the graph structures and restrict graphs in a single constant-curvature representation space, which is only suitable to particular kinds of graph structure indeed. Additionally, these methods follow the supervised or semisupervised learning paradigm, and thereby notably limit their deployment on the unlabeled graphs in real applications. To address these aforementioned limitations, we take the first attempt to study the self-supervised graph representation learning in the mixed-curvature spaces. In this paper, we present a novel Self-supervised Mixed-curvature Graph Neural Network (SELFMGNN). To capture the complex graph structures, we construct a mixed-curvature space via the Cartesian product of multiple Riemannian component spaces, and design hierarchical attention mechanisms for learning and fusing graph representations across these component spaces. To enable the self-supervisd learning, we propose a novel dual contrastive approach. The constructed mixed-curvature space actually provides multiple Riemannian views for the contrastive learning. We introduce a Riemannian projector to reveal these views, and utilize a welldesigned Riemannian discriminator for the single-view and cross-view contrastive learning within and across the Riemannian views. Finally, extensive experiments show that SELFMGNN captures the complex graph structures and outperforms state-of-the-art baselines. © 2021, CC BY-NC-SA.

关键词： Graph neural networks

Codebleu: a method for automatic evaluation of code synthesis

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ren, Shuo Guo, Daya Lu, Shuai Zhou, Long Liu, Shujie Tang, Duyu Sundaresan, Neel Zhou, Ming Blanco, Ambrosio Ma, Shuai SKLSDE Lab Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing China Sun Yat-sen University China Peking University China Microsoft United States

Evaluation metrics play a vital role in the growth of an area as it defines the standard of distinguishing between good and bad models. In the area of code synthesis, the commonly used evaluation metric is BLEU or perfect accuracy, but they are not suitable enough to evaluate codes, because BLEU is originally designed to evaluate natural language, neglecting important syntactic and semantic features of codes, and perfect accuracy is too strict thus it underestimates different outputs with the same semantic logic. To remedy this, we introduce a new automatic evaluation metric, dubbed CodeBLEU. It absorbs the strength of BLEU in the n-gram match, and further injects code syntax via abstract syntax trees (AST) and code semantics via data-flow. We conduct experiments by evaluating the correlation coefficient between CodeBLEU and quality scores assigned by the programmers on three code synthesis tasks, i.e., text-to-code, code translation, and code refinement. Experimental results show that, our proposed CodeBLEU can achieve a better correlation with programmer assigned scores compared with BLEU and accuracy. Copyright © 2020, The Authors. All rights reserved.

关键词： Syntactics

Cross-domain object detection through coarse-to-fine feature adaptation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zheng, Yangtao Huang, Di Liu, Songtao Wang, Yunhong Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University State Key Laboratory of Software Development Environment Beihang University School of Computer Science and Engineering Beihang University Beijing100191 China

Recent years have witnessed great progress in deep learning based object detection. However, due to the domain shift problem, applying off-the-shelf detectors to an unseen domain leads to significant performance drop. To address such an issue, this paper proposes a novel coarseto-fine feature adaptation approach to cross-domain object detection. At the coarse-grained stage, different from the rough image-level or instance-level feature alignment used in the literature, foreground regions are extracted by adopting the attention mechanism, and aligned according to their marginal distributions via multi-layer adversarial learning in the common feature space. At the fine-grained stage, we conduct conditional distribution alignment of foregrounds by minimizing the distance of global prototypes with the same category but from different domains. Thanks to this coarse-to-fine feature adaptation, domain knowledge in foreground regions can be effectively transferred. Extensive experiments are carried out in various cross-domain detection scenarios. The results are state-of-the-art, which demonstrate the broad applicability and effectiveness of the proposed approach. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Dou, Yingtong Liu, Zhiwei Sun, Li Deng, Yutong Peng, Hao Yu, Philip S. Department of Computer Science University of Illinois at Chicago United States School of Computer Science Beijing University of Posts and Telecommunications China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China

Graph Neural Networks (GNNs) have been widely applied to fraud detection problems in recent years, revealing the suspiciousness of nodes by aggregating their neighborhood information via different relations. However, few prior works have noticed the camouflage behavior of fraudsters, which could hamper the performance of GNN-based fraud detectors during the aggregation process. In this paper, we introduce two types of camouflages based on recent empirical studies, i.e., the feature camouflage and the relation camouflage. Existing GNNs have not addressed these two camouflages, which results in their poor performance in fraud detection problems. Alternatively, we propose a new model named CAmouflage-REsistant GNN (CARE-GNN), to enhance the GNN aggregation process with three unique modules against camouflages. Concretely, we first devise a label-aware similarity measure to find informative neighboring nodes. Then, we leverage reinforcement learning (RL) to find the optimal amounts of neighbors to be selected. Finally, the selected neighbors across different relations are aggregated together. Comprehensive experiments on two real-world fraud datasets demonstrate the effectiveness of the RL algorithm. The proposed CARE-GNN also outperforms state-of-the-art GNNs and GNN-based fraud detectors. We integrate all GNN-based fraud detectors as an open-source toolbox1. The CARE-GNN code and datasets are available at https://***/YingtongDou/CARE-GNN. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks

Distributed State Estimation for Nonlinear Networked System with Correlated Noises

学校读者我要写书评

暂无评论

Distributed State Estimation for Nonlinear Networked System ...

International Conference on Control, Automation, Robotics and Vision (ICARCV)

作者： Yuan Liang Sibo Hu Xiwang Dong Qingdong Li Zhang Ren School of Automation Science and Electrical Engineering Beihang University Beijing P. R. China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing P. R. China

ISBN: (数字)9781728177090

ISBN: (纸本)9781728177106

In this paper, the problem of distributed state estimation for nonlinear networked system with correlated noises is investigated. First, a distributed weighted consensus-based cubature information filtering algorithm is designed, of which the goal is to achieve accurate estimated states with the presence of correlated noises in a fully distributed fashion. Then based on the statistical linear approximation method, it is further proved that, the estimated states of the proposed filtering algorithm are consistent. Finally, the improved performance of the proposed filtering algorithm are confirmed by the numerical simulation.

关键词： Sensors Sensor fusion Noise measurement Sensor systems Wireless sensor networks State estimation Kalman filters

Adaptive NMS: Refining Pedestrian Detection in a Crowd

学校读者我要写书评

暂无评论

Adaptive NMS: Refining Pedestrian Detection in a Crowd

IEEE/CVF Conference on Computer Vision and Pattern Recognition

作者： Songtao Liu Di Huang Yunhong Wang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

ISBN: (纸本)9781728132945

Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel Non-Maximum Suppression (NMS) algorithm to better refine the bounding boxes given by detectors. The contributions are threefold: (1) we propose adaptive-NMS, which applies a dynamic suppression threshold to an instance, according to the target density;(2) we design an efficient subnetwork to learn density scores, which can be conveniently embedded into both the single-stage and two-stage detectors;and (3) we achieve state of the art results on the CityPersons and CrowdHuman benchmarks.

关键词： state of the art Crowding Pedestrians bounding boxes Purification detector Refining Subnetwork Self tuning

Hierarchical Decomposition and Prescribed Performance Bound based Adaptive Control for Leader-Follower Formation of Uncertain Nonholonomic Mobile Robots

学校读者我要写书评

暂无评论

Hierarchical Decomposition and Prescribed Performance Bound ...

International Conference on Control, Automation, Robotics and Vision (ICARCV)

作者： Jiajun Shen Wei Wang Jinhu Lü Chao Deng School of Automation Science and Electrical Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China School of Electrical and Electronic Engineering Nanyang Technological University Singapore

ISBN: (数字)9781728177090

ISBN: (纸本)9781728177106

In this paper, the cooperative formation control problem is investigated for multiple two-wheeled mobile robots with unknown parameters. By combining the hierarchical decomposition and prescribed performance bound (PPB) technique, distributed adaptive formation controllers are designed based on dynamic surface control. It is proved in the Lyapunov sense that all the closed-loop signals are semi-globally bounded and the tracking error converges to a compact set, which can be made arbitrarily small by adjusting the design parameters appropriately. Furthermore, formation maintenance, connectivity preservation and collision avoidance can be achieved with the proposed control scheme. Simulations are also given to verify the effectiveness of the theoretical results.

关键词： Mobile robots Robot kinematics Wheels Collision avoidance Directed graphs Kinematics Information processing