检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Tang, Chufeng Sheng, Lu Zhang, Zhaoxiang Hu, Xiaolin State Key Laboratory of Intelligent Technology and Systems Institute for Artificial Intelligence Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua University College of Software Beihang University Institute of Automation Chinese Academy of Sciences

Pedestrian attribute recognition has been an emerging research topic in the area of video surveillance. To predict the existence of a particular attribute, it is demanded to localize the regions related to the attribute. However, in this task, the region annotations are not available. How to carve out these attribute-related regions remains challenging. Existing methods applied attribute-agnostic visual attention or heuristic body-part localization mechanisms to enhance the local feature representations, while neglecting to employ attributes to define local feature areas. We propose a flexible Attribute Localization Module (ALM) to adaptively discover the most discriminative regions and learns the regional features for each attribute at multiple levels. Moreover, a feature pyramid architecture is also introduced to enhance the attribute-specific localization at low-levels with high-level semantic guidance. The proposed framework does not require additional region annotations and can be trained end-to-end with multi-level deep supervision. Extensive experiments show that the proposed method achieves state-of-the-art results on three pedestrian attribute datasets, including PETA, RAP, and PA-100K. Copyright © 2019, The Authors. All rights reserved.

关键词： Heuristic methods

来源：评论

学校读者我要写书评

暂无评论

Learning domain-aware detection head with prompt tuning 23

Learning domain-aware detection head with prompt tuning

引用

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Haochen Li Rui Zhang Hantao Yao Xinkai Song Yifan Hao Yongwei Zhao Ling Li Yunji Chen Intelligent Software Research Center Institute of Software CAS Beijing China and University of Chinese Academy of Sciences Beijing China State Key Lab of Processors Institute of Computing Technology CAS Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation CAS Beijing China State Key Lab of Processors Institute of Computing Technology CAS Beijing China and University of Chinese Academy of Sciences Beijing China

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. However, existing methods focus on reducing the domain bias of the detection backbone by inferring a discriminative visual encoder, while ignoring the domain bias in the detection head. Inspired by the high generalization of vision-language models (VLMs), applying a VLM as the robust detection backbone following a domain-aware detection head is a reasonable way to learn the discriminative detector for each domain, rather than reducing the domain bias in traditional methods. To achieve the above issue, we thus propose a novel DAOD framework named Domain-Aware detection head with Prompt tuning (DA-Pro), which applies the learnable domain-adaptive prompt to generate the dynamic detection head for each domain. Formally, the domain-adaptive prompt consists of the domain-invariant tokens, domain-specific tokens, and the domain-related textual description along with the class label. Furthermore, two constraints between the source and target domains are applied to ensure that the domain-adaptive prompt can capture the domains-shared and domain-specific knowledge. A prompt ensemble strategy is also proposed to reduce the effect of prompt disturbance. Comprehensive experiments over multiple cross-domain adaptation tasks demonstrate that using the domain-adaptive prompt can produce an effectively domain-related detection head for boosting domain-adaptive object detection. Our code is available at https://***/Therock90421/DA-Pro.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Interpretability Analysis of Travel Decision Learning in Cyber-Physical-Social-systems

An Interpretability Analysis of Travel Decision Learning in ...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Miao Guo Peijun Ye Xudong Liu Sheng Liu Gang Xiong Liguo Zhang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Faculty of Information and Technology Beijing University of Technology Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Chinese Academy of Sciences Beijing China

In the few decades, the rise of Internet and social media has fundamentally changed the management, control, and operation modes of modern engineering and social systems like defense, energy, critical health care and ... 详细信息

关键词： Deep learning Social networking (online) Scalability Perturbation methods Neurons Transportation Transforms

来源：评论

学校读者我要写书评

暂无评论

Joint Face Alignment and 3D Face Reconstruction with Efficient Convolution Neural Networks

Joint Face Alignment and 3D Face Reconstruction with Efficie...

引用

International Conference on Pattern Recognition

作者： Keqiang Li Huaiyu Wu Xiuqin Shang Zhen Shen Gang Xiong Xisong Dong Bin Hu Fei-Yue Wang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

3D face reconstruction from a single 2D facial image is a challenging and concerned problem. Recent methods based on CNN typically aim to learn parameters of 3D Morphable Model (3DMM) from 2D images to render face alignment and 3D face reconstruction. Most algorithms are designed for faces with small, medium yaw angles, which is extremely challenging to align faces in large poses. At the same time, they are not efficient usually. The main challenge is that it takes time to determine the parameters accurately. In order to address this challenge with the goal of improving performance, this paper proposes a novel and efficient end-to-end framework. We design an efficient and lightweight network model combined with Depthwise Separable Convolution and Muti-scale Representation, Lightweight Attention Mechanism, named Mobile-FRNet. Simultaneously, different loss functions are used to constrain and optimize 3DMM parameters and 3D vertices during training to improve the performance of the network. Meanwhile, extensive experiments on the challenging datasets show that our method significantly improves the accuracy of face alignment and 3D face reconstruction. Model parameters and complexity of our method are also improved greatly.

关键词： Training Solid modeling Three-dimensional displays Convolution Face recognition Neural networks Complexity theory

来源：评论

学校读者我要写书评

暂无评论

A Geometry Aware Diffusion Model for 3D Point Cloud Generation

A Geometry Aware Diffusion Model for 3D Point Cloud Generati...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Ao Zhang Zhen Shen Qihang Fang Jian Yang Gang Xiong Xisong Dong State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Point clouds have increasingly become the preferred representation for various visual and graphical applications. Denoising diffusion probability models (DDPMs) have demonstrated remarkable applications in areas such as 3D point cloud generation. Furthermore, the ability to generate or reconstruct high-resolution, high-fidelity point clouds stands as a pivotal requirement within this domain. To this end, we propose a geometry aware diffusion model for 3D shape generation. Considering that the global latent shape space overlooks the inherent topology and fine-grained information within the 3D shape itself, we introduce a geometry latent space that operates in a cascaded relationship with the global shape latent space. This latent space combines the global shape latent with the geometry latent space. To generate high-quality point clouds, we conduct training on the geometry latent space, which yields superior results compared to training solely on the global shape latent space. Specifically, we represent the point cloud as a set of unordered point representations with positional embedding. We further employ a geometry aware attention block to model global geometric relationships and retaining local detail features, capturing the inductive bias of the 3D geometric structure of the point cloud. We conduct experiments across various ShapeNet benchmarks, and our approach has demonstrated substantial advancements in the generation of point clouds when compared to the baseline.

关键词： Point cloud compression Geometry Training Solid modeling Visualization Three-dimensional displays Shape Noise reduction Diffusion models Topology

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

International Conference on Parallel and Distributed systems (ICPADS)

作者： Yan Zeng ChengChuang Huang YiJie Ni ChunBao Zhou JiLin Zhang Jue Wang MingYao Zhou MeiTing Xue YunQuan Zhang School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou China Data Security Governance Zhejiang Engineering Research Center Hangzhou China School of ITMO Joint Institute Hangzhou Dianzi University Hangzhou China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing China HuaWei State Key Laboratory of Computer Architecture Institute of Computing Technology of the Chinese Academy of Sciences Beijing China

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network’s dataflow graph and device cluster’s topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating adjacency-constrained subgoals in hierarchical reinforcement learning 20

Generating adjacency-constrained subgoals in hierarchical re...

引用

Proceedings of the 34th International Conference on Neural Information Processing systems

作者： Tianren Zhang Shangqi Guo Tian Tan Xiaolin Hu Feng Chen Department of Automation Tsinghua University Department of Civil and Environmental Engineering Stanford University Department of Computer Science and Technology Tsinghua University and Beijing National Research Center for Information Science and Technology and State Key Laboratory of Intelligent Technology and Systems Department of Automation Tsinghua University and Beijing Innovation Center for Future Chip and LSBDPA Beijing Key Laboratory

ISBN: (纸本)9781713829546

Goal-conditioned hierarchical reinforcement learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the goal space, is often large. Searching in a large goal space poses difficulties for both high-level subgoal generation and low-level policy learning. In this paper, we show that this problem can be effectively alleviated by restricting the high-level action space from the whole goal space to a k-step adjacent region of the current state using an adjacency constraint. We theoretically prove that the proposed adjacency constraint preserves the optimal hierarchical policy in deterministic MDPs, and show that this constraint can be practically implemented by training an adjacency network that can discriminate between adjacent and non-adjacent subgoals. Experimental results on discrete and continuous control tasks show that incorporating the adjacency constraint improves the performance of state-of-the-art HRL approaches in both deterministic and stochastic environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast Calibration of Agent-Based Model using Mean-Field Approach

Fast Calibration of Agent-Based Model using Mean-Field Appro...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Wanze Lu Gang Xiong Xudong Liu Sheng Liu Peijun Ye Liguo Zhang Faculty of Information and Technology Beijing University of Technology Beijing China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Chinese Academy of Sciences Beijing China

Calibration of simulation system is an important step to establish a reliable simulation system. In this paper, based on the existing mean field calibration theory, a new fast calibration method for complex urban traffic system based on mean field method is discussed by establishing the relationship between the macroscopic observation quantity and the proxy microscopic parameters. This method makes use of the machine learning method, and reduces the dimension of the state vector in the discrete time period, so that the dimension of the macroscopic state transition matrix is lower, and then reduces the computational complexity of the system calibration. Finally, the calibration results of the simulation system were verified by SUMO traffic simulation software.

关键词： Visualization Computational modeling Microscopy Digital twin Machine learning Traffic control Reliability theory

来源：评论

学校读者我要写书评

暂无评论

research on Attention-Based Predictive Model in Multi-Agent Reinforcement Learning

Research on Attention-Based Predictive Model in Multi-Agent ...

引用

Chinese Automation Congress (CAC)

作者： Weixin Hong Huaiyu Wu Zhen Shen Gang Xiong Bin Hu Xisong Dong Fei-Yue Wang The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

Agent actions planning is a challenging problem in multi-agent reinforcement learning. Recent methods typically build their predictive models by full connection layers, but the shortage of utilizing action and observation information in complex multi-agent environment limits the performance of those methods. To address this issue, we propose a novel predictive model based on self-attention mechanism which can effectively use information in the environment. Specifically, we use the MADDPG algorithm to make a dataset where the input is the observations and actions and the output is the predicted observations and rewards. We also introduce the multi-head attention mechanism into the predictive model so that the predictive model can better combine different information for prediction. We perform extensive experiments to assess the proposed method and compare it with the representative baseline approach. Results demonstrate that our method outperforms competitors with higher accuracy in different tasks. Our implementation will be publicly available.

关键词： Automation Reinforcement learning Predictive models Prediction algorithms Planning Task analysis

来源：评论

学校读者我要写书评

暂无评论

Parallel systems Framework: A Safe and Efficient Testbed for Unmanned Ships

Parallel Systems Framework: A Safe and Efficient Testbed for...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Long Fu Zhen Shen Xisong Dong Yunjun Han Shuguang Yang Gang Xiong Fei-Yue Wang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China Schoool of Rail Transportation Shandong Jiaotong University Jinan China State Key Laboratory for Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350349252

ISBN: (纸本)9798350349269

In this study, unmanned ships test platform based on the parallel systems framework is proposed to improve the test efficiency and accuracy of unmanned ships in complex ocean environment. The parallel intelligence theory and ACP approach, the efficient interaction between virtual and real environment is achieved, which provides more comprehensive and accurate data for unmanned ships testing. Future research will further expand the scope of virtual environment simulation and improve systems accuracy and response speed to a wider range of unmanned ships test requirements.

关键词： Accuracy Oceans Virtual environments Digital twins Marine vehicles Testing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：