检索结果-内蒙古大学图书馆

Multi-Agent Deep Reinforcement Learning based Collaborative Computation Offloading in Vehicular Edge Networks

学校读者我要写书评

暂无评论

Multi-Agent Deep Reinforcement Learning based Collaborative ...

International Conference on Distributed Computing Systems Workshop

作者： Hao Wang Huan Zhou Liang Zhao Xuxun Liu Victor C. M. Leung Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering College of Computer and Information Technology China Three Gorges University Yichang China College of Electronic and Information Engineering South China University of Technology Guangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Recently, to cope with the long communication distance and unreliability of cloud-based computing architectures, mobile edge computing has emerged as a solution with great promise. This pattern extends cloud-based services towards the vehicular edge network and enables vehicular tasks to be offloaded to intermediate Roadside Units (RSUs) directly. However, as more and more tasks are offloaded to RSUs, the computation capacity of a single RSU becomes insufficient. Without edge cooperation, overall resource utilization and effectiveness are prone to being underutilized. To address this issue, this paper investigates a collaborative computation offloading scheme where adjacent RSUs can process offloaded tasks collaboratively rather than individually. First, we explore a vehicular edge network where the bilateral synergy between RSUs is leveraged. In particular, we incorporate a price-based incentive mechanism into the resource allocation process to promote overall resource utilization. Second, considering the time-varying system conditions and uncertain resource requirements, the optimization problem is approximated as a Markov Decision Process (MDP) and extended to a multi-agent system. Finally, we propose a Multi-agent Deep deterministic policy gradient-based computation Offloading and resource Allocation scheme (MDOA) to solve the corresponding problem. Simulation results show that the proposed MDOA can not only achieve a higher long-term utility of RSUs but also have better performance than other baselines in different scenarios.

关键词：

MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ding, Yanbo Zhuang, Shaobin Li, Kunchang Yue, Zhengrong Qiao, Yu Wang, Yali Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Shanghai Artificial Intelligence Laboratory China Shanghai Jiao Tong University China

Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To tackle this limitation, we introduce a generic AI system, namely MUSES, for 3D-controllable image generation from user queries. Specifically, our MUSES develops a progressive workflow with three key components, including (1) Layout Manager for 2D-to-3D layout lifting, (2) Model Engineer for 3D object acquisition and calibration, (3) Image Artist for 3D-to-2D image rendering. By mimicking the collaboration of human professionals, this multi-modal agent pipeline facilitates the effective and automatic creation of images with 3D-controllable objects, through an explainable integration of top-down planning and bottom-up generation. Additionally, existing benchmarks lack detailed descriptions of complex Copyright © 2024, The Authors. All rights reserved.

关键词： 3D modeling

Degradation Conditioned GAN for Degradation Generalization of Face Restoration Models

学校读者我要写书评

暂无评论

Degradation Conditioned GAN for Degradation Generalization o...

IEEE International Conference on Image Processing

作者： Song Qi Wu Shi Guojing Ge Liang Chang Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences School of Artificial Intelligence Beijing Normal University Institute of Automation Chinese Academy of Sciences

Face restoration models are usually trained on synthetic degraded data to output an image that matches the clean version of itself. Most previous methods use a single model to deal with all the degradation levels, resulting in a domain generalization problem. We explore the value of degradation information and propose a Degradation Conditioned GAN (DeCGAN). The architecture consists of modulated convolution, bias, and fusion modules, inspired by deblurring, denoising and super-resolution. The whole network can be modulated by the degradation levels to achieve delicate and precise restoration effects. Experiments are conducted on conventional and modulated face restoration tasks. DeCGAN can achieve more faithful restoration and better metrics (FID, LPIPS, etc.) than previous methods do. Moreover, our model performs well on real-world low-quality face images.

关键词：

Reflash Dropout in Image Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kong, Xiangtao Liu, Xina Gu, Jinjin Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab. Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China The University of Sydney Australia Shanghai AI Laboratory Shanghai China

Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR). As a classic regression problem, SR exhibits a different behaviour as high-level tasks and is sensitive to the dropout operation. However, in this paper, we show that appropriate usage of dropout benefits SR networks and improves the generalization ability. Specifically, dropout is better embedded at the end of the network and is significantly helpful for the multi-degradation settings. This discovery breaks our common sense and inspires us to explore its working mechanism. We further use two analysis tools – one is from a recent network interpretation work, and the other is specially designed for this task. The analysis results provide side proofs to our experimental findings and show us a new perspective to understand SR networks. Copyright © 2021, The Authors. All rights reserved.

关键词： Optical resolving power

Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3DAD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

Clustering-based Discriminative Locality Alignment for Face Gender Recognition

学校读者我要写书评

暂无评论

Clustering-based Discriminative Locality Alignment for Face ...

IEEE/RSJ International Conference on Intelligent robotics and Systems

作者： Duo Chen Jun Cheng Dacheng Tao College of Communication Engineering Chongqing University Chongqing 400044 China. He is also with the Shenzhen Key Laboratory of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences. Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 China. He is also with the Chinese University of Hong Kong and Guangdong Provincial Key Laboratory of Robotics and Intelligent System. Center for Quantum Computation and Intelligent System Faculty of Engineering and Information Technology University of Technology Sydney New South Wales 2007 Australia.

ISBN: (数字)9781467317368

ISBN: (纸本)9781467317375

To facilitate human-robot interactions, human gender information is very important. Motivated by the success of manifold learning for visual recognition, we present a novel clustering-based discriminative locality alignment (CDLA) algorithm to discover the low-dimensional intrinsic submanifold from the embedding high-dimensional ambient space for improving the face gender recognition performance. In particular, CDLA exploits the global geometry through k-means clustering, extracts the discriminative information through margin maximization and explores the local geometry through intra cluster sample concentration. These three properties uniquely characterize CDLA for face gender recognition. The experimental results obtained from the FERET data sets suggest the superiority of the proposed method in terms of recognition speed and accuracy by comparing with several representative methods.

关键词： FERET CDLA comparing Recognition (Psychology) Gender Global geometry Compare Face Face

Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Donghao Li, Jialin Li, Jinpeng Huang, Jiancheng Nie, Qiang Liu, Yong Gao, Bin-Bin Wang, Qiong Heng, Pheng-Ann Chen, Guangyong The Chinese University of Hong Kong Hong Kong Tencent YouTu Lab Shenzhen China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Guangzhou China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Zhejiang Lab Hangzhou China

Large-scale well-annotated datasets are of great importance for training an effective object detector. However, obtaining accurate bounding box annotations is laborious and demanding. Unfortunately, the resultant noisy bounding boxes could cause corrupt supervision signals and thus diminish detection performance. Motivated by the observation that the real ground-truth is usually situated in the aggregation region of the proposals assigned to a noisy ground-truth, we propose DIStribution-aware CalibratiOn (DISCO) to model the spatial distribution of proposals for calibrating supervision signals. In DISCO, spatial distribution modeling is performed to statistically extract the potential locations of objects. Based on the modeled distribution, three distribution-aware techniques, i.e., distribution-aware proposal augmentation (DA-Aug), distribution-aware box refinement (DA-Ref), and distribution-aware confidence estimation (DA-Est), are developed to improve classification, localization, and interpretability, respectively. Extensive experiments demonstrate that DISCO can achieve SOTA performance in this task, especially at high noise levels. Code is available at https://***/Correr-Zhou/DISCO. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

RTM3D: Real-time monocular 3D detection from object keypoints for autonomous driving

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Peixuan Zhao, Huaici Liu, Pengfei Cao, Feidao Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences University of Chinese Academy of Sciences Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Key Lab of Image Understanding and Computer Vision Liaoning Province

In this work, we propose an efficient and accurate monocular 3D detection framework in single shot. Most successful 3D detectors take the projection constraint from the 3D bounding box to the 2D box as an important component. Four edges of a 2D box provide only four constraints and the performance deteriorates dramatically with the small error of the 2D detector. Different from these approaches, our method predicts the nine perspective keypoints of a 3D bounding box in image space, and then utilize the geometric relationship of 3D and 2D perspectives to recover the dimension, location, and orientation in 3D space. In this method, the properties of the object can be predicted stably even when the estimation of keypoints is very noisy, which enables us to obtain fast detection speed with a small architecture. Training our method only uses the 3D properties of the object without the need for external networks or supervision data. Our method is the first real-time system for monocular image 3D detection while achieves state-ofthe-art performance on the KITTI benchmark. Code will be released at https://***/Banconxuan/RTM3D. Copyright © 2020, The Authors. All rights reserved.

关键词： Real time systems

Terrain-Aware Quadrupedal Locomotion via Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shi, Haojie Zhu, Qingxu Han, Lei Chi, Wanchao Li, Tingguang Meng, Max Q.-H. Tencent Robotics X China The Chinese University of Hong Kong Hong Kong Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong The Department of Electrical and Computer Engineering The University of Alberta Canada

In nature, legged animals have developed the ability to adapt to challenging terrains through perception, allowing them to plan safe body and foot trajectories in advance, which leads to safe and energy-efficient locomotion. Inspired by this observation, we present a novel approach to train a Deep Neural Network (DNN) policy that integrates proprioceptive and exteroceptive states with a parameterized trajectory generator for quadruped robots to traverse rough terrains. Our key idea is to use a DNN policy that can modify the parameters of the trajectory generator, such as foot height and frequency, to adapt to different terrains. To encourage the robot to step on safe regions and save energy consumption, we propose foot terrain reward and lifting foot height reward, respectively. By incorporating these rewards, our method can learn a safer and more efficient terrain-aware locomotion policy that can move a quadruped robot flexibly in any direction. To evaluate the effectiveness of our approach, we conduct simulation experiments on challenging terrains, including stairs, stepping stones, and poles. The simulation results demonstrate that our approach can successfully direct the robot to traverse such tough terrains in any direction. Furthermore, we validate our method on a real legged robot, which learns to traverse stepping stones with gaps over 25.5cm. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks