检索结果-内蒙古大学图书馆

Learning-Based Low-Latency Collaborative Inference for Multi-Branch Models in D2D-Assisted MEC

学校读者我要写书评

暂无评论

Learning-Based Low-Latency Collaborative Inference for Multi...

IEEE Conference on Wireless Communications and Networking

作者： Kai Guo Yilin Xiao Xiaozhen Lu Liang Xiao Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Peng Cheng Laboratory Shenzhen China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Department of Information and Communication Engineering Xiamen University Xiamen China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Deploying high-complexity deep neural network (DNN) on mobile devices presents significant challenges, stemming from the conflict between their computationally intensive demands and the constrained computational resources. Device-to-device ( $D$ 2 $D$ ) assisted mobile edge computing (MEC) exploits sharing resources among devices to perform DNN inference collaboratively for higher efficiency. However, most existing collaborative inference schemes ignore the structure of DNN models, thus suffering from high latency under dynamic network conditions and computational loads. In this paper, we propose a learning-based low-latency collaborative inference scheme for multi-branch models, which schedules the computations of each DNN layer to optimize the alignment between the DNN structure's characteristics and the D2D network environments. Specifically, the computational task of each branch is assigned to nearby mobile devices or the edge server for efficient collaboration. In addition, we design proximal policy optimization with task-specific architecture to choose the computational scheduling policy, which contains a two-stream NN to extract features from the D2D network and the tasks at each layer, as well as a multi-head output to obtain the collaborative devices for all tasks in the layer. Simulation results show that the proposed scheme reduces the inference latency compared with benchmarks.

关键词： Schedules Processor scheduling Computational modeling Simulation Collaboration Artificial neural networks Mobile handsets Device-to-device communication Servers Low latency communication

Entropy Maximization in High Dimensional Multiagent State Spaces

学校读者我要写书评

暂无评论

Entropy Maximization in High Dimensional Multiagent State Sp...

International Symposium on Multi-Robot and Multi-Agent Systems (MRS)

作者： Ayhan Alp Aydeniz Enrico Marchesini Robert Loftin Kagan Tumer Collaborative Robotics and Intelligent Systems Institute Oregon State University Corvallis Oregon USA Laboratory for Information & Decision Systems Massachusetts Institute of Technology Cambridge Massachusetts USA Department of Computer Science University of Sheffield Sheffield United Kingdom

Underwater or planetary exploration are prime examples of missions that can benefit from autonomous agents working together. However, discovering effective team-level behaviors (i.e., coordinated joint actions) is challenging in these domains as agents typically receive a sparse reward (zero-or constant-for the majority of the interactions). To address this issue, intrinsic rewards encourage agents to explore diverse policies to visit the state space more effectively. Unfortunately, as the agents’ state space grows, intrinsic reward-based (i.e., curiosity) approaches become less effective as they cannot effectively distinguish a diverse set of states. In this direction, we introduce state entropy maximization for multiagent learning where agents explore using local (dense) rewards and learn to solve the coordination task by leveraging global (sparse) rewards. Because of the intrinsic ability to balance local and global rewards, our approach enables the state entropy function to remain effective in high dimensional state spaces. Experiments in tightly coupled tasks requiring complex joint actions, show that local entropy-based rewards enable agents to discover successful team behaviors in high dimensional spaces where previous hand-tuned count-based rewards fail.

关键词：

Socially CompliAnt Navigation Dataset (SCAND): A Large-Scale Dataset Of Demonstrations For Social Navigation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Karnan, Haresh Nair, Anirudh Xiao, Xuesu Warnell, Garrett Pirk, Sören Toshev, Alexander Hart, Justin Biswas, Joydeep Stone, Peter The University of Texas at Austin Department of Computer Science United States Robotics Google Sony AI Computational and Information Sciences Directorate Army Research Laboratory United States

Social navigation is the capability of an autonomous agent, such as a robot, to navigate in a "socially compliant" manner in the presence of other intelligent agents such as humans. With the emergence of autonomously navigating mobile robots in human-populated environments (e.g., domestic service robots in homes and restaurants and food delivery robots on public sidewalks), incorporating socially compliant navigation behaviors on these robots becomes critical to ensuring safe and comfortable human-robot coexistence. To address this challenge, imitation learning is a promising framework, since it is easier for humans to demonstrate the task of social navigation rather than to formulate reward functions that accurately capture the complex multi-objective setting of social navigation. The use of imitation learning and inverse reinforcement learning to social navigation for mobile robots, however, is currently hindered by a lack of large-scale datasets that capture socially compliant robot navigation demonstrations in the wild. To fill this gap, we introduce Socially CompliAnt Navigation Dataset (SCAND)-a large-scale, first-person-view dataset of socially compliant navigation demonstrations. Our dataset contains 8.7 hours, 138 trajectories, 25 miles of socially compliant, human tele-operated driving demonstrations that comprises multi-modal data streams including 3D lidar, joystick commands, odometry, visual and inertial information, collected on two morphologically different mobile robots-a Boston Dynamics Spot and a Clearpath Jackal-by four different human demonstrators in both indoor and outdoor environments. We additionally perform preliminary analysis and validation through real-world robot experiments and show that navigation policies learned by imitation learning on SCAND generate socially compliant behaviors. © 2022, CC BY.

关键词： Navigation

GRATIS: Deep Learning Graph Representation with Task-specific Topology and Multi-dimensional Edge Features

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Song, Siyang Song, Yuxin Luo, Cheng Song, Zhiyuan Kuzucu, Selim Jia, Xi Guo, Zhijiang Xie, Weicheng Shen, Linlin Gunes, Hatice The Department of Computer Science and Technology University of Cambridge CambridgeCB3 0FT United Kingdom Baidu Inc Beijing100193 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China Department of Computer Engineering Middle East Technical University Ankara Turkey School of Computer Science University of Birmingham Birmingham United Kingdom

Graph is powerful for representing various types of real-world data. The topology (edges’ presence) and edges’ features of a graph decides the message passing mechanism among vertices within the graph. While most existing approaches only manually define a single-value edge to describe the connectivity or strength of association between a pair of vertices, task-specific and crucial relationship cues may be disregarded by such manually defined topology and single-value edge features. In this paper, we propose the first general graph representation learning framework (called GRATIS) which can generate a strong graph representation with a task-specific topology and task-specific multi-dimensional edge features from any arbitrary input (i.e., graph or non-graph data). To learn each edge’s presence and multi-dimensional feature, our framework takes both of the corresponding vertices pair and their global contextual information into consideration, enabling the generated graph representation to have a globally optimal message passing mechanism for different down-stream tasks. The principled investigation results achieved for various graph analysis tasks (e.g., graph classification, vertex classification, and link prediction) on 11 graph and non-graph datasets show that our GRATIS can not only largely enhance pre-defined graphs but also learns a strong graph representation for non-graph data, with clear performance improvements on all tasks. In particular, the learned topology and multi-dimensional edge features provide complementary task-related cues for graph analysis tasks. Our framework is effective, robust and flexible, and is a plug-and-play module that can be combined with different backbones and Graph Neural Networks (GNNs) to generate a task-specific graph representation from various graph and non-graph data. Our code is made publicly available at https://***/SSYSteve/Learning-Graph-Representation-with-Task-specific-Topology-and-Multi-dimensional-Edge-Feature

关键词： Graph neural networks

Neural P3M: a long-range interaction modeling enhancer for geometric GNNs 24

学校读者我要写书评

暂无评论

Neural P3M: a long-range interaction modeling enhancer for g...

Proceedings of the 38th International Conference on Neural information Processing Systems

作者： Yusong Wang Chaoran Cheng Shaoning Li Yuxuan Ren Bin Shao Ge Liu Pheng-Ann Heng Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University University of Illinois Urbana-Champaign Department of Computer Science and Engineering The Chinese University of Hong Kong University of Science and Technology of China Microsoft Research AI4Science

ISBN: (纸本)9798331314385

Geometric graph neural networks (GNNs) have emerged as powerful tools for modeling molecular geometry. However, they encounter limitations in effectively capturing long-range interactions in large molecular systems due to the localization assumption of GNN. To address this challenge, we introduce Neural P3M, a versatile enhancer of geometric GNNs to expand the scope of their capabilities by incorporating mesh points alongside atoms and reimaging traditional mathematical operations in a trainable manner. Neural P3M exhibits flexibility across a wide range of molecular systems and demonstrates remarkable accuracy in predicting energies and forces, outperforming on benchmarks such as the MD22 dataset. It also achieves an average improvement of 22% on the OE62 dataset while integrating with various architectures. Codes are available at https://***/OnlyLoveKFC/Neural_P3M.

关键词：

MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yaning Wang, Tianyi Yu, Zitong Gao, Zan Shen, Linlin Chen, Shengyong Jinan250353 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Jinan250014 China The Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored, which limits the generalization capability of the model. In addition, most FFD methods tend to identify facial images generated by GAN, but struggle to detect unseen diffusion-synthesized ones. To address the limitations, we aim to leverage the cutting-edge foundation model, contrastive language-image pre-training (CLIP), to achieve generalizable diffusion face forgery detection (DFFD). In this paper, we propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities via language-guided face forgery representation learning, to facilitate the advancement of DFFD. Specifically, we devise a fine-grained language encoder (FLE) that extracts fine global language features from hierarchical text prompts. We design a multi-modal vision encoder (MVE) to capture global image forgery embeddings as well as fine-grained noise forgery patterns extracted from the richest patch, and integrate them to mine general visual forgery traces. Moreover, we build an innovative plug-and-play sample pair attention (SPA) method to emphasize relevant negative pairs and suppress irrelevant ones, allowing cross-modality sample pairs to conduct more flexible alignment. Extensive experiments and visualizations show that our model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

RDA: An Accelerated Collision Free Motion Planner for Autonomous Navigation in Cluttered Environments

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Han, Ruihua Wang, Shuai Wang, Shuaijun Zhang, Zeqing Zhang, Qianru Eldar, Yonina C. Hao, Qi Pan, Jia The Department of Computer Science and Engineering Southern University of Science and Technology Guangdong Shenzhen China The Department of Computer Science The University of Hong Kong Hong Kong Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China The Department of Computer Science and Engineering Harbin Institute of Technology Guangdong Shenzhen China The Weizmann Institute of Science Rehovot Israel The Department of Computer Science and Engineering The Shenzhen Key Laboratory of Robotics and Computer Vision The Sifakis Research Institute for Trustworthy Autonomous Systems Southern University of Science and Technology Guangdong Shenzhen China

Autonomous motion planning is challenging in multi-obstacle environments due to nonconvex collision avoidance constraints. Directly applying numerical solvers to these nonconvex formulations fails to exploit the constraint structures, resulting in excessive computation time. In this paper, we present an accelerated collision-free motion planner, namely regularized dual alternating direction method of multipliers (RDADMM or RDA for short), for the model predictive control (MPC) based motion planning problem. The proposed RDA addresses nonconvex motion planning via solving a smooth biconvex reformulation via duality and allows the collision avoidance constraints to be computed in parallel for each obstacle to reduce computation time significantly. We validate the performance of the RDA planner through path-tracking experiments with car-like robots in both simulation and real-world settings. Experimental results show that the proposed method generates smooth collision-free trajectories with less computation time compared with other benchmarks and performs robustly in cluttered environments. The source code is available at https://***/hanruihua/ RDA_planner. Copyright © 2022, The Authors. All rights reserved.

关键词： Motion planning

Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization

学校读者我要写书评

暂无评论

Online Refinement of Low-level Feature Based Activation Map ...

International Conference on computer vision (ICCV)

作者： Jinheng Xie Cheng Luo Xiangping Zhu Ziqi Jin Weizeng Lu Linlin Shen Shenzhen Institute of Artificial Intelligence of Robotics of Society Guangdong Key Laboratory of Intelligent Information Processing Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University

ISBN: (纸本)9781665428132

We present a two-stage learning framework for weakly supervised object localization (WSOL). While most previous efforts rely on high-level feature based CAMs (Class Activation Maps), this paper proposes to localize objects using the low-level feature based activation maps. In the first stage, an activation map generator produces activation maps based on the low-level feature maps in the classifier, such that rich contextual object information is included in an online manner. In the second stage, we employ an evaluator to evaluate the activation maps predicted by the activation map generator. Based on this, we further propose a weighted entropy loss, an attentive erasing, and an area loss to drive the activation map generator to substantially reduce the uncertainty of activations between object and background, and explore less discriminative regions. Based on the low-level object information preserved in the first stage, the second stage model gradually generates a well-separated, complete, and compact activation map of object in the image, which can be easily thresholded for accurate localization. Extensive experiments on CUB-200-2011 and ImageNet-1K datasets show that our framework surpasses previous methods by a large margin, which sets a new state-of-the-art for WSOL. Code will be available soon.

关键词： Location awareness computer vision Uncertainty Codes Drives Generators Entropy

NTIRE 2023 HR NonHomogeneous Dehazing Challenge Report

学校读者我要写书评

暂无评论

NTIRE 2023 HR NonHomogeneous Dehazing Challenge Report

2023 IEEE/CVF Conference on computer vision and Pattern Recognition Workshops, CVPRW 2023

作者： Ancuti, Codruta O. Ancuti, Cosmin Vasluianu, Florin-Alexandru Timofte, Radu Zhou, Han Dong, Wei Liu, Yangyi Chen, Jun Liu, Huan Li, Liangyan Wu, Zijun Dong, Yubo Li, Yuyan Qiu, Tian He, Yu Lu, Yonghong Wu, Yinwei Jiang, Zhenxiang Liu, Songhua Yang, Xingyi Jing, Yongcheng Benjdira, Bilel Ali, Anas M. Koubaa, Anis Yang, Hao-Hsiang Chen, I-Hsiang Chen, Wei-Ting Huang, Zhi-Kai Chen, Yi-Chung Hsieh, Chia-Hsuan Chang, Hua-En Chiang, Yuan-Chun Kuo, Sy-Yen Guo, Yu Gao, Yuan Liu, Ryan Wen Lu, Yuxu Qu, Jingxiang He, Shengfeng Ren, Wenqi Hoang, Trung Zhang, Haichuan Yazdani, Amirsaeed Monga, Vishal Yang, Lehan Wu, Alex Jiahao Mai, Tiancheng Cong, Xiaofeng Yin, Xuemeng Yin, Xuefei Emad, Hazim Abdallah, Ahmed Yasser, Yahya Elshahat, Dalia Elbaz, Esraa Li, Zhan Kuang, Wenqing Luo, Ziwei Gustafsson, Fredrik K. Zhao, Zheng Sjölund, Jens Schön, Thomas B. Zhang, Zhao Wei, Yanyan Wang, Junhu Zhao, Suiyi Zheng, Huan Guo, Jin Sun, Yangfan Liu, Tianli Hao, Dejun Jiang, Kui Sarvaiya, Anjali Prajapati, Kalpesh Patra, Ratnadeep Barik, Pragnesh Rathod, Chaitanya Upla, Kishor Raja, Kiran Ramachandra, Raghavendra Busch, Christoph ETcTI Universitatea Politehnica Timisoara Romania ICTEAM UCL Belgium Computer Vision Lab University of Wuerzburg Germany Computer Vision Lab ETH Zurich Switzerland Department of Electrical and Computer Engineering McMaster University Canada Department of Electrical and Computer Engineering University of Alberta Canada McMaster University Canada Xidian University China Research Institute Singapore National University of Singapore Singapore University of Sydney Australia Robotics and Internet-of-Things Laboratory Prince Sultan University Riyadh12435 Saudi Arabia Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Electronics Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Wuhan University of Technology China Singapore Management University Singapore Singapore Sun Yat-sen University China Electrical Engineering Department Pennsylvania State University United States The University of Sydney Australia Southeast University China University of California Los Angeles United States Beijing Jiaotong University China Mansoura Univeristy Egypt College of Information Science and Technology Jinan University China Department of Information Technology Uppsala University Sweden Hefei University of Technology China Zhejiang Dahua Technology China Sardar Vallabhbhai National Institute of Technology India Norwegian University of Science and Technology Norway

ISBN: (纸本)9798350302493

This study assesses the outcomes of the NTIRE 2023 Challenge on Non-Homogeneous Dehazing, wherein novel techniques were proposed and evaluated on new image dataset called HD-NH-HAZE. The HD-NH-HAZE dataset contains 50 high resolution pairs of real-life outdoor images featuring nonhomogeneous hazy images and corresponding haze-free images of the same scene. The nonhomogeneous haze was simulated using a professional setup that replicated real-world conditions of hazy scenarios. The competition had 246 participants and 17 teams submitted solutions for the final testing phase. The proposed solutions demonstrated the cutting-edge in image dehazing technology. © 2023 IEEE.

关键词： Demulsification