检索结果-内蒙古大学图书馆

Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Jian Sun, Wei Yang, Hui Deng, Pengchao Liu, Chongpei Sebe, Nicu Rahmani, Hossein Mian, Ajmal National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering School of Robotics State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China Department of Information Engineering and Computer Science University of Trento Trento38123 Italy School of Computing and Communications Lancaster University LA1 4YW United Kingdom Department of Computer Science The University of Western Australia WA6009 Australia

Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potential for generalization to intra-class unknown objects. However, these methods require manual collection and labeling of large-scale real-world training data. To address this problem, we introduce a diffusion-based paradigm for domain-generalized category-level 9-DoF object pose estimation. Our motivation is to leverage the latent generalization ability of the diffusion model to address the domain generalization challenge in object pose estimation. This entails training the model exclusively on rendered synthetic data to achieve generalization to real-world scenes. We propose an effective diffusion model to redefine 9-DoF object pose estimation from a generative perspective. Our model does not require any 3D shape priors during training or inference. By employing the Denoising Diffusion Implicit Model, we demonstrate that the reverse diffusion process can be executed in as few as 3 steps, achieving near real-time performance. Finally, we design a robotic grasping system comprising both hardware and software components. Through comprehensive experiments on two benchmark datasets and the real-world robotic system, we show that our method achieves state-of-the-art domain generalization performance. Our code will be made public at https://***/CNJianLiu/Diff9D. Copyright © 2025, The Authors. All rights reserved.

关键词： Augmented reality

Low-Light Enhancement Effect on Classification and Detection: An Empirical Study

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Xu Lai, Zhihui Jie, Zhou Gao, Can Hou, Xianxu Zhang, Ya-Nan Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China

Low-light images are commonly encountered in real-world scenarios, and numerous low-light image enhancement (LLIE) methods have been proposed to improve the visibility of these images. The primary goal of LLIE is to generate clearer images that are more visually pleasing to humans. However, the impact of LLIE methods in high-level vision tasks, such as image classification and object detection, which rely on high-quality image datasets, is not well explored. To explore the impact, we comprehensively evaluate LLIE methods on these high-level vision tasks by utilizing an empirical investigation comprising image classification and object detection experiments. The evaluation reveals a dichotomy: While Low-Light Image Enhancement (LLIE) methods enhance human visual interpretation, their effect on computer vision tasks is inconsistent and can sometimes be harmful. Our findings suggest a disconnect between image enhancement for human visual perception and for machine analysis, indicating a need for LLIE methods tailored to support high-level vision tasks effectively. This insight is crucial for the development of LLIE techniques that align with the needs of both human and machine vision. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine vision

A Stackelberg Game-based Wireless Powered Federated Learning

学校读者我要写书评

暂无评论

A Stackelberg Game-based Wireless Powered Federated Learning

International Conference on computer Supported Cooperative Work in Design

作者： Jianmeng Guo Huan Zhou Xuxun Liu Liang Zhao Victor Leung Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges University Yichang China School of Computer Science Northwestern Polytechnical University Xi’an China School of Electronics and Information Engineering South China University of Technology Guangzhou China Department of Electrical and Computer Engineering The University of British Columbia Vancouver BC Canada

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

By sharing model parameters instead of raw data to train machine models, Federated Learning (FL) can protect End equipment Workers (EWs)’ data privacy. However, due to energy constraints and selfishness, EWs may not be willing to participate or train slowly, which affects the performance of global FL model. To address these issues, we propose a three-stage Stackelberg game-based wireless powered FL framework to incentivize all players to participate in the system while ensuring the successful completion of FL tasks. Specifically, Base Station (BS) publishes the FL task and wants to obtain a better FL model at a lower cost. EWs train local FL models, and want to get more payment with less energy consumption. When EWs train and upload their local models, Charging Service Provider (CSP) transmits energy to them via Wireless Power Transfer (WPT) while charging fees. In order to obtain the optimal strategy for all participants, we analyze the proposed game problem using the backward induction method. Meanwhile, we prove that the unique Stackelberg equilibrium and Nash equilibrium can be obtained, and we obtain the approximate optimal solution of BS using the subgradient method. Finally, extensive simulations are conducted to evaluate the performance of the proposed method in different scenarios. The results show that the proposed method improves the utility of three parties by an average of 19.09% - 51.86% compared with the benchmark methods.

关键词： Wireless communication Energy consumption Data privacy Costs Federated learning Games Wireless power transfer

Enhanced multi-stage network for defocus deblurring using dual-pixel images 13

学校读者我要写书评

暂无评论

Enhanced multi-stage network for defocus deblurring using du...

13th International Conference on Signal Processing Systems, ICSPS 2021

作者： Li, Ru Xie, Junwei Xue, Yuyang Zou, Wenbin Tong, Tong Luo, Ming Gao, Qinquan College of Physics and Information Engineering Fuzhou University China Fujian Key Lab of Medical Instrumentation & Pharmaceutical Technology Fuzhou University China Imperial Vision Technology Fujian China Department of Computer Science University of Tsukuba Tsukuba Japan Fujian Provincial Key Laboratory of Photonics Technology Fujian Normal University China

ISBN: (数字)9781510653184

ISBN: (纸本)9781510653177

The defocus deblurring raised from the finite aperture size and exposure time is an essential problem in the shooting process, which seriously affects the quality of the images. However, studies based on defocus deblurring in monocular images yielded good results, while those on binocular images are rare. The current methods directly merge the left and right views regardless of their unique features. Objects within the camera's DoF will not have a difference in phase, while light rays from outside the DoF will have a relative shift that is directly correlated with the amount of defocus blur. In this paper, we firstly proposed an enhanced multi-stage network for defocus deblurring using dual-pixel Images. Taking into account the parallax between the left and right views, the first two stages learn the information of them, respectively, and correct the deviation of the images under the supervision of the ground truth. The third stage consists of EERG and ERGS. It merges with the feature map of the previous stage, so that the left and right views are mutually enhanced, and a good restored image is obtained. ERGS uses the residual block as the basic unit to restore the details of the blurred area while maintaining the clear. Experimental results show that our proposed network can achieve better accuracy than state-of-the-art approaches on the public DPD dataset. © COPYRIGHT SPIE.

关键词： Geometrical optics

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...

2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

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

ISBN: (纸本)9798350368369

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 (D2D) 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. © 2025 IEEE.

关键词： Reinforcement learning

Introducing the structural bases of typicality effects in deep learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Pino, Omar Vidal Nascimento, Erickson R. Campos, Mario F.M. Computer Vision and Robotics Laboratory Computer Science Department Universidade Federal de Minas Gerais Belo Horizonte31270-010 Brazil

In this paper, we hypothesize that the effects of the degree of typicality in natural semantic categories can be generated based on the structure of artificial categories learned with deep learning models. Motivated by the human approach to representing natural semantic categories and based on the foundations of Prototype Theory, we propose a novel Computational Prototype Model (CPM) to represent the internal structure of semantic categories. Unlike other prototype learning approaches, our mathematical framework proposes a first approach to provide deep neural networks with the ability to model abstract semantic concepts such as category central semantic meaning (semantic prototype), typicality degree of object's image, and family resemblance relationship. We proposed several methodologies based on the typicality's concept to evaluate our CPM model in image semantic processing tasks such as image classification, a global semantic description of images, and transfer learning. Our experiments on different image datasets, such as ImageNet and Coco, showed that our approach might be an admissible proposition in the effort to endow machines with greater power of abstraction for the semantic representation of objects' *** Codes 68T07 (Primary) 68Q55 (Secondary) Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xiao, Chunjing Pang, Shikang Xu, Xovee Li, Xuan Trajcevski, Goce Zhou, Fan The School of Computer and Information Engineering Henan University China The Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China The University of Electronic Science and Technology of China Sichuan Chengdu610054 China The National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan University Chengdu610065 China The Department of Electrical and Computer Engineering Iowa State University AmesIA50011 United States

A critical aspect of Graph Neural Networks (GNNs) is to enhance the node representations by aggregating node neighborhood information. However, when detecting anomalies, the representations of abnormal nodes are prone to be averaged by normal neighbors, making the learned anomaly representations less distinguishable. To tackle this issue, we propose CAGAD - an unsupervised Counterfactual data Augmentation method for Graph Anomaly Detection - which introduces a graph pointer neural network as the heterophilic node detector to identify potential anomalies whose neighborhoods are normal-node-dominant. For each identified potential anomaly, we design a graph-specific diffusion model to translate a part of its neighbors, which are probably normal, into anomalous ones. At last, we involve these translated neighbors in GNN neighborhood aggregation to produce counterfactual representations of anomalies. Through aggregating the translated anomalous neighbors, counterfactual representations become more distinguishable and further advocate detection performance. The experimental results on four datasets demonstrate that CAGAD significantly outperforms strong baselines, with an average improvement of 2.35% on F1, 2.53% on AUC-ROC, and 2.79% on AUC-PR. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

Image-based Navigation in Real-World Environments via Multiple Mid-level Representations: Fusion Models, Benchmark and Efficient Evaluation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Rosano, Marco Furnari, Antonino Gulino, Luigi Santoro, Corrado Farinella, Giovanni Maria FPV@IPLAB - Department of Mathematics and Computer Science University of Catania Catania Italy Robotics Laboratory Department of Mathematics and Computer Science University of Catania Catania Italy OrangeDev s.r.l. Firenze Italy Cognitive Robotics and Social Sensing Laboratory ICAR-CNR Palermo Italy Next Vision s.r.l. Catania Italy

Robot visual navigation is a relevant research topic. Current deep navigation models conveniently learn the navigation policies in simulation, given the large amount of experience they need to collect. Unfortunately, the resulting models show a limited generalization ability when deployed in the real world. In this work we explore solutions to facilitate the development of visual navigation policies trained in simulation that can be successfully transferred in the real world. We first propose an efficient evaluation tool to reproduce realistic navigation episodes in simulation. We then investigate a variety of deep fusion architectures to combine a set of mid-level representations, with the aim of finding the best merge strategy that maximize the real world performances. Our experiments, performed both in simulation and on a robotic platform, show the effectiveness of the considered mid-level representations-based models and confirm the reliability of the evaluation tool. The 3D models of the environment and the code of the validation tool are publicly available at the following link: https://***/EmbodiedVN/ © 2022, CC BY-NC-SA.

关键词： Reinforcement learning

Image-Based Navigation in Real-World Environments Via Multiple Mid-Level Representations: Fusion Models, Benchmark and Efficient Evaluation

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Rosano, Marco Furnari, Antonino Gulino, Luigi Santoro, Corrado Farinella, Giovanni Maria FPV@IPLAB Department of Mathematics and Computer Science University of Catania Catania Italy Robotics Laboratory Department of Mathematics and Computer Science University of Catania Catania Italy OrangeDev s.r.l. Firenze Italy Cognitive Robotics and Social Sensing Laboratory ICAR-CNR Palermo Italy Next Vision s.r.l. Catania Italy

Robot visual navigation is a relevant research topic. Current deep navigation models mostly learn the navigation policies in simulation. This is convenient, given the efficiency offered by simulators to collect the required training experience. Unfortunately, the resulting models show a limited generalization ability when deployed in the real world. In this work we investigate the problem of learning robust visual navigation policies in simulation that can successfully transferred in the real world. We propose an evaluation tool to reproduce realistic navigation episodes in simulation. We then study whether the mid-level visual representations, that have proven to be effective in previous applications, can be successfully used in simulation to solve the domain gap. Our experiments, performed both in simulation and on a robotic platform, show the proposed evaluation tool can provide results which are consistent with the ones obtained in the real world. © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning