检索结果-内蒙古大学图书馆

Anytime Fault-tolerant Adaptive Routing for Multi-Robot Teams

学校读者我要写书评

暂无评论

Anytime Fault-tolerant Adaptive Routing for Multi-Robot Team...

IEEE International Conference on robotics and Automation (ICRA)

作者： Ronaldo F. dos Santos Erickson R. Nascimento Douglas G. Macharet Computer Vision and Robotics Laboratory (VeRLab) Universidade Federal de Minas Gerais MG Brazil Tres Lagoas Campus Universidadeˆ Federal de Mato Grosso do Sul MS Brazil

The Correlated Team Orienteering Problem (CTOP) is a routing problem where the objective is to determine a set of routes that maximizes the summation of collected rewards in the environment while respecting the vehicles’ budget. However, solutions to this problem usually consider static instances and may produce poor results in dynamic real-world scenarios. In this paper, we propose an approach to deal with the execution of missions planned as a CTOP instance, especially when vehicles of the team are prone to failure and may not complete their routes. The main contribution of this paper is a novel anytime heuristic that iteratively adapts the initial set of routes, allowing to increase the overall robustness of the mission and still collect the most profitable rewards. The methodology was thoroughly evaluated considering different scenarios and in all the cases was able to achieve comparable or better results in terms of reward than planning a new set of routes, however, spending considerably less time.

关键词： Fault tolerance Automation Conferences Fault tolerant systems Routing Robustness Planning

Group-wise Inhibition based Feature Regularization for Robust Classification

学校读者我要写书评

暂无评论

Group-wise Inhibition based Feature Regularization for Robus...

International Conference on computer vision (ICCV)

作者： Haozhe Liu Haoqian Wu Weicheng Xie Feng Liu Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

The convolutional neural network (CNN) is vulnerable to degraded images with even very small variations (e.g. corrupted and adversarial samples). One of the possible reasons is that CNN pays more attention to the most discriminative regions, but ignores the auxiliary features when learning, leading to the lack of feature diversity for final judgment. In our method, we propose to dynamically suppress significant activation values of CNN by group-wise inhibition, but not fixedly or randomly handle them when training. The feature maps with different activation distribution are then processed separately to take the feature independence into account. CNN is finally guided to learn richer discriminative features hierarchically for robust classification according to the proposed regularization. Our method is comprehensively evaluated under multiple settings, including classification against corruptions, adversarial attacks and low data regime. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both robustness and generalization performances, when compared with the state-of-the-art methods. Code is available at https://***/LinusWu/TENET_Training.

关键词： Training computer vision Codes Heuristic algorithms Robustness Classification algorithms Convolutional neural networks

Learning Graph Representation of Person-specific Cognitive Processes from Audio-visual Behaviours for Automatic Personality Recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Song, Siyang Shao, Zilong Jaiswal, Shashank Shen, Linlin Valstar, Michel Gunes, Hatice Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom Computer Vision Institute Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Computer Vision Lab University of Nottingham Nottingham United Kingdom

This paper proposes to recognise the true (self-reported) personality from the learned simulation of the target subject’s cognition. This approach builds on two following findings in cognitive science: (i) human cognition partially determines expressed behaviour and is directly linked to true personality traits;and (ii) in dyadic interactions individuals’ nonverbal behaviours are influenced by their conversational partner’s behaviours. In this context, we hypothesise that during a dyadic interaction, a target subject’s facial reactions are driven by two main factors, i.e. their internal (person-specific) cognitive process, and the externalised nonverbal behaviours of their conversational partner. Consequently, we propose to represent the target subject’s (defined as the listener) person-specific cognition in the form of a person-specific CNN architecture that has unique architectural parameters and depth, which takes audio-visual non-verbal cues displayed by the conversational partner (defined as the speaker) as input, and is able to reproduce the target subject’s facial reactions. Each person-specific CNN is explored by the Neural Architecture Search (NAS) and a novel adaptive loss function, which is then represented as a graph representation for recognising the target subject’s true personality. Experimental results not only show that the produced graph representations are well associated with target subjects’ personality traits in both human-human and human-machine interaction scenarios, and outperform the existing approaches with significant advantages, but also demonstrate that the proposed novel strategies such as adaptive loss, and the end-to-end vertices/edges feature learning, help the proposed approach in learning more reliable personality representations. Building on our earlier version of this work, this paper further proposes: (i) assigning a unique depth for each CNN;(ii) a novel end-to-end graph vertex feature learning strategy;(iii) a transformer-bas

关键词： Cognitive systems

Optimisation of a siamese neural network for real-time energy efficient object tracking

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2020年

作者： Przewlocka, Dominika Wasala, Mateusz Szolc, Hubert Blachut, Krzysztof Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

In this paper the research on optimisation of visual object tracking using a Siamese neural network for embedded vision systems is presented. It was assumed that the solution shall operate in real-time, preferably for a high resolution video stream, with the lowest possible energy consumption. To meet these requirements, techniques such as the reduction of computational precision and pruning were considered. Brevitas, a tool dedicated for optimisation and quantisation of neural networks for FPGA implementation, was used. A number of training scenarios were tested with varying levels of optimisations – from integer uniform quantisation with 16 bits to ternary and binary networks. Next, the influence of these optimisations on the tracking performance was evaluated. It was possible to reduce the size of the convolutional filters up to 10 times in relation to the original network. The obtained results indicate that using quantisation can significantly reduce the memory and computational complexity of the proposed network while still enabling precise tracking, thus allow to use it in embedded vision systems. Moreover, quantisation of weights positively affects the network training by decreasing overfitting. © 2020, CC BY-NC-SA.

关键词： Field programmable gate arrays (FPGA)

Optimisation of a siamese neural network for real-time energy efficient object tracking

学校读者我要写书评

暂无评论

arXiv 2020年

In this paper the research on optimisation of visual object tracking using a Siamese neural network for embedded vision systems is presented. It was assumed that the solution shall operate in real-time, preferably for a high resolution video stream, with the lowest possible energy consumption. To meet these requirements, techniques such as the reduction of computational precision and pruning were considered. Brevitas, a tool dedicated for optimisation and quantisation of neural networks for FPGA implementation, was used. A number of training scenarios were tested with varying levels of optimisations - from integer uniform quantisation with 16 bits to ternary and binary networks. Next, the influence of these optimisations on the tracking performance was evaluated. It was possible to reduce the size of the convolutional filters up to 10 times in relation to the original network. The obtained results indicate that using quantisation can significantly reduce the memory and computational complexity of the proposed network while still enabling precise tracking, thus allow to use it in embedded vision systems. Moreover, quantisation of weights positively affects the network training by decreasing overfitting. Copyright © 2020, The Authors. All rights reserved.

关键词： Field programmable gate arrays (FPGA)

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

Multiscale Convolutional Transformer with Diverse-aware Feature Learning for Motor Imagery EEG Decoding

学校读者我要写书评

暂无评论

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Hang, Wenlong Wang, Junliang Liang, Shuang Lei, Baiying Wang, Qiong Li, Guanglin Chen, Badong Qin, Jing Nanjing Tech University College of Computer Nanjing211816 China Nanjing Tech University Information Engineering Nanjing211816 China Nanjing University of Posts and Telecommunications School of Internet of Things Nanjing210023 China Shenzhen University School of Biomedical Engineering Shenzhen518060 China Guangdong Provincial Key Laboratory of Computer Vision Shenzhen518055 China Virtual Reality Technology Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China Shenzhen Institute of Advanced Technology Shenzhen518055 China Chinese Academy of Sciences Shenzhen518055 China Xi'an Jiaotong University Institute of Artificial Intelligence and Robotics Xi'an710049 China Hong Kong Polytechnic University School of Nursing Hung Hom Hong Kong

Electroencephalogram (EEG)-based motor imagery (MI) brain-computer interfaces (BCIs) have significant potential in improving motor function for neurorehabilitation. Despite recent advancements, learning diversified EEG features across different frequency ranges remains a significant challenge, as the homogenization of feature representations often limits the generalization capabilities of EEG decoding models for BCIs. In this paper, we propose a novel multiscale convolutional transformer framework for EEG decoding that integrates multiscale convolution, transformer, and diverse-aware feature learning scheme (MCTD) to tackle the above challenge. Specifically, we first capture multiple frequency features using dynamic one-dimensional temporal convolution with different kernel lengths. Subsequently, we incorporate convolutional layers and transformers with a contrastive learning scheme to extract discriminative local and global EEG features within a single frequency range. To mitigate the homogenization of features extracted from different frequency ranges, we propose a novel decorrelation regularization. It enables multiscale convolutional transformers produce less correlated features with each other, thereby enhancing the overall expressiveness of EEG decoding model. The performance of MCTD is evaluated on four public MI-based EEG datasets, including the BCI competition III 3a and IV 2a, the BNCI 2015- 001, and the OpenBMI. For the average Kappa/Accuracy scores, MCTD obtains improvements of 3.58%/2.68%, 3.09%/2.20%, 2.33%/1.54%, and 4.44%/2.22%, over the state-of-the-art method on four EEG datasets, respectively. Experimental results demonstrate that our method exhibits superior performance. © 2016 IEEE.

关键词： Brain computer interface

Cross Domain Object Detection by Target-Perceived Dual Branch Distillation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： He, Mengzhe Wang, Yali Wu, Jiaxi Wang, Yiru Li, Hanqing Li, Bo Gan, Weihao Wu, Wei Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China SenseTime Research University of Chinese Academy of Science China Shanghai AI Laboratory Shanghai China Beihang University China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Cross domain object detection is a realistic and challenging task in the wild. It suffers from performance degradation due to large shift of data distributions and lack of instance-level annotations in the target domain. Existing approaches mainly focus on either of these two difficulties, even though they are closely coupled in cross domain object detection. To solve this problem, we propose a novel Target-perceived Dual-branch Distillation (TDD) framework. By integrating detection branches of both source and target domains in a unified teacher-student learning scheme, it can reduce domain shift and generate reliable supervision effectively. In particular, we first introduce a distinct Target Proposal Perceiver between two domains. It can adaptively enhance source detector to perceive objects in a target image, by leveraging target proposal contexts from iterative cross-attention. Afterwards, we design a concise Dual Branch Self Distillation strategy for model training, which can progressively integrate complementary object knowledge from different domains via self-distillation in two branches. Finally, we conduct extensive experiments on a number of widely-used scenarios in cross domain object detection. The results show that our TDD significantly outperforms the state-of-the-art methods on all the benchmarks. Our code and model will be available at here. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

Abstract: Learning to avoid poor images: towards task-aware c-arm cone-beam ct trajectories

学校读者我要写书评

暂无评论

Abstract: Learning to avoid poor images: towards task-aware ...

International workshop on Algorithmen - Systeme - Anwendungen, 2020

作者： Zaech, Jan-Nico Gao, Cong Bier, Bastian Taylor, Russell Maier, Andreas Navab, Nassir Unberath, Mathias Laboratory for Computational Sensing and Robotics Johns Hopkins University Baltimore United States Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Computer Vision Laboratory Eidgenössische Technische Hochschule Zürich Zürich Germany

ISBN: (纸本)9783658292669

Metal artifacts in computed tomography (CT) arise from a mismatch between physics of image formation and idealized assumptions during tomographic reconstruction. These artifacts are particularly strong around metal implants, inhibiting widespread adoption of 3D cone-beam CT (CBCT) despite clear opportunity for intra-operative verification of implant positioning, e. g. in spinal fusion surgery. On synthetic and real data, we demonstrate that much of the artifact can be avoided by acquiring better data for reconstruction in a task-aware and patient-specific manner, and describe the first step towards the envisioned task-aware CBCT protocol. © Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2020.

关键词： computerized tomography