Visual affordance detection using an efficient attention convolutional neural network | |
Gu, Qipeng2,3; Su, Jianhua3; Yuan, Lei1 | |
刊名 | NEUROCOMPUTING |
2021-06-14 | |
卷号 | 440期号:2021页码:36-44 |
关键词 | Affordance detection Attention mechanism Up-sampling layer |
ISSN号 | 0925-2312 |
DOI | 10.1016/j.neucom.2021.01.018 |
英文摘要 | Visual affordance detection is an important issue in the field of robotics and computer vision. This paper proposes a novel and practical convolutional neural network architecture that adopts an encoder-decoder architecture for pixel-wise affordance detection. The encoder network comprises two modules: a dilated residual network that is the backbone for feature extraction, and an attention mechanism that is used for modeling long-range, multi-level dependency relations. The decoder network consists of a novel up sampling layer that maps the low-resolution encoder feature to a high-resolution pixel-wise prediction map. Specifically, integrating an attention mechanism into our network reduces the loss of salient details and improves the feature representation performance of the model. The results of experiments conducted on the University of Maryland dataset (UMD) verify that the proposed network with the attention mechanism and up-sampling layer improved performance compared with classical methods. The proposed method lays the foundation for subsequent research on multi-task learning by physical robots. |
资助项目 | NSFC[91848109] ; Beijing Natural Science Foundation[4182068] ; Science and Technology on Space Intelligent Control Laboratory[HTKJ2019KL502013] ; State Key Laboratory of Rail Traffic Control and Safety[RS2018K009] ; Beijing Jiaotong University ; Major scientific and technological innovation projects in Shandong Province[2019JZZY010430] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:000642408200005 |
资助机构 | NSFC ; Beijing Natural Science Foundation ; Science and Technology on Space Intelligent Control Laboratory ; State Key Laboratory of Rail Traffic Control and Safety ; Beijing Jiaotong University ; Major scientific and technological innovation projects in Shandong Province |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44639] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组 |
通讯作者 | Su, Jianhua |
作者单位 | 1.Beijing Jiaotong Univ, State key Lab Rail Traff Control & Safety, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Automat, Key Lab Complex Syst & Intelligence Sci, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Gu, Qipeng,Su, Jianhua,Yuan, Lei. Visual affordance detection using an efficient attention convolutional neural network[J]. NEUROCOMPUTING,2021,440(2021):36-44. |
APA | Gu, Qipeng,Su, Jianhua,&Yuan, Lei.(2021).Visual affordance detection using an efficient attention convolutional neural network.NEUROCOMPUTING,440(2021),36-44. |
MLA | Gu, Qipeng,et al."Visual affordance detection using an efficient attention convolutional neural network".NEUROCOMPUTING 440.2021(2021):36-44. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论