Key-Part Attention Retrieval for Robotic Object Recognition

doi:10.26599/TST.2023.9010022

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Key-Part Attention Retrieval for Robotic Object Recognition
	Liu, Jierui 1,2; Cao, Zhiqiang 1,2; Tang, Yingbo 1,2
刊名	TSINGHUA SCIENCE AND TECHNOLOGY
	2024-06-01
卷号	29 期号:3 页码:644-655
关键词	Training Visualization Image recognition Cameras Object recognition Convolutional neural networks Data mining key-part attention retrieval robotic object recognition
ISSN号	1007-0214
DOI	10.26599/TST.2023.9010022
通讯作者	Cao, Zhiqiang(zhiqiang.cao@ia.ac.cn)
英文摘要	The ability to recognize novel objects with a few visual samples is critical in the robotic applications. Existing methods mainly concern the recognition of inter-category objects, however, the object recognition from different sub-classes within the same category remains challenging due to their similar appearances. In this paper, we propose a key-part attention retrieval solution to distinguish novel objects of different sub-classes according to a few samples without re-training. Especially, an object encoder, including convolutional neural network with attention and key-part aggregation, is designed to generate object attention map and extract the object-level embedding, where object attention map from the middle stage of the backbone is used to guide the key-part aggregation. Besides, to overcome the non-differentiability drawback of key-part attention, the object encoder is trained in a two-step scheme, and a more stable object-level embedding is obtained. On this basis, the potential objects are located from a scene image by mining connected domains of the attention map. By matching the embedding of each potential object and embeddings from support data, the recognition of the potential objects is achieved. The effectiveness of the proposed method is verified by experiments.
资助项目	National Natural Science Foundation of China[62073322] ; National Natural Science Foundation of China[61973302] ; CIE-Tencent Robotics X Rhino-Bird Focused Research Program[2022-07] ; Beijing Natural Science Foundation[2022MQ05]
WOS关键词	IMAGE ; PATTERNS
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	TSINGHUA UNIV PRESS
WOS记录号	WOS:001123318200007
资助机构	National Natural Science Foundation of China ; CIE-Tencent Robotics X Rhino-Bird Focused Research Program ; Beijing Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54988]
专题	多模态人工智能系统全国重点实验室
通讯作者	Cao, Zhiqiang
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Liu, Jierui,Cao, Zhiqiang,Tang, Yingbo. Key-Part Attention Retrieval for Robotic Object Recognition[J]. TSINGHUA SCIENCE AND TECHNOLOGY,2024,29(3):644-655.
APA	Liu, Jierui,Cao, Zhiqiang,&Tang, Yingbo.(2024).Key-Part Attention Retrieval for Robotic Object Recognition.TSINGHUA SCIENCE AND TECHNOLOGY,29(3),644-655.
MLA	Liu, Jierui,et al."Key-Part Attention Retrieval for Robotic Object Recognition".TSINGHUA SCIENCE AND TECHNOLOGY 29.3(2024):644-655.