中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 机器人视觉团队
Hierarchical Attention Network for Open-Set Fine-Grained Image Recognition

文献类型：期刊论文

作者Sun, Jiayin1,2,3; Wang, Hong4; Dong, Qiulei1,2,3
刊名IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
出版日期2024-05-01
卷号34期号:5页码:3891-3904
关键词Transformers Feature extraction Task analysis Image recognition Training Visualization Computer vision Open-set fine-grained image recognition hierarchical attention long-short term memory
ISSN号1051-8215
DOI10.1109/TCSVT.2023.3325001
通讯作者Dong, Qiulei(qldong@nlpr.ia.ac.cn)
英文摘要Triggered by the success of transformers in various visual tasks, the spatial self-attention mechanism has recently attracted more and more attention in the computer vision community. However, we empirically found that a typical vision transformer with the spatial self-attention mechanism could not learn accurate attention maps for distinguishing different categories of fine-grained images. To address this problem, motivated by the temporal attention mechanism in brains, we propose a hierarchical attention network for learning fine-grained feature representations, called HAN, where the features learnt by implementing a sequence of spatial self-attention operations corresponding to multiple moments are aggregated progressively. The proposed HAN consists of four modules: a self-attention backbone module for learning a sequence of features with self-attention operations, a spatial feature self-organizing module for facilitating the model training, a hierarchical aggregation module for aggregating the re-organized features via a Long Short-Term Memory network, and a context-aware module that is implemented as the forget block of the hierarchical aggregation module for preserving/forgetting the long-term memory by utilizing contextual information. Then, we propose a HAN-based method for open-set fine-grained recognition by integrating the proposed HAN network with a linear classifier, called HAN-OSFGR. Extensive experimental results on 3 fine-grained datasets and 2 coarse-grained datasets demonstrate that the proposed HAN-OSFGR outperforms 9 state-of-the-art open-set recognition methods significantly in most cases.
WOS关键词TEMPORAL ATTENTION ; DIFFICULTY
资助项目National Key Research and Development Program of China
WOS研究方向Engineering
语种英语
WOS记录号WOS:001221132000022
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China
源URL[http://ir.ia.ac.cn/handle/173211/58660]  
专题自动化研究所_模式识别国家重点实验室_机器人视觉团队
通讯作者Dong, Qiulei
作者单位1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
4.Univ Chinese Acad Sci, Coll Life Sci, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Sun, Jiayin,Wang, Hong,Dong, Qiulei. Hierarchical Attention Network for Open-Set Fine-Grained Image Recognition[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2024,34(5):3891-3904.
APA Sun, Jiayin,Wang, Hong,&Dong, Qiulei.(2024).Hierarchical Attention Network for Open-Set Fine-Grained Image Recognition.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,34(5),3891-3904.
MLA Sun, Jiayin,et al."Hierarchical Attention Network for Open-Set Fine-Grained Image Recognition".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 34.5(2024):3891-3904.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。