The Image Data and Backbone in Weakly Supervised Fine-Grained Visual Categorization: A Revisit and Further Thinking
文献类型：期刊论文
| 作者 | Ye, Shuo5; Wang, Yu5 ; Peng, Qinmu4,5; You, Xinge4,5; Chen, C. L. Philip1,2,3
|
| 刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
 |
| 出版日期 | 2024 |
| 卷号 | 34期号:1页码:2-16 |
| ISSN号 | 1051-8215 |
| 关键词 | Fine-grained visual categorization deep learning weakly supervised learning |
| DOI | 10.1109/TCSVT.2023.3284405 |
| 通讯作者 | Peng, Qinmu(pengqinmu@hust.edu.cn) |
| 英文摘要 | Weakly-supervised fine-grained visual categorization (FGVC) aims to achieve subclass classification within the same large class using only label information. Compared to general images, fine-grained images have similar appearances and features, and are often affected by disturbances such as viewpoint, lighting, and occlusion during data collection, resulting in significant intra-class variance and small inter-class variance. To achieve FGVC, carefully designed models are often needed to explore the locally discriminative regions of the image. This paper revisits high-quality FGVC publications based on deep learning and analyzes from two new perspective: fine-grained image data and backbone. We address two ignored but interesting problems in FGVC. First, we argue that the reasons for exacerbating intra-class variance are not the same in data of animal, plant, and commodity types, and it is necessary to consider the effects of posture, covariate shift, and structural changes. Additionally, the "soft boundary" between subclasses intensifies the difficulty of classification. Second, we highlight that convolutional networks and self-attention networks have different receptive fields and shape biases, leading to performance differences when processing different types of fine-grained data. Overall, our analysis provides new insights into recent advances, challenges, and future directions for FGVC based on deep learning, which can help researchers develop more effective models for FGVC. |
| WOS关键词 | EXPLOITING WEB IMAGES ; ATTENTION ; NETWORK ; CLASSIFICATION ; LOCALIZATION ; RECOGNITION ; SIMILARITY ; CATEGORY |
| 资助项目 | National Key Research and Development Program |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| WOS记录号 | WOS:001138814400011 |
| 资助机构 | National Key Research and Development Program |
| 源URL | [http://ir.ia.ac.cn/handle/173211/55557]  |
| 专题 | 离退休人员 |
| 通讯作者 | Peng, Qinmu |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100080, Peoples R China 2.Dalian Maritime Univ, Coll Nav, Dalian 116026, Peoples R China 3.Univ Macau, Fac Sci & Technol, Dept Comp & Informat Sci, Macau 99999, Peoples R China 4.Huazhong Univ Sci & Technol, Shenzhen Res Inst, Shenzhen 518000, Peoples R China 5.Huazhong Univ Sci & Technol, Sch Elect Informat & Commun, Wuhan 430074, Peoples R China |
| 推荐引用方式 GB/T 7714 | Ye, Shuo,Wang, Yu,Peng, Qinmu,et al. The Image Data and Backbone in Weakly Supervised Fine-Grained Visual Categorization: A Revisit and Further Thinking[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2024,34(1):2-16. |
| APA | Ye, Shuo,Wang, Yu,Peng, Qinmu,You, Xinge,&Chen, C. L. Philip.(2024).The Image Data and Backbone in Weakly Supervised Fine-Grained Visual Categorization: A Revisit and Further Thinking.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,34(1),2-16. |
| MLA | Ye, Shuo,et al."The Image Data and Backbone in Weakly Supervised Fine-Grained Visual Categorization: A Revisit and Further Thinking".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 34.1(2024):2-16. |
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。