Task-specific Part Discovery for Fine-grained Few-shot Classification
文献类型：期刊论文
| 作者 | Yongxian Wei; Xiu-Shen Wei |
| 刊名 | Machine Intelligence Research
 |
| 出版日期 | 2024 |
| 卷号 | 21期号:5页码:954-965 |
| 关键词 | Fine-grained image recognition few-shot learning transductive learning visual dictionary part feature discovery |
| ISSN号 | 2731-538X |
| DOI | 10.1007/s11633-023-1451-7 |
| 英文摘要 | Localizing discriminative object parts (e.g., bird head) is crucial for fine-grained classification tasks, especially for the more challenging fine-grained few-shot scenario. Previous work always relies on the learned object parts in a unified manner, where they at tend the same object parts (even with common attention weights) for different few-shot episodic tasks. In this paper, we propose that it should adaptively capture the task-specific object parts that require attention for each few-shot task, since the parts that can distinguish different tasks are naturally different. Specifically for a few-shot task, after obtaining part-level deep features, we learn a task-specific part-based dictionary for both aligning and reweighting part features in an episode. Then, part-level categorical prototypes are generated based on the part features of support data, which are later employed by calculating distances to classify query data for evaluation. To retain the discriminative ability of the part-level representations (i.e., part features and part prototypes), we design an optimal transport solution that also utilizes query data in a transductive way to optimize the aforementioned distance calculation for the final predictions. Extensive experiments on five fine-grained benchmarks show the superiority of our method, especially for the 1-shot setting, gaining 0.12%, 8.56% and 5.87% improvements over state-of-the-art methods on CUB, Stanford Dogs, and Stanford Cars, respectively. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/59424]  |
| 专题 | 自动化研究所_学术期刊_International Journal of Automation and Computing |
| 作者单位 | School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing 210094, China |
| 推荐引用方式 GB/T 7714 | Yongxian Wei,Xiu-Shen Wei. Task-specific Part Discovery for Fine-grained Few-shot Classification[J]. Machine Intelligence Research,2024,21(5):954-965. |
| APA | Yongxian Wei,&Xiu-Shen Wei.(2024).Task-specific Part Discovery for Fine-grained Few-shot Classification.Machine Intelligence Research,21(5),954-965. |
| MLA | Yongxian Wei,et al."Task-specific Part Discovery for Fine-grained Few-shot Classification".Machine Intelligence Research 21.5(2024):954-965. |
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。