View : 397 Download: 0
SAPENet: Self-Attention based Prototype Enhancement Network for Few-shot Learning
- Title
- SAPENet: Self-Attention based Prototype Enhancement Network for Few-shot Learning
- Authors
- Huang, Xilang; Choi, Seon Han
- Ewha Authors
- 최선한
- SCOPUS Author ID
- 최선한
- Issue Date
- 2023
- Journal Title
- PATTERN RECOGNITION
- ISSN
- 0031-3203
1873-5142
- Citation
- PATTERN RECOGNITION vol. 135
- Keywords
- Few -shot learning; Multi -head self -attention mechanism; Image classification; k -Nearest neighbor
- Publisher
- ELSEVIER SCI LTD
- Indexed
- SCIE; SCOPUS
- Document Type
- Article
- Abstract
- Few-shot learning considers the problem of learning unseen categories given only a few labeled samples. As one of the most popular few-shot learning approaches, Prototypical Networks have received considerable attention owing to their simplicity and efficiency. However, a class prototype is typically obtained by averaging a few labeled samples belonging to the same class, which treats the samples as equally important and is thus prone to learning redundant features. Herein, we propose a self-attention based prototype enhancement network (SAPENet) to obtain a more representative prototype for each class. SAPENet utilizes multi-head self-attention mechanisms to selectively augment discriminative features in each sample feature map, and generates channel attention maps between intra-class sample features to attentively retain informative channel features for that class. The augmented feature maps and attention maps are finally fused to obtain representative class prototypes. Thereafter, a local descriptor-based metric module is employed to fully exploit the channel information of the prototypes by searching k similar local descriptors of the prototype for each local descriptor in the unlabeled samples for classification. We performed experiments on multiple benchmark datasets: miniImageNet, tieredImageNet, and CUB-200-2011. The experimental results on these datasets show that SAPENet achieves a considerable improvement compared to Prototypical Networks and also outperforms related state-of-the-art methods.(c) 2022 Elsevier Ltd. All rights reserved.
- DOI
- 10.1016/j.patcog.2022.109170
- Appears in Collections:
- 공과대학 > 전자전기공학전공 > Journal papers
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML