Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.03159 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917856533282816 |
|---|---|
| author | Dang, Yunkai Zhang, Min Chen, Zhengyu Zhang, Xinliang Wang, Zheng Sun, Meijun Wang, Donglin |
| author_facet | Dang, Yunkai Zhang, Min Chen, Zhengyu Zhang, Xinliang Wang, Zheng Sun, Meijun Wang, Donglin |
| contents | Few-shot image classification(FSIC) aims to recognize novel classes given few labeled images from base classes. Recent works have achieved promising classification performance, especially for metric-learning methods, where a measure at only image feature level is usually used. In this paper, we argue that measure at such a level may not be effective enough to generalize from base to novel classes when using only a few images. Instead, a multi-level descriptor of an image is taken for consideration in this paper. We propose a multi-level correlation network (MLCN) for FSIC to tackle this problem by effectively capturing local information. Concretely, we present the self-correlation module and cross-correlation module to learn the semantic correspondence relation of local information based on learned representations. Moreover, we propose a pattern-correlation module to capture the pattern of fine-grained images and find relevant structural patterns between base classes and novel classes. Extensive experiments and analysis show the effectiveness of our proposed method on four widely-used FSIC benchmarks. The code for our approach is available at: https://github.com/Yunkai696/MLCN. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03159 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-Level Correlation Network For Few-Shot Image Classification Dang, Yunkai Zhang, Min Chen, Zhengyu Zhang, Xinliang Wang, Zheng Sun, Meijun Wang, Donglin Computer Vision and Pattern Recognition Computation and Language Few-shot image classification(FSIC) aims to recognize novel classes given few labeled images from base classes. Recent works have achieved promising classification performance, especially for metric-learning methods, where a measure at only image feature level is usually used. In this paper, we argue that measure at such a level may not be effective enough to generalize from base to novel classes when using only a few images. Instead, a multi-level descriptor of an image is taken for consideration in this paper. We propose a multi-level correlation network (MLCN) for FSIC to tackle this problem by effectively capturing local information. Concretely, we present the self-correlation module and cross-correlation module to learn the semantic correspondence relation of local information based on learned representations. Moreover, we propose a pattern-correlation module to capture the pattern of fine-grained images and find relevant structural patterns between base classes and novel classes. Extensive experiments and analysis show the effectiveness of our proposed method on four widely-used FSIC benchmarks. The code for our approach is available at: https://github.com/Yunkai696/MLCN. |
| title | Multi-Level Correlation Network For Few-Shot Image Classification |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2412.03159 |