FAAGC: Feature Augmentation on Adaptive Geodesic Curve Based on the shape space theory
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915483594260480 |
|---|---|
| author | Han, Yuexing Li, Ruijie |
| author_facet | Han, Yuexing Li, Ruijie |
| contents | Deep learning models have been widely applied across various domains and industries. However, many fields still face challenges due to limited and insufficient data. This paper proposes a Feature Augmentation on Adaptive Geodesic Curve (FAAGC) method in the pre-shape space to increase data. In the pre-shape space, objects with identical shapes lie on a great circle. Thus, we project deep model representations into the pre-shape space and construct a geodesic curve, i.e., an arc of a great circle, for each class. Feature augmentation is then performed by sampling along these geodesic paths. Extensive experiments demonstrate that FAAGC improves classification accuracy under data-scarce conditions and generalizes well across various feature types. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_18619 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FAAGC: Feature Augmentation on Adaptive Geodesic Curve Based on the shape space theory Han, Yuexing Li, Ruijie Computer Vision and Pattern Recognition Machine Learning Deep learning models have been widely applied across various domains and industries. However, many fields still face challenges due to limited and insufficient data. This paper proposes a Feature Augmentation on Adaptive Geodesic Curve (FAAGC) method in the pre-shape space to increase data. In the pre-shape space, objects with identical shapes lie on a great circle. Thus, we project deep model representations into the pre-shape space and construct a geodesic curve, i.e., an arc of a great circle, for each class. Feature augmentation is then performed by sampling along these geodesic paths. Extensive experiments demonstrate that FAAGC improves classification accuracy under data-scarce conditions and generalizes well across various feature types. |
| title | FAAGC: Feature Augmentation on Adaptive Geodesic Curve Based on the shape space theory |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2501.18619 |