1S-DAug: One-Shot Data Augmentation for Robust Few-Shot Generalization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917415165624320 |
|---|---|
| author | Bai, Yunwei Tan, Ying Kiat Shu, Yao Chen, Tsuhan |
| author_facet | Bai, Yunwei Tan, Ying Kiat Shu, Yao Chen, Tsuhan |
| contents | Few-shot learning (FSL) challenges model generalization to novel classes based on just a few shots of labeled examples, a testbed where traditional test-time augmentations fail to be effective. We introduce 1S-DAug, a one-shot generative augmentation operator that synthesizes diverse yet faithful variants from just one example image at test time. 1S-DAug couples traditional geometric perturbations with controlled noise injection and a denoising diffusion process conditioned on the original image. The generated images are then encoded and aggregated, alongside the original image, into a combined representation for more robust few-shot predictions. Integrated as a training-free model-agnostic plugin, 1S-DAug consistently improves few-shot classification across standard benchmarks of 4 different datasets without any model parameter update, including achieving up to 20\% relative accuracy improvement on the miniImagenet 5-way-1-shot benchmark. Additionally, we provide extension experiments on the larger vision language models as well as theoretical analyses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00114 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | 1S-DAug: One-Shot Data Augmentation for Robust Few-Shot Generalization Bai, Yunwei Tan, Ying Kiat Shu, Yao Chen, Tsuhan Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Few-shot learning (FSL) challenges model generalization to novel classes based on just a few shots of labeled examples, a testbed where traditional test-time augmentations fail to be effective. We introduce 1S-DAug, a one-shot generative augmentation operator that synthesizes diverse yet faithful variants from just one example image at test time. 1S-DAug couples traditional geometric perturbations with controlled noise injection and a denoising diffusion process conditioned on the original image. The generated images are then encoded and aggregated, alongside the original image, into a combined representation for more robust few-shot predictions. Integrated as a training-free model-agnostic plugin, 1S-DAug consistently improves few-shot classification across standard benchmarks of 4 different datasets without any model parameter update, including achieving up to 20\% relative accuracy improvement on the miniImagenet 5-way-1-shot benchmark. Additionally, we provide extension experiments on the larger vision language models as well as theoretical analyses. |
| title | 1S-DAug: One-Shot Data Augmentation for Robust Few-Shot Generalization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.00114 |