| Autor: |
Joonhyun Jeong, Sungmin Cha, Jongwon Choi, Sangdoo Yun, Taesup Moon, Youngjoon Yoo |
| Jazyk: |
angličtina |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
IEEE Access, Vol 11, Pp 16631-16643 (2023) |
| Druh dokumentu: |
article |
| ISSN: |
2169-3536 |
| DOI: |
10.1109/ACCESS.2023.3243108 |
| Popis: |
Image-mixing augmentations (e.g., Mixup and CutMix), which typically involve mix ing two images, have become the de-facto training techniques for image classification. Despite their huge success in image classification, the number of images to be mix ed has not been elucidated in the literature: only the naive K-image expansion has been shown to lead to performance degradation. This study derives a new K-image mixing augmentation based on the stick-breaking process under Dirichlet prior distribution. We demonstrate the superiority of our K-image expansion augmentation over conventional two-image mixing augmentation methods through extensive experiments and analyses: 1) more robust and generalized classifiers; 2) a more desirable loss landscape shape; 3) better adversarial robustness. Moreover, we show that our probabilistic model can measure the sample-wise uncertainty and boost the efficiency for network architecture search by achieving a 7-fold reduction in the search time. Code will be available at https://github.com/yjyoo3312/DCutMix-PyTorch.git. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
