Abstract | ||
---|---|---|
Data augmentation is a key practice in machine learning for improving generalization performance. However, finding the best data augmentation hype rparameters requires domain knowledge or a computationally demanding search. We address this issue by proposing an efficient approach to automatically train a network that learns an effective distribution of transformations to improve its generalization. Using bilevel optimization, we directly optimize the data augmentation parameters using a validation set. This framework can be used as a general solution to learn the optimal data augmentation jointly with an end task model like a classifier. Results show that our joint training method produces an image classification accuracy that is comparable to or better than carefully hand-crafted data augmentation. Yet, it does not need an expensive external validation loop on the data augmentation hyperparaineters. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/WACV48630.2021.00173 | 2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021) |
DocType | ISSN | Citations |
Conference | 2472-6737 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Saypraseuth Mounsaveng | 1 | 0 | 0.34 |
Issam H. Laradji | 2 | 79 | 9.40 |
Ismail Ben Ayed | 3 | 0 | 0.68 |
David Vázquez | 4 | 488 | 28.04 |
Marco Pedersoli | 5 | 0 | 0.34 |