Learning Data Augmentation With Online Bilevel Optimization for Image Classification

Saypraseuth Mounsaveng, Issam Laradji, Ismail Ben Ayed, David Vazquez, Marco Pedersoli; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021, pp. 1691-1700

Abstract


Data augmentation is a key practice in machine learning for improving generalization performance. However, finding the best data augmentation hyperparameters 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 hyperparameters.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mounsaveng_2021_WACV, author = {Mounsaveng, Saypraseuth and Laradji, Issam and Ben Ayed, Ismail and Vazquez, David and Pedersoli, Marco}, title = {Learning Data Augmentation With Online Bilevel Optimization for Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2021}, pages = {1691-1700} }