Learning Data Augmentation with Online Bilevel Optimization for Image Classification
This addresses the need for efficient, automated data augmentation in machine learning, particularly for image classification, though it is incremental as it builds on existing bilevel optimization techniques.
The paper tackles the problem of automating data augmentation hyperparameter selection for image classification by proposing a bilevel optimization framework that jointly learns augmentation parameters with the classifier, achieving accuracy comparable to or better than hand-crafted methods without expensive validation loops.
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.