FreeAugment: Data Augmentation Search Across All Degrees of Freedom
This addresses the need for efficient and comprehensive data augmentation optimization in deep learning, though it appears incremental as it builds on existing search methods by extending them to more degrees of freedom.
The paper tackled the problem of automatic data augmentation search by proposing FreeAugment, the first method to jointly optimize all four degrees of freedom—number, types, order, and magnitudes of transformations—simultaneously, achieving state-of-the-art results on various natural image benchmarks and other domains.
Data augmentation has become an integral part of deep learning, as it is known to improve the generalization capabilities of neural networks. Since the most effective set of image transformations differs between tasks and domains, automatic data augmentation search aims to alleviate the extreme burden of manually finding the optimal image transformations. However, current methods are not able to jointly optimize all degrees of freedom: (1) the number of transformations to be applied, their (2) types, (3) order, and (4) magnitudes. Many existing methods risk picking the same transformation more than once, limit the search to two transformations only, or search for the number of transformations exhaustively or iteratively in a myopic manner. Our approach, FreeAugment, is the first to achieve global optimization of all four degrees of freedom simultaneously, using a fully differentiable method. It efficiently learns the number of transformations and a probability distribution over their permutations, inherently refraining from redundant repetition while sampling. Our experiments demonstrate that this joint learning of all degrees of freedom significantly improves performance, achieving state-of-the-art results on various natural image benchmarks and beyond across other domains. Project page at https://tombekor.github.io/FreeAugment-web