Research

OnlineAugment: Online Data Augmentation with Less Domain Knowledge

ECCV

Authors

Published on

07/17/2020

Categories

Computer Vision ECCV

Data augmentation is one of the most important tools in training modern deep neural networks. Recently, great advances have been made in searching for optimal augmentation policies in the image classification domain. However, two key points related to data augmentation remain uncovered by the current methods. First is that most if not all modern augmentation search methods are offline and learning policies are isolated from their usage. The learned policies are mostly constant throughout the training process and are not adapted to the current training model state. Second, the policies rely on class-preserving image processing functions. Hence applying current offline methods to new tasks may require domain knowledge to specify such kind of operations. In this work, we offer an orthogonal online data augmentation scheme together with three new augmentation networks, co-trained with the target learning task. It is both more efficient, in the sense that it does not require expensive offline training when entering a new domain, and more adaptive as it adapts to the learner state. Our augmentation networks require less domain knowledge and are easily applicable to new tasks. Extensive experiments demonstrate that the proposed scheme alone performs on par with the state-of-the-art offline data augmentation methods, as well as improving upon the state-of-the-art in combination with those methods.

This paper has been published at ECCV 2020

Please cite our work using the BibTeX below.

@misc{tang2020onlineaugment,
      title={OnlineAugment: Online Data Augmentation with Less Domain Knowledge}, 
      author={Zhiqiang Tang and Yunhe Gao and Leonid Karlinsky and Prasanna Sattigeri and Rogerio Feris and Dimitris Metaxas},
      year={2020},
      eprint={2007.09271},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
Close Modal