Learning to Augment via Implicit Differentiation for Domain Generalization
Tingwei Wang (University of Surrey),* Da Li (Samsung), Kaiyang Zhou (Nanyang Technological University), Tao Xiang (University of Surrey), Yi-Zhe Song (University of Surrey)
The 33rd British Machine Vision Conference
Abstract
Machine learning models are intrinsically vulnerable to domain shift between training and testing data, resulting in poor performance in novel domains. Domain generalization (DG) aims to overcome the problem by leveraging multiple source domains to learn a domain-generalizable model. In this paper, we propose a novel augmentation-based DG approach, dubbed AugLearn. Different from existing data augmentation methods, our AugLearn views a data augmentation module as hyper-parameters of a classification model and optimizes the module together with the model via meta-learning. Specifically, at each training step, AugLearn (i) divides source domains into a pseudo source and a pseudo target set, and (ii) trains the augmentation module in such a way that the augmented (synthetic) images can make the model generalize well on the pseudo target set. Moreover, to overcome the expensive second-order gradient computation during meta-learning, we formulate an efficient joint training algorithm, for both the augmentation module and the classification model, based on the implicit function theorem. With the flexibility of augmenting data in both time and frequency spaces, AugLearn shows effectiveness on three standard DG benchmarks, PACS, Office-Home and Digits-DG.Video
Citation
@inproceedings{Wang_2022_BMVC,
author = {Tingwei Wang and Da Li and Kaiyang Zhou and Tao Xiang and Yi-Zhe Song},
title = {Learning to Augment via Implicit Differentiation for Domain Generalization},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0888.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by