Improving Auto-Augment via Augmentation-Wise Weight Sharing
This work improves auto-augmentation search for computer vision tasks by addressing the efficiency bottleneck in policy evaluation, offering incremental but practical gains.
The paper tackles the problem of efficiently evaluating augmentation policies in automatic augmentation search by proposing Augmentation-Wise Weight Sharing (AWS), which reduces computational cost while maintaining accuracy, achieving a top-1 error rate of 1.24% on CIFAR-10 and 20.36% on ImageNet with ResNet-50.
The recent progress on automatically searching augmentation policies has boosted the performance substantially for various tasks. A key component of automatic augmentation search is the evaluation process for a particular augmentation policy, which is utilized to return reward and usually runs thousands of times. A plain evaluation process, which includes full model training and validation, would be time-consuming. To achieve efficiency, many choose to sacrifice evaluation reliability for speed. In this paper, we dive into the dynamics of augmented training of the model. This inspires us to design a powerful and efficient proxy task based on the Augmentation-Wise Weight Sharing (AWS) to form a fast yet accurate evaluation process in an elegant way. Comprehensive analysis verifies the superiority of this approach in terms of effectiveness and efficiency. The augmentation policies found by our method achieve superior accuracies compared with existing auto-augmentation search methods. On CIFAR-10, we achieve a top-1 error rate of 1.24%, which is currently the best performing single model without extra training data. On ImageNet, we get a top-1 error rate of 20.36% for ResNet-50, which leads to 3.34% absolute error rate reduction over the baseline augmentation.