TeachAugment: Data Augmentation Optimization Using Teacher Knowledge
Author:
Preprint
Abstract
Optimization of image transformation functions for the purpose of data augmentation has been intensively studied. In particular, adversarial data augmentation strategies, which search augmentation maximizing task loss, show significant improvement in the model generalization for many tasks. However, the existing methods require careful parameter tuning to avoid excessively strong deformations that take away image features critical for acquiring generalization. In this paper, we propose a data augmentation optimization method based on the adversarial strategy called TeachAugment, which can produce informative transformed images to the model without requiring careful tuning by leveraging a teacher model. Specifically, the augmentation is searched so that augmented images are adversarial for the target model and recognizable for the teacher model. We also propose data augmentation using neural networks, which simplifies the search space design and allows for updating of the data augmentation using the gradient method. We show that TeachAugment outperforms existing methods in experiments of image classification, semantic segmentation, and unsupervised representation learning tasks.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Meta Approach to Data Augmentation Optimization2022
- Differentiable Automatic Data Augmentation2020
- Adversarial Transformations for Semi-Supervised LearningProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Shakedrop Regularization for Deep Residual LearningIEEE Access, 2019
- Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Wide Residual Networks2016
- Sliced and Radon Wasserstein Barycenters of MeasuresJournal of Mathematical Imaging and Vision, 2014