Augmentation Learning for Semi-Supervised Classification

TL;DR

This paper introduces a semi-supervised learning approach that automatically learns effective data augmentation policies using meta-learning, improving performance on diverse datasets beyond natural images.

Contribution

We extend Fixmatch with meta-learning of augmentations, enabling automatic, dataset-specific augmentation policy learning for semi-supervised classification.

Findings

Achieved state-of-the-art results on satellite and sketch datasets.

Demonstrated adaptability of learned augmentations to different domains.

Showed effectiveness of bi-level optimization for augmentation policy learning.

Abstract

Recently, a number of new Semi-Supervised Learning methods have emerged. As the accuracy for ImageNet and similar datasets increased over time, the performance on tasks beyond the classification of natural images is yet to be explored. Most Semi-Supervised Learning methods rely on a carefully manually designed data augmentation pipeline that is not transferable for learning on images of other domains. In this work, we propose a Semi-Supervised Learning method that automatically selects the most effective data augmentation policy for a particular dataset. We build upon the Fixmatch method and extend it with meta-learning of augmentations. The augmentation is learned in additional training before the classification training and makes use of bi-level optimization, to optimize the augmentation policy and maximize accuracy. We evaluate our approach on two domain-specific datasets, containing satellite images and hand-drawn sketches, and obtain state-of-the-art results. We further investigate in an ablation the different parameters relevant for learning augmentation policies and show how policy learning can be used to adapt augmentations to datasets beyond ImageNet.