SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2673-2682
Abstract
A common practice in unsupervised representation learning is to use labeled data to evaluate the quality of the learned representations. This supervised evaluation is then used to guide critical aspects of the training process such as selecting the data augmentation policy. However, guiding an unsupervised training process through supervised evaluations is not possible for real-world data that does not actually contain labels (which may be the case, for example, in privacy sensitive fields such as medical imaging). Therefore, in this work we show that evaluating the learned representations with a self-supervised image rotation task is highly correlated with a standard set of supervised evaluations (rank correlation > 0.94). We establish this correlation across hundreds of augmentation policies, training settings, and network architectures and provide an algorithm (SelfAugment) to automatically and efficiently select augmentation policies without using supervised evaluations. Despite not using any labeled data, the learned augmentation policies perform comparably with augmentation policies that were determined using exhaustive supervised evaluations.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- End-to-end Multi-Modal Multi-Task Vehicle Control for Self-Driving Cars with Visual Perceptions2018
- Mask R-CNN2017
- Feature Pyramid Networks for Object Detection2017
- Unsupervised Visual Representation Learning by Context Prediction2015
- Deep learningNature, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Learning Feature Representations with K-Means2012
- Autoencoder in Time-Series Analysis for Unsupervised Tissues Characterisation in a Large Unlabelled Medical Image Dataset2011
- A training algorithm for optimal margin classifiers1992
- The Proof and Measurement of Association between Two ThingsThe American Journal of Psychology, 1904