@misc{bachman2019learning,
author = {Bachman, Philip and Hjelm, Devon and Buchwalter, William},
title = {Learning Representations by Maximizing Mutual Information Across Views},
year = {2019},
month = {June},
abstract = {We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context. For example, one could produce multiple views of a local spatio-temporal context by observing it from different locations (e.g., camera positions within a scene), and via different modalities (e.g., tactile, auditory, or visual). Or, an ImageNet image could provide a context from which one produces multiple views by repeatedly applying data augmentation.  Maximizing mutual information between features extracted from these views requires capturing information about high-level factors whose influence spans multiple views – e.g., presence of certain objects or occurrence of certain events. Following our proposed approach, we develop a model which learns image representations that significantly outperform prior methods on the tasks we consider. Most notably, using self-supervised learning, our model learns representations which achieve 68.1% accuracy on ImageNet using standard linear evaluation.  This beats prior results by over 12% and concurrent results by 7%. When we extend our model to use mixture-based representations, segmentation behavior emerges as a natural side-effect. Our code is available online: https://github.com/Philip-Bachman/amdim-public},
url = {http://approjects.co.za/?big=en-us/research/publication/learning-representations-by-maximizing-mutual-information-across-views/},
}