Abstract
Contrastive coding has achieved promising results in self-supervised representation learning. However, there are practical challenges given that obtaining a tight lower bound on mutual information (MI) requires a sample size exponential in MI and thus a large set of negative samples. We can incorporate more samples by building a large queue-based dictionary, but there are theoretical limits to performance improvements even with a large number of negative samples. We hypothesize that 'random negative sampling' leads to a highly redundant dictionary, which could result in representations that are suboptimal for downstream tasks. In this paper, we propose an active contrastive coding approach that builds an 'actively sampled' dictionary with diverse and informative items, which improves the quality of negative samples and achieves substantially improved results on tasks where there is high mutual information in the data, e.g., video classification. Our model achieves state-of-the-art performance on multiple challenging audio and visual downstream benchmarks including UCF101, HMDB51 and ESC50.
Abstract (translated)
URL
https://arxiv.org/abs/2009.09805
