Stochastic Contrastive Learning
arXiv:2110.00552
Abstract
While state-of-the-art contrastive Self-Supervised Learning (SSL) models produce results competitive with their supervised counterparts, they lack the ability to infer latent variables. In contrast, prescribed latent variable (LV) models enable attributing uncertainty, inducing task specific compression, and in general allow for more interpretable representations. In this work, we introduce LV approximations to large scale contrastive SSL models. We demonstrate that this addition improves downstream performance (resulting in 96.42% and 77.49% test top-1 fine-tuned performance on CIFAR10 and ImageNet respectively with a ResNet50) as well as producing highly compressed representations (588x reduction) that are useful for interpretability, classification and regression downstream tasks.
Accepted to 2nd Workshop on Self-Supervised Learning: Theory and Practice (NeurIPS 2021), Sydney, Australia
References in corpus (6)
- A Simple Framework for Contrastive Learning of Visual Representations
- Bootstrap your own latent: A new approach to self-supervised Learning
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Barlow Twins: Self-Supervised Learning via Redundancy Reduction
- Big Self-Supervised Models are Strong Semi-Supervised Learners
- On Variational Bounds of Mutual Information