Self-supervised Pretraining of Visual Features in the Wild

03/02/2021 ∙ by Priya Goyal, et al. ∙ 0

Recently, self-supervised learning methods like MoCo, SimCLR, BYOL and SwAV have reduced the gap with supervised methods. These results have been achieved in a control environment, that is the highly curated ImageNet dataset. However, the premise of self-supervised learning is that it can learn from any random image and from any unbounded dataset. In this work, we explore if self-supervision lives to its expectation by training large models on random, uncurated images with no supervision. Our final SElf-supERvised (SEER) model, a RegNetY with 1.3B parameters trained on 1B random images with 512 GPUs achieves 84.2 1 Interestingly, we also observe that self-supervised models are good few-shot learners achieving 77.9



There are no comments yet.


page 1

page 2

page 3

page 4

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.