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% top-1 accuracy, surpassing the best self-supervised pretrained model by 1% and confirming that self-supervised learning works in a real world setting. Interestingly, we also observe that self-supervised models are good few-shot learners achieving 77.9% top-1 with access to only 10% of ImageNet. Code: https://github.com/facebookresearch/vissl
@article{arxiv.2103.01988,
title = {Self-supervised Pretraining of Visual Features in the Wild},
author = {Priya Goyal and Mathilde Caron and Benjamin Lefaudeux and Min Xu and Pengchao Wang and Vivek Pai and Mannat Singh and Vitaliy Liptchinsky and Ishan Misra and Armand Joulin and Piotr Bojanowski},
journal= {arXiv preprint arXiv:2103.01988},
year = {2021}
}