This is an UNOFFICIAL PyTorch based implementation of TiCo: Transformation Invariance and Covariance Contrast for Self-Supervised Visual Representation Learning using Lightly.
Please feel free to raise bugs/issues if you find any.
$ pip install -r requirements.txt
@article{zhu2022tico,
title={TiCo: Transformation Invariance and Covariance Contrast for Self-Supervised Visual Representation Learning},
author={Zhu, Jiachen and Moraes, Rafael M and Karakulak, Serkan and Sobol, Vlad and Canziani, Alfredo and LeCun, Yann},
journal={arXiv preprint arXiv:2206.10698},
year={2022}
}