Solo-Learn: A Library of Self-Supervised Methods for Visual Representation Learning

Abstract

This paper presents solo-learn, a library of self-supervised methods for visual representation learning. Implemented in Python, using Pytorch and Pytorch lightning, the library fits both research and industry needs by featuring distributed training pipelines with mixed-precision, faster data loading via Nvidia DALI, online linear evaluation for better prototyping, and many additional training tricks. Our goal is to provide an easy-to-use library comprising a large amount of Self-supervised Learning (SSL) methods, that can be easily extended and fine-tuned by the community. solo-learn opens up avenues for exploiting large-budget SSL solutions on inexpensive smaller infrastructures and seeks to democratize SSL by making it accessible to all. The source code is available at https://github.com/vturrisi/solo-learn.

Cite

Text

da Costa et al. "Solo-Learn: A Library of Self-Supervised Methods for Visual Representation Learning." Machine Learning Open Source Software, 2022.

Markdown

[da Costa et al. "Solo-Learn: A Library of Self-Supervised Methods for Visual Representation Learning." Machine Learning Open Source Software, 2022.](https://mlanthology.org/mloss/2022/dacosta2022jmlr-sololearn/)

BibTeX

@article{dacosta2022jmlr-sololearn,
  title     = {{Solo-Learn: A Library of Self-Supervised Methods for Visual Representation Learning}},
  author    = {da Costa, Victor Guilherme Turrisi and Fini, Enrico and Nabi, Moin and Sebe, Nicu and Ricci, Elisa},
  journal   = {Machine Learning Open Source Software},
  year      = {2022},
  pages     = {1-6},
  volume    = {23},
  url       = {https://mlanthology.org/mloss/2022/dacosta2022jmlr-sololearn/}
}