Solo-learn: A Library of Self-supervised Methods for Visual Representation Learning
Victor G. Turrisi da Costa, Enrico Fini, Moin Nabi, Nicu Sebe, Elisa Ricci
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/lightly-ai/lightlyOfficialIn paperpytorch★ 3,700
- github.com/vturrisi/solo-learnOfficialIn paperpytorch★ 1,553
- github.com/ludysama/crppytorch★ 1
- github.com/trungpx/solo-learn-1214pytorch★ 0
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.