Solo-learn: A Library of Self-supervised Methods for Visual Representation Learning
This library aims to democratize self-supervised learning by providing an easy-to-use tool for researchers and industry, though it is incremental as it packages existing methods.
The authors introduced solo-learn, a Python library for self-supervised visual representation learning, featuring distributed training, faster data loading, and online evaluation to make SSL accessible on smaller infrastructures.
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.