Solo-learn: A Library of Self-supervised Methods for Visual Representation Learning

TL;DR

solo-learn is a comprehensive, easy-to-use Python library that facilitates self-supervised visual representation learning with advanced features like distributed training, fast data loading, and online evaluation, aimed at democratizing SSL research and application.

Contribution

It introduces a versatile, community-extensible library for self-supervised learning in vision, integrating multiple methods and optimized training pipelines for research and industry use.

Findings

Supports various SSL methods with a unified framework

Enables large-scale SSL training on modest hardware

Provides tools for rapid prototyping and evaluation

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.