Simple PyTorch implementation of Bootstrap Your Own Latent (BYOL).
-
Updated
Aug 7, 2020 - Python
Simple PyTorch implementation of Bootstrap Your Own Latent (BYOL).
PyTorch implementation of "Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning" with DDP and Apex AMP
Bootstrap Your Own Latent (BYOL) in PyTorch
Collections of self-supervised methods, based on cvpods.
Pytorch implementation of the paper, "Bootstrap Your Own Latent A New Approach to Self-Supervised Learning", or BYOL, https://arxiv.org/pdf/2006.07733v3.pdf
Self-Supervised Learning for General Audio Representation of Raw Waveform
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Melanoma Classification using Semi-supervised learning
SERAB: a multi-lingual benchmark for speech emotion recognition
BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation
Codebase for Imperial MSc AI Individual Project - Self-Supervised Learning for Audio Inference
Contrastive learning implementations using pyssl
Review and Implement Paper of Self-supervised learning
Official PyTorch Implementation of Guarding Barlow Twins Against Overfitting with Mixed Samples
[NeurIPS 2023 (Spotlight)] Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts
Self-Supervised Learning in PyTorch
A python library for self-supervised learning
Add a description, image, and links to the byol topic page so that developers can more easily learn about it.
To associate your repository with the byol topic, visit your repo's landing page and select "manage topics."