YannDubs/SSL-Risk-Decomposition
Benchmark and analysis of 165 pretrained SSL models. Code for "Evaluating Self-Supervised Learning via Risk Decomposition".
This project helps machine learning researchers and practitioners understand the performance of self-supervised learning (SSL) models. It allows you to analyze how different factors contribute to a model's error. You provide a pretrained SSL model and a dataset, and it outputs a breakdown of its performance into components like usability and generalization error. This is for machine learning engineers and researchers evaluating or developing new SSL approaches.
No commits in the last 6 months.
Use this if you need to systematically evaluate and compare self-supervised learning models by decomposing their overall risk into understandable components.
Not ideal if you are an application developer looking for a ready-to-use, production-ready machine learning model for a specific task without needing to deeply analyze its internal performance characteristics.
Stars
14
Forks
2
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 26, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YannDubs/SSL-Risk-Decomposition"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification