brendel-group/cl-ica
Code for the paper "Contrastive Learning Inverts the Data Generating Process".
This project helps researchers and machine learning practitioners analyze complex datasets by separating the underlying factors that generate the data. It takes in raw, complex data (like images of objects or driving scenes) and outputs disentangled representations, making it easier to understand and interpret the distinct causes of variation in your data. It's intended for those working on understanding and improving generative models.
No commits in the last 6 months.
Use this if you are developing or studying generative models and need to disentangle the core, independent factors (like object shape, color, or position) that contribute to your observed data.
Not ideal if you are looking for a plug-and-play solution for general image classification or object detection without a specific interest in the underlying generative factors.
Stars
92
Forks
12
Language
Python
License
MIT
Category
Last pushed
Jul 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/brendel-group/cl-ica"
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