MehdiZouitine/Learning-Disentangled-Representations-via-Mutual-Information-Estimation
Pytorch implementation of Learning Disentangled Representations via Mutual Information Estimation (ECCV 2020)
This project helps machine learning engineers and researchers disentangle the various features contributing to a dataset. You input images (like colored digits) and the output is a set of learned representations that separate features that are shared across different domains from those that are unique to a specific domain. This is particularly useful for those working on robust model development and interpretability.
No commits in the last 6 months.
Use this if you need to understand and isolate the core characteristics within your image data from superficial or domain-specific attributes to build more generalized models.
Not ideal if you are looking for a plug-and-play solution for general image classification without a specific need to analyze or control disentangled features.
Stars
82
Forks
8
Language
Python
License
MIT
Category
Last pushed
Aug 03, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MehdiZouitine/Learning-Disentangled-Representations-via-Mutual-Information-Estimation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
YU1ut/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
kamata1729/QATM_pytorch
Pytorch Implementation of QATM:Quality-Aware Template Matching For Deep Learning
nttcslab/msm-mae
Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations
rgeirhos/generalisation-humans-DNNs
Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)