/IIC

Invariant Information Clustering for Unsupervised Image Classification and Segmentation

Primary LanguagePythonMIT LicenseMIT

Invariant Information Clustering for Unsupervised Image Classification and Segmentation

This repository contains PyTorch code for the IIC paper.

IIC is an unsupervised clustering objective that trains neural networks into image classifiers and segmenters without labels, with state-of-the-art semantic accuracy.

We set 9 new state-of-the-art records on unsupervised STL10 (unsupervised variant of ImageNet), CIFAR10, CIFAR20, MNIST, COCO-Stuff-3, COCO-Stuff, Potsdam-3, Potsdam, and supervised/semisupervised STL. For example:

unsupervised_SOTA

Commands used to train the models in the paper here. There you can also find the flag to turn on prediction drawing for MNIST:

progression

How to download all our trained models here.

How to set up the segmentation datasets here.