About

Models that learn to label each image (i.e. cluster the dataset into its ground truth classes) without seeing the ground truth labels.

Image credit: ImageNet clustering results of SCAN: Learning to Classify Images without Labels (ECCV 2020)

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Greatest papers with code

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

NeurIPS 2016 tensorflow/models

This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner.

IMAGE GENERATION REPRESENTATION LEARNING UNSUPERVISED IMAGE CLASSIFICATION UNSUPERVISED MNIST

Adversarial Autoencoders

18 Nov 2015eriklindernoren/PyTorch-GAN

In this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the aggregated posterior of the hidden code vector of the autoencoder with an arbitrary prior distribution.

DATA VISUALIZATION DIMENSIONALITY REDUCTION UNSUPERVISED IMAGE CLASSIFICATION UNSUPERVISED MNIST VARIATIONAL INFERENCE

Invariant Information Clustering for Unsupervised Image Classification and Segmentation

ICCV 2019 xu-ji/IIC

The method is not specialised to computer vision and operates on any paired dataset samples; in our experiments we use random transforms to obtain a pair from each image.

IMAGE CLUSTERING SEMANTIC SEGMENTATION UNSUPERVISED IMAGE CLASSIFICATION UNSUPERVISED MNIST

Unsupervised Deep Embedding for Clustering Analysis

19 Nov 2015elieJalbout/Clustering-with-Deep-learning

Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms.

Ranked #3 on Unsupervised Image Classification on SVHN (using extra training data)

IMAGE CLUSTERING UNSUPERVISED IMAGE CLASSIFICATION

Learning Discrete Representations via Information Maximizing Self-Augmented Training

ICML 2017 weihua916/imsat

Learning discrete representations of data is a central machine learning task because of the compactness of the representations and ease of interpretation.

Ranked #2 on Unsupervised Image Classification on SVHN (using extra training data)

DATA AUGMENTATION UNSUPERVISED IMAGE CLASSIFICATION

Self-Supervised Learning for Large-Scale Unsupervised Image Clustering

24 Aug 2020Randl/kmeans_selfsuper

Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data.

IMAGE CLUSTERING REPRESENTATION LEARNING SELF-SUPERVISED LEARNING UNSUPERVISED IMAGE CLASSIFICATION

Improving Unsupervised Image Clustering With Robust Learning

21 Dec 2020deu30303/RUC

Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results.

IMAGE CLUSTERING UNSUPERVISED IMAGE CLASSIFICATION

Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

19 Nov 2015ZhimingZhou/AM-GAN

Our approach is based on an objective function that trades-off mutual information between observed examples and their predicted categorical class distribution, against robustness of the classifier to an adversarial generative model.

ROBUST CLASSIFICATION UNSUPERVISED IMAGE CLASSIFICATION UNSUPERVISED MNIST