Unsupervised Image Classification

28 papers with code • 7 benchmarks • 6 datasets

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)

Libraries

Use these libraries to find Unsupervised Image Classification models and implementations

Most implemented papers

Self-Supervised Learning by Estimating Twin Class Distributions

bytedance/TWIST 14 Oct 2021

To solve this problem, we propose to maximize the mutual information between the input and the class predictions.

PixelGAN Autoencoders

anonyme20/nips20 NeurIPS 2017

In this paper, we describe the "PixelGAN autoencoder", a generative autoencoder in which the generative path is a convolutional autoregressive neural network on pixels (PixelCNN) that is conditioned on a latent code, and the recognition path uses a generative adversarial network (GAN) to impose a prior distribution on the latent code.

Deep Transformation-Invariant Clustering

monniert/dti-clustering NeurIPS 2020

In contrast, we present an orthogonal approach that does not rely on abstract features but instead learns to predict image transformations and performs clustering directly in image space.

Unsupervised Image Classification for Deep Representation Learning

HIK-LAB/Unsupervised-Image-Classification 20 Jun 2020

Extensive experiments on ImageNet dataset have been conducted to prove the effectiveness of our method.

Self-Supervised Learning for Large-Scale Unsupervised Image Clustering

Randl/kmeans_selfsuper 24 Aug 2020

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.

Improving Self-Organizing Maps with Unsupervised Feature Extraction

lyes-khacef/GPU-SOM 4 Sep 2020

We conduct a comparative study on the SOM classification accuracy with unsupervised feature extraction using two different approaches: a machine learning approach with Sparse Convolutional Auto-Encoders using gradient-based learning, and a neuroscience approach with Spiking Neural Networks using Spike Timing Dependant Plasticity learning.

Improving Unsupervised Image Clustering With Robust Learning

deu30303/RUC CVPR 2021

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

Unsupervised Visual Representation Learning by Online Constrained K-Means

idstcv/coke CVPR 2022

Clustering is to assign each instance a pseudo label that will be used to learn representations in discrimination.

iBOT: Image BERT Pre-Training with Online Tokenizer

bytedance/ibot 15 Nov 2021

We present a self-supervised framework iBOT that can perform masked prediction with an online tokenizer.

DeepDPM: Deep Clustering With an Unknown Number of Clusters

bgu-cs-vil/deepdpm CVPR 2022

Using a split/merge framework, a dynamic architecture that adapts to the changing K, and a novel loss, our proposed method outperforms existing nonparametric methods (both classical and deep ones).