Image Clustering

104 papers with code • 33 benchmarks • 21 datasets

Models that partition the dataset into semantically meaningful clusters without having access to 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 Image Clustering models and implementations

Most implemented papers

An Image Clustering Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids and MMD Distance

zyWang-Power/Clustering 10 Jun 2019

The algorithm uses PEDCC (Predefined Evenly-Distributed Class Centroids) as the clustering centers, which ensures the inter-class distance of latent features is maximal, and adds data distribution constraint, data augmentation constraint, auto-encoder reconstruction constraint and Sobel smooth constraint to improve the clustering performance.

Graph Degree Linkage: Agglomerative Clustering on a Directed Graph

waynezhanghk/gactoolbox 25 Aug 2012

We explore the different roles of two fundamental concepts in graph theory, indegree and outdegree, in the context of clustering.

Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit

ChongYou/subspace-clustering CVPR 2016

Subspace clustering methods based on $\ell_1$, $\ell_2$ or nuclear norm regularization have become very popular due to their simplicity, theoretical guarantees and empirical success.

Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders

waynezhanghk/gacluster 23 Mar 2017

Traditional image clustering methods take a two-step approach, feature learning and clustering, sequentially.

CNN features are also great at unsupervised classification

jorisguerin/pretrainedCNN_clustering 6 Jul 2017

This paper aims at providing insight on the transferability of deep CNN features to unsupervised problems.

Leveraging tensor kernels to reduce objective function mismatch in deep clustering

DanielTrosten/DTKC 20 Jan 2020

In this work we study OFM in deep clustering, and find that the popular autoencoder-based approach to deep clustering can lead to both reduced clustering performance, and a significant amount of OFM between the reconstruction and clustering objectives.

SCAN: Learning to Classify Images without Labels

wvangansbeke/Unsupervised-Classification ECCV 2020

First, a self-supervised task from representation learning is employed to obtain semantically meaningful features.

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

ryanchankh/mcr2 NeurIPS 2020

To learn intrinsic low-dimensional structures from high-dimensional data that most discriminate between classes, we propose the principle of Maximal Coding Rate Reduction ($\text{MCR}^2$), an information-theoretic measure that maximizes the coding rate difference between the whole dataset and the sum of each individual class.

Dissimilarity Mixture Autoencoder for Deep Clustering

larajuse/DMAE 15 Jun 2020

The dissimilarity mixture autoencoder (DMAE) is a neural network model for feature-based clustering that incorporates a flexible dissimilarity function and can be integrated into any kind of deep learning architecture.

Learning Hierarchical Graph Neural Networks for Image Clustering

dmlc/dgl ICCV 2021

Our hierarchical GNN uses a novel approach to merge connected components predicted at each level of the hierarchy to form a new graph at the next level.