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)

Benchmarks

Add a Result

These leaderboards are used to track progress in Image Clustering

Dataset	Best Model	Compare
CIFAR-10	TEMI CLIP ViT-L (openai)	See all
STL-10	TEMI DINO ViT-B	See all
CIFAR-100	TEMI CLIP ViT-L (openai)	See all
Imagenet-dog-15	MAE-CT (best)	See all
USPS	SPC	See all
ImageNet-10	SPICE (Full ImageNet pre-train)	See all
MNIST-full	SPC	See all
Fashion-MNIST	AE+SNNL	See all
Tiny-ImageNet	SPICE	See all
MNIST-test	DynAE	See all
coil-100	A-DSSC (Scattered)	See all
ImageNet	MIM-Refiner (D2V2-ViT-H/14)	See all
Extended Yale-B	DMSC	See all
Coil-20	JULE-RC	See all
ImageNet-50	TEMI CLIP ViT-L (openai)	See all
ImageNet-100	TEMI CLIP ViT-L (openai)	See all
ImageNet-200	TEMI CLIP ViT-L (openai)	See all
YouTube Faces DB	JULE-RC	See all
UMist	J-DSSC (Scattered)	See all
CMU-PIE	JULE-RC	See all
CUB Birds	FineGAN	See all
Stanford Dogs	FineGAN	See all
Stanford Cars	FineGAN	See all
FRGC	DEPICT	See all
HAR	FCMI	See all
coil-40	A-DSSC (Scattered)	See all
LetterA-J	DDC-DA	See all
pendigits	N2D (UMAP)	See all
MNIST	CoHiClust	See all
ARL Polarimetric Thermal Face Dataset	DMSC	See all
EMNIST-Balanced	AE+SNNL	See all
CUB-200-2011	MES-Loss	See all
CARS196	MES-Loss	See all

Show all 33 benchmarks

Collapse benchmarks

Libraries

Use these libraries to find Image Clustering models and implementations

Li-Hongmin/MyPaperWithCode

3 papers

waynezhanghk/gacluster

2 papers

wikibook/keras

2 papers

Datasets

Subtasks

Most implemented papers

Most implemented Social Latest No code

Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types

KevinWangHP/Anomaly-Clustering • • 21 Dec 2021

We define a distance function between images, each of which is represented as a bag of embeddings, by the Euclidean distance between weighted averaged embeddings.

Paper
Code

Twin Contrastive Learning for Online Clustering

XLearning-SCU/2022-IJCV-TCL • • 21 Oct 2022

Specifically, we find that when the data is projected into a feature space with a dimensionality of the target cluster number, the rows and columns of its feature matrix correspond to the instance and cluster representation, respectively.

Paper
Code

Web-Scale Image Clustering Revisited

iavr/iqm • ICCV 2015

Large scale duplicate detection, clustering and mining of documents or images has been conventionally treated with seed detection via hashing, followed by seed growing heuristics using fast search.

Paper
Code

Scalable Sequential Spectral Clustering

zahraDehghanian97/Scalable_Sequential_Spectral_Clustering • • AAAI 2016

In the past decades, Spectral Clustering (SC) has become one of the most effective clustering approaches.

Paper
Code

Deep Colorization

djflstkddk/Auto-Colorization • • ICCV 2015

This paper investigates into the colorization problem which converts a grayscale image to a colorful version.

Paper
Code

Oracle Based Active Set Algorithm for Scalable Elastic Net Subspace Clustering

ChongYou/subspace-clustering • • CVPR 2016

Our geometric analysis also provides a theoretical justification and a geometric interpretation for the balance between the connectedness (due to $\ell_2$ regularization) and subspace-preserving (due to $\ell_1$ regularization) properties for elastic net subspace clustering.

Paper
Code

Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization

herandy/DEPICT • ICCV 2017

We define a clustering objective function using relative entropy (KL divergence) minimization, regularized by a prior for the frequency of cluster assignments.

Paper
Code