Image Clustering
105 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
These leaderboards are used to track progress in Image Clustering
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Image Clustering models and implementationsDatasets
CIFAR-10
ImageNet
CIFAR-100
MNIST
Fashion-MNIST
CUB-200-2011
STL-10
Tiny ImageNet
Stanford Cars
USPS
Subtasks
Most implemented papers
StampNet: unsupervised multi-class object discovery
Unsupervised object discovery in images involves uncovering recurring patterns that define objects and discriminates them against the background.
Deep Comprehensive Correlation Mining for Image Clustering
Cory-M/DCCM
•
•
ICCV 2019
Recent developed deep unsupervised methods allow us to jointly learn representation and cluster unlabelled data.
Feature-Based Image Clustering and Segmentation Using Wavelets
Pixel intensity is a widely used feature for clustering and segmentation algorithms, the resulting segmentation using only intensity values might suffer from noises and lack of spatial context information.
Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning
sseung0703/GALA_TF2.0
•
•
ICCV 2019
For the reconstruction of node features, the decoder is designed based on Laplacian sharpening as the counterpart of Laplacian smoothing of the encoder, which allows utilizing the graph structure in the whole processes of the proposed autoencoder architecture.
Pareto-optimal data compression for binary classification tasks
The goal of lossy data compression is to reduce the storage cost of a data set $X$ while retaining as much information as possible about something ($Y$) that you care about.
Multi-Modal Deep Clustering: Unsupervised Partitioning of Images
guysrn/mmdc
•
•
Simultaneously, the same deep network is trained to solve an additional self-supervised task of predicting image rotations.
Tree-SNE: Hierarchical Clustering and Visualization Using t-SNE
Building on recent advances in speeding up t-SNE and obtaining finer-grained structure, we combine the two to create tree-SNE, a hierarchical clustering and visualization algorithm based on stacked one-dimensional t-SNE embeddings.
GATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering
niuchuangnn/GATCluster
•
•
ECCV 2020
To train the GATCluster in a completely unsupervised manner, we design four self-learning tasks with the constraints of transformation invariance, separability maximization, entropy analysis, and attention mapping.
Hyperspectral Image Clustering with Spatially-Regularized Ultrametrics
We propose a method for the unsupervised clustering of hyperspectral images based on spatially regularized spectral clustering with ultrametric path distances.
Improving k-Means Clustering Performance with Disentangled Internal Representations
afagarap/pt-snnl
•
•
Deep clustering algorithms combine representation learning and clustering by jointly optimizing a clustering loss and a non-clustering loss.
