Image Clustering
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)
Papers
Showing 1–10 of 236 papers
All datasetsCIFAR-10CIFAR-100STL-10Imagenet-dog-15ImageNet-10MNIST-fullUSPSTiny ImageNetFashion-MNISTImageNetMNIST-testcoil-100
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | TURTLE (CLIP + DINOv2) | Accuracy | 1 | — | Unverified |
| 2 | PRCut (CLIP) | Accuracy | 0.98 | — | Unverified |
| 3 | PRO-DSC | Accuracy | 0.97 | — | Unverified |
| 4 | TEMI CLIP ViT-L (openai) | Accuracy | 0.97 | — | Unverified |
| 5 | DPAC | Accuracy | 0.93 | — | Unverified |
| 6 | SPICE-BPA | Accuracy | 0.93 | — | Unverified |
| 7 | SeCu | Accuracy | 0.93 | — | Unverified |
| 8 | TAC | Accuracy | 0.92 | — | Unverified |
| 9 | SPICE* | Accuracy | 0.92 | — | Unverified |
| 10 | DCN+BRB | Accuracy | 0.91 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | TURTLE (CLIP + DINOv2) | Accuracy | 0.9 | — | Unverified |
| 2 | PRCut (DinoV2) | Accuracy | 0.79 | — | Unverified |
| 3 | PRO-DSC | Accuracy | 0.77 | — | Unverified |
| 4 | TEMI CLIP ViT-L (openai) | Accuracy | 0.74 | — | Unverified |
| 5 | TEMI DINO ViT-B | Accuracy | 0.67 | — | Unverified |
| 6 | ITAE | Accuracy | 0.65 | — | Unverified |
| 7 | SPICE* | Accuracy | 0.58 | — | Unverified |
| 8 | HUME | Accuracy | 0.56 | — | Unverified |
| 9 | DPAC | Accuracy | 0.56 | — | Unverified |
| 10 | SPICE-BPA | Accuracy | 0.55 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | TURTLE (CLIP + DINOv2) | Accuracy | 1 | — | Unverified |
| 2 | TEMI DINO ViT-B | Accuracy | 0.99 | — | Unverified |
| 3 | TAC | Accuracy | 0.98 | — | Unverified |
| 4 | SPICE-BPA | Accuracy | 0.94 | — | Unverified |
| 5 | DPAC | Accuracy | 0.93 | — | Unverified |
| 6 | SPICE* | Accuracy | 0.93 | — | Unverified |
| 7 | HUME | Accuracy | 0.91 | — | Unverified |
| 8 | TCL | Accuracy | 0.87 | — | Unverified |
| 9 | RUC | Accuracy | 0.87 | — | Unverified |
| 10 | IMC-SwAV (Best) | Accuracy | 0.85 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | MAE-CT (best) | Accuracy | 0.94 | — | Unverified |
| 2 | MAE-CT (mean) | Accuracy | 0.87 | — | Unverified |
| 3 | PRO-DSC | Accuracy | 0.84 | — | Unverified |
| 4 | ProPos* | Accuracy | 0.78 | — | Unverified |
| 5 | ProPos | Accuracy | 0.75 | — | Unverified |
| 6 | DPAC | Accuracy | 0.73 | — | Unverified |
| 7 | ConCURL | Accuracy | 0.7 | — | Unverified |
| 8 | SPICE | Accuracy | 0.68 | — | Unverified |
| 9 | TCL | Accuracy | 0.64 | — | Unverified |
| 10 | IDFD | Accuracy | 0.59 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | SPC | NMI | 0.98 | — | Unverified |
| 2 | ADEC | NMI | 0.97 | — | Unverified |
| 3 | DynAE | NMI | 0.96 | — | Unverified |
| 4 | N2D (UMAP) | NMI | 0.96 | — | Unverified |
| 5 | DDC-DA | NMI | 0.96 | — | Unverified |
| 6 | DEN | NMI | 0.96 | — | Unverified |
| 7 | DTI-Clustering | NMI | 0.94 | — | Unverified |
| 8 | EnSC | NMI | 0.94 | — | Unverified |
| 9 | ClusterGAN | NMI | 0.94 | — | Unverified |
| 10 | DBC | NMI | 0.94 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | SPC | NMI | 0.95 | — | Unverified |
| 2 | DynAE | NMI | 0.95 | — | Unverified |
| 3 | DEN | NMI | 0.94 | — | Unverified |
| 4 | DDC-DA | NMI | 0.94 | — | Unverified |
| 5 | SR-K-means | NMI | 0.94 | — | Unverified |
| 6 | ClusterGAN | NMI | 0.93 | — | Unverified |
| 7 | DMSC | NMI | 0.93 | — | Unverified |
| 8 | DDC | NMI | 0.92 | — | Unverified |
| 9 | JULE-RC | NMI | 0.91 | — | Unverified |
| 10 | N2D (UMAP) | NMI | 0.9 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | PRO-DSC | Accuracy | 0.7 | — | Unverified |
| 2 | ITAE | Accuracy | 0.68 | — | Unverified |
| 3 | SPICE | Accuracy | 0.31 | — | Unverified |
| 4 | IMC-SwAV (Best) | Accuracy | 0.28 | — | Unverified |
| 5 | IMC-SwAV (Avg+-) | Accuracy | 0.28 | — | Unverified |
| 6 | C3 | Accuracy | 0.14 | — | Unverified |
| 7 | CC | Accuracy | 0.14 | — | Unverified |
| 8 | MMDC | Accuracy | 0.12 | — | Unverified |
| 9 | DCCM | Accuracy | 0.11 | — | Unverified |
| 10 | DAC | Accuracy | 0.07 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | PRCut (DinoV2) | Accuracy | 0.79 | — | Unverified |
| 2 | VMM | Accuracy | 0.72 | — | Unverified |
| 3 | SPC | Accuracy | 0.68 | — | Unverified |
| 4 | N2D (UMAP) | Accuracy | 0.67 | — | Unverified |
| 5 | CoHiClust | Accuracy | 0.65 | — | Unverified |
| 6 | DEN | Accuracy | 0.64 | — | Unverified |
| 7 | PSSC | Accuracy | 0.63 | — | Unverified |
| 8 | GDL | Accuracy | 0.63 | — | Unverified |
| 9 | DDC | Accuracy | 0.62 | — | Unverified |
| 10 | DTI-Clustering | Accuracy | 0.61 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | TURTLE (CLIP + DINOv2) | Accuracy | 72.9 | — | Unverified |
| 2 | MIM-Refiner (D2V2-ViT-H/14) | Accuracy | 67.3 | — | Unverified |
| 3 | SeLa | NMI | 66.4 | — | Unverified |
| 4 | PRO-DSC | Accuracy | 65 | — | Unverified |
| 5 | MIM-Refiner (MAE-ViT-H/14) | Accuracy | 64.6 | — | Unverified |