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 | 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 | DPAC | Accuracy | 0.56 | — | Unverified |
| 9 | HUME | Accuracy | 0.56 | — | Unverified |
| 10 | SPICE-BPA | Accuracy | 0.55 | — | Unverified |