Unsupervised Image Classification On Imagenet
Metriken
ARI
Accuracy (%)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | ARI | Accuracy (%) | Paper Title | Repository |
|---|---|---|---|---|
| Self-Classifier (ResNet-50) | 29.5 | 41.1 | Self-Supervised Classification Network | |
| SimCLRv2 ResNet-152 + SK (PCA+k-means, 1500 clusters) | 23.94±0.16 | 46.03±0.21 | Self-Supervised Learning for Large-Scale Unsupervised Image Clustering | |
| DeepDPM (nonparametric) | 14 | 25 | DeepDPM: Deep Clustering With an Unknown Number of Clusters | |
| iBOT (ViT-S/16) | 32.8 | 43.4 | iBOT: Image BERT Pre-Training with Online Tokenizer | |
| TURTLE (CLIP + DINOv2) | 62.5 | 72.9 | Let Go of Your Labels with Unsupervised Transfer | |
| TWIST (ResNet-50) | 30.0 | 40.6 | Self-Supervised Learning by Estimating Twin Class Distributions | - |
| SimCLRv2 ResNet-152 + SK (PCA+k-means) | 22.80±0.60 | 39.07±0.61 | Self-Supervised Learning for Large-Scale Unsupervised Image Clustering | |
| SCAN (ResNet-50) | 27.5 | 39.9 | SCAN: Learning to Classify Images without Labels |
0 of 8 row(s) selected.