DEC+BRB

Reported on 6 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

Image ClusteringonCIFAR-10
ARI· 2024-11-04
0.812
best: 0.989 (TURTLE (CLIP + DINOv2))
Breaking the Reclustering Barrier in Centroid-based Deep Clustering arXiv:2411.02275
Image ClusteringonCIFAR-10
Accuracy· 2024-11-04
0.906
best: 0.995 (TURTLE (CLIP + DINOv2))
Breaking the Reclustering Barrier in Centroid-based Deep Clustering arXiv:2411.02275
Image ClusteringonCIFAR-10
NMI· 2024-11-04
0.826
best: 0.985 (TURTLE (CLIP + DINOv2))
Breaking the Reclustering Barrier in Centroid-based Deep Clustering arXiv:2411.02275
Image ClassificationonCIFAR-20
ARI· 2024-11-04
35.05
best: 41.15 (DCN+BRB)
Breaking the Reclustering Barrier in Centroid-based Deep Clustering arXiv:2411.02275
Image ClassificationonCIFAR-20
Accuracy· 2024-11-04
50.46
best: 73.2 (MV-MR)
Breaking the Reclustering Barrier in Centroid-based Deep Clustering arXiv:2411.02275
Image ClassificationonCIFAR-20
NMI· 2024-11-04
51.72
best: 73.2 (PRO-DSC)
Breaking the Reclustering Barrier in Centroid-based Deep Clustering arXiv:2411.02275