TSUC

Reported on 6 benchmarks across 2 tasks

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
Accuracy· uses extra data
0.81
best: 0.995 (TURTLE (CLIP + DINOv2))
Image ClusteringonCIFAR-100
Accuracy· uses extra data
0.353
best: 0.898 (TURTLE (CLIP + DINOv2))
Image ClusteringonSTL-10
Accuracy· uses extra data
0.665
best: 0.997 (TURTLE (CLIP + DINOv2))
Image ClassificationonSTL-10
Accuracy
66.5
best: 99.7 (TURTLE (CLIP + DINOv2))
Image ClassificationonCIFAR-10
Accuracy· uses extra data
81
best: 99.612 (efficient adaptive ensembling)
Image ClassificationonCIFAR-20
Accuracy
35.3
best: 73.2 (MV-MR)