Ours (SlotCon)

Reported on 3 benchmarks across 3 tasks · 1 paper

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

Medical1 result

Semantic SegmentationonCOCO-Stuff-27
Clustering [Accuracy]· 2022-05-30
42.36
best: 81.1 (DynaSeg - FSF (ResNet-18 FPN))
Self-Supervised Visual Representation Learning with Semantic Grouping arXiv:2205.15288

Computer Vision1 result

Unsupervised Semantic SegmentationonCOCO-Stuff-27
Clustering [Accuracy]· 2022-05-30
42.36
best: 81.1 (DynaSeg - FSF (ResNet-18 FPN))
Self-Supervised Visual Representation Learning with Semantic Grouping arXiv:2205.15288

Audio1 result

10-shot image generationonCOCO-Stuff-27
Clustering [Accuracy]· 2022-05-30
42.36
best: 81.1 (DynaSeg - FSF (ResNet-18 FPN))
Self-Supervised Visual Representation Learning with Semantic Grouping arXiv:2205.15288