SlotAttention

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

Instance SegmentationonShelf&Tote Training Dataset
ARI· 2021-04-20
0.03
best: 0.55 (GENESIS-V2)
GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement arXiv:2104.09958
Instance SegmentationonShapeStacks
ARI-FG· 2021-04-20
0.76
best: 0.82 (AST)
GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement arXiv:2104.09958
Instance SegmentationonObjectsRoom
ARI-FG· 2021-04-20
0.79
best: 0.87 (AST)
GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement arXiv:2104.09958
Unsupervised Object SegmentationonShelf&Tote Training Dataset
ARI· 2021-04-20
0.03
best: 0.55 (GENESIS-V2)
GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement arXiv:2104.09958
Unsupervised Object SegmentationonShapeStacks
ARI-FG· 2021-04-20
0.76
best: 0.82 (AST)
GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement arXiv:2104.09958
Unsupervised Object SegmentationonObjectsRoom
ARI-FG· 2021-04-20
0.79
best: 0.87 (AST)
GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement arXiv:2104.09958