DLFE

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.

Computer Vision2 results

Scene ParsingonVisual Genome
Recall@50· 2021-07-05
25.4
best: 32.9 (SpeaQ (without reweighting))
Recovering the Unbiased Scene Graphs from the Biased Ones arXiv:2107.02112
Scene Graph GenerationonVisual Genome
Recall@50· 2021-07-05
25.4
best: 32.9 (SpeaQ (without reweighting))
Recovering the Unbiased Scene Graphs from the Biased Ones arXiv:2107.02112

Audio1 result

2D Semantic SegmentationonVisual Genome
Recall@50· 2021-07-05
25.4
best: 32.9 (SpeaQ (without reweighting))
Recovering the Unbiased Scene Graphs from the Biased Ones arXiv:2107.02112