CogTree (MOTIFS-ResNeXt-101-FPN backbone; SGDet mode)

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
mR@20· 2020-09-16
7.9
best: 35.6 (SHA-GCL (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode))
CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation arXiv:2009.07526
Scene Graph GenerationonVisual Genome
mR@20· 2020-09-16
7.9
best: 35.6 (SHA-GCL (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode))
CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation arXiv:2009.07526

Audio1 result

2D Semantic SegmentationonVisual Genome
mR@20· 2020-09-16
7.9
best: 35.6 (SHA-GCL (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode))
CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation arXiv:2009.07526