FCN + CascadePSP

Reported on 4 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.

Medical2 results

Semantic SegmentationonBIG
IoU· uses extra data· 2020-05-06
77.87
best: 93.93 (PSPNet + CascadePSP)
CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement arXiv:2005.02551
Semantic SegmentationonBIG
mBA· uses extra data· 2020-05-06
67.04
best: 75.32 (PSPNet + CascadePSP)
CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement arXiv:2005.02551

Audio2 results

10-shot image generationonBIG
IoU· uses extra data· 2020-05-06
77.87
best: 93.93 (PSPNet + CascadePSP)
CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement arXiv:2005.02551
10-shot image generationonBIG
mBA· uses extra data· 2020-05-06
67.04
best: 75.32 (PSPNet + CascadePSP)
CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement arXiv:2005.02551