SIMO

Reported on 4 benchmarks across 2 tasks

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

Computer Vision4 results

Instance SegmentationonSegTrack-v2
mIoU
62
best: 79.6 (RCF (with post-processing))
Instance SegmentationonDAVIS 2016
J score· uses extra data
67.8
best: 83 (RCF (with Post-Processing))
Unsupervised Object SegmentationonSegTrack-v2
mIoU
62
best: 79.6 (RCF (with post-processing))
Unsupervised Object SegmentationonDAVIS 2016
J score· uses extra data
67.8
best: 83 (RCF (with Post-Processing))