MOD

Reported on 6 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision6 results

Instance SegmentationonDAVIS 2016
J score· 2022-10-01
73.9
best: 83 (RCF (with Post-Processing))
SOTA
Motion-inductive Self-supervised Object Discovery in Videos arXiv:2210.00221
Unsupervised Object SegmentationonDAVIS 2016
J score· 2022-10-01
73.9
best: 83 (RCF (with Post-Processing))
SOTA
Motion-inductive Self-supervised Object Discovery in Videos arXiv:2210.00221
Instance SegmentationonSegTrack-v2
mIoU· 2022-10-01
62.2
best: 79.6 (RCF (with post-processing))
Motion-inductive Self-supervised Object Discovery in Videos arXiv:2210.00221
Instance SegmentationonFBMS-59
mIoU· 2022-10-01
61.3
best: 72.4 (RCF (with post-processing))
Motion-inductive Self-supervised Object Discovery in Videos arXiv:2210.00221
Unsupervised Object SegmentationonSegTrack-v2
mIoU· 2022-10-01
62.2
best: 79.6 (RCF (with post-processing))
Motion-inductive Self-supervised Object Discovery in Videos arXiv:2210.00221
Unsupervised Object SegmentationonFBMS-59
mIoU· 2022-10-01
61.3
best: 72.4 (RCF (with post-processing))
Motion-inductive Self-supervised Object Discovery in Videos arXiv:2210.00221