Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

ReasonSeg

Benchmarks

Task NameDataset NameSOTA ResultTrend
Reasoning SegmentationReasonSeg (val)
cIoU74.9
145
Reasoning SegmentationReasonSeg (test)
gIoU73.8
102
Reasoning SegmentationReasonSeg long (test)
cIoU0.733
40
Reasoning SegmentationReasonSeg short (test)
cIoU59.4
40
Reasoning SegmentationReasonSeg
gIoU59.2
17
Visual GroundingReasonSeg
cIoU (Overall)61.6
15
Referring Expression SegmentationReasonSeg (test)
mIoU64.2
9
Referring Expression SegmentationReasonSeg (val)
mIoU66.3
9
Reasoning segmentationREASONSEG HARD (test)
gIoU58.6
6
Showing 9 of 9 rows