Codesota · Models · OneFormer (DiNAT-L)SHI Labs2 results · 2 benchmarks
Model card

OneFormer (DiNAT-L).

SHI Labsopen-sourceUnknown paramsUniversal image segmentation with task-conditioned joint training (DiNAT-L backbone)

First multi-task universal image segmentation framework. Task-conditioned architecture trained once on panoptic, instance, and semantic jointly. DiNAT-L backbone achieves 58.3 mIoU (ss) on ADE20K val. CVPR 2023.

§ 02 · Benchmarks

Every benchmark OneFormer (DiNAT-L) has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01CityscapesVision & Documents · Semantic Segmentationmiou83.0%#3/32026-04-20source ↗
02ADE20KVision & Documents · Semantic SegmentationmIoU58.3%#8/132026-04-20unverified
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where OneFormer (DiNAT-L) actually performs.

Vision & Documents
2
benchmarks
avg rank #5.5
§ 05 · Related models

Other SHI Labs models scored on Codesota.

SeMask-L
Unknown params · 0 results
§ 06 · Sources & freshness

Where these numbers come from.

codesota-api
1
result
src
1
result
1 of 2 rows marked verified.