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
No recorded benchmark results yet.
This model is in the registry but doesn’t have any benchmark_results rows yet. If you have a score, submit it →
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.