Model card
Co-DETR (Swin-L).
Researchopen-sourceUnknown paramsCollaborative DETR + Swin-L backbone1 current SOTA
Collaborative hybrid assignments training for DETR. 66.0 mAP on COCO test-dev. ICCV 2023.
§ 01 · Benchmarks
Every benchmark Co-DETR (Swin-L) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | COCO | Computer Vision · Object Detection | mAP | 66.0% | #1 | — | source ↗ |
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.
§ 02 · Strengths by area
Where Co-DETR (Swin-L) actually performs.
§ 04 · Related models
Other Research models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
1
result
0 of 1 rows marked verified.