Model card
D-FINE-X.
Peterande et al.open-sourceUnknown paramsDETR + Fine-grained Distribution Refinement (FDR)
D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement. X-large variant achieves 55.8 AP on COCO val2017 without extra pretraining. ICLR 2025 Spotlight. arXiv Oct 2024.
§ 02 · Benchmarks
Every benchmark D-FINE-X has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | COCO | Computer Vision · Object Detection | map | 59.3% | #7 | — | 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.
§ 04 · Papers
1 paper with results for D-FINE-X.
§ 05 · Related models
Other Peterande et al. models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
1
result
0 of 1 rows marked verified.