Codesota · Models · D-FINE-XPeterande et al.1 results · 1 benchmarks
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.

#BenchmarkArea · TaskMetricValueRankDateSource
01COCOComputer Vision · Object Detectionmap59.3%#7/55source ↗
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 D-FINE-X actually performs.

Computer Vision
1
benchmark
avg rank #7.0
§ 04 · Papers

1 paper with results for D-FINE-X.

  1. 2024-10-17· 1 result

    D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement

§ 05 · Related models

Other Peterande et al. models scored on Codesota.

D-FINE-X (Objects365)
Unknown params · 0 results
§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
1
result
0 of 1 rows marked verified.