Codesota · Models · DETRMeta AI / FAIR8 results · 2 benchmarks
Model card

DETR.

Meta AI / FAIRopen-sourceUnknown paramsUnknown

Imported from Papers With Code

§ 02 · Benchmarks

Every benchmark DETR has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01publaynet-valComputer Vision · Document Layout Analysistable1.0%#1/152023-06-23source ↗
02publaynet-valComputer Vision · Document Layout Analysisfigure1.0%#1/142023-06-23source ↗
03publaynet-valComputer Vision · Document Layout Analysisoverall1.0%#3/142023-06-23source ↗
04publaynet-valComputer Vision · Document Layout Analysislist1.0%#3/142023-06-23source ↗
05publaynet-valComputer Vision · Document Layout Analysistitle0.9%#4/142023-06-23source ↗
06publaynet-valComputer Vision · Document Layout Analysistext0.9%#4/142023-06-23source ↗
07COCOComputer Vision · Object Detectionbox-map43.3%#9/112020-05-26source ↗
08COCOComputer Vision · Object Detectionmap42.0%#49/55source ↗
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 DETR actually performs.

Computer Vision
2
benchmarks
avg rank #9.3
§ 04 · Papers

2 papers with results for DETR.

  1. 2023-06-23· Computer Vision· 6 results

    Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images

  2. 2020-05-26· 1 result

    End-to-End Object Detection with Transformers

§ 05 · Related models

Other Meta AI / FAIR models scored on Codesota.

Mask R-CNN
Unknown params · 1 result
MAE ViT-H/14
0 results
§ 06 · Sources & freshness

Where these numbers come from.

papers-with-code
6
results
editorial
1
result
pwc-dump
1
result
6 of 8 rows marked verified. · first result 2020-05-26, latest 2023-06-23.