TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Methodology/2D Object Detection/COCO 2017 val

2D Object Detection on COCO 2017 val

Metric: APS (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕APS▼AugmentationsPaperDate↕Code
1Mr. DETR (Swin-L, 1x, 5cale)47.7YesMr. DETR: Instructive Multi-Route Training for D...2024-12-13Code
2MI-DETR (Swin-L 1x)42.5NoMI-DETR: An Object Detection Model with Multi-ti...2025-03-03Code
3Relation-DETR (Swin-L 2x)41.8NoRelation DETR: Exploring Explicit Position Relat...2024-07-16Code
4Relation-DETR (Swin-L 1x)41.2NoRelation DETR: Exploring Explicit Position Relat...2024-07-16Code
5Salience-DETR (Focal-L 1x)40.9NoSalience DETR: Enhancing Detection Transformer w...2024-03-24Code
6Mr. DETR (Swin-L, 1x, 4scale)40.8NoMr. DETR: Instructive Multi-Route Training for D...2024-12-13Code
7Salience-DETR (Swin-L 1x)40.2NoSalience DETR: Enhancing Detection Transformer w...2024-03-24Code
8Relation-DETR (ResNet50 2x)36.1NoRelation DETR: Exploring Explicit Position Relat...2024-07-16Code
9Relation-DETR (ResNet50 1x)36.1NoRelation DETR: Exploring Explicit Position Relat...2024-07-16Code
10Salience-DETR (ResNet50 1x)33.3NoSalience DETR: Enhancing Detection Transformer w...2024-03-24Code
11ViDT Swin-base30.6NoViDT: An Efficient and Effective Fully Transform...2021-10-08Code
12ViDT Swin-small29.2NoViDT: An Efficient and Effective Fully Transform...2021-10-08Code
13ViDT Swin-tiny25.9NoViDT: An Efficient and Effective Fully Transform...2021-10-08Code
14ViDT Swin-nano23.2NoViDT: An Efficient and Effective Fully Transform...2021-10-08Code