Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Methodology
/
2D Object Detection
/
COCO 2017 val
2D Object Detection on COCO 2017 val
Metric: APS (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Hide augmentations
Export CSV
#
Model
↕
APS
▼
Augmentations
Paper
Date
↕
Code
1
Mr. DETR (Swin-L, 1x, 5cale)
47.7
Yes
Mr. DETR: Instructive Multi-Route Training for D...
2024-12-13
Code
2
MI-DETR (Swin-L 1x)
42.5
No
MI-DETR: An Object Detection Model with Multi-ti...
2025-03-03
Code
3
Relation-DETR (Swin-L 2x)
41.8
No
Relation DETR: Exploring Explicit Position Relat...
2024-07-16
Code
4
Relation-DETR (Swin-L 1x)
41.2
No
Relation DETR: Exploring Explicit Position Relat...
2024-07-16
Code
5
Salience-DETR (Focal-L 1x)
40.9
No
Salience DETR: Enhancing Detection Transformer w...
2024-03-24
Code
6
Mr. DETR (Swin-L, 1x, 4scale)
40.8
No
Mr. DETR: Instructive Multi-Route Training for D...
2024-12-13
Code
7
Salience-DETR (Swin-L 1x)
40.2
No
Salience DETR: Enhancing Detection Transformer w...
2024-03-24
Code
8
Relation-DETR (ResNet50 2x)
36.1
No
Relation DETR: Exploring Explicit Position Relat...
2024-07-16
Code
9
Relation-DETR (ResNet50 1x)
36.1
No
Relation DETR: Exploring Explicit Position Relat...
2024-07-16
Code
10
Salience-DETR (ResNet50 1x)
33.3
No
Salience DETR: Enhancing Detection Transformer w...
2024-03-24
Code
11
ViDT Swin-base
30.6
No
ViDT: An Efficient and Effective Fully Transform...
2021-10-08
Code
12
ViDT Swin-small
29.2
No
ViDT: An Efficient and Effective Fully Transform...
2021-10-08
Code
13
ViDT Swin-tiny
25.9
No
ViDT: An Efficient and Effective Fully Transform...
2021-10-08
Code
14
ViDT Swin-nano
23.2
No
ViDT: An Efficient and Effective Fully Transform...
2021-10-08
Code