Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Methodology
/
2D Object Detection
/
COCO 2017 val
2D Object Detection on COCO 2017 val
Metric: APM (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Hide augmentations
Export CSV
Sort:
APM (best first)
APM (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
APM
▼
Augmentations
Paper
Date
↕
Code
1
Mr. DETR (Swin-L, 1x, 5cale)
65.6
Yes
Mr. DETR: Instructive Multi-Route Training for D...
2024-12-13
Code
2
Relation-DETR (Swin-L 2x)
63
No
Relation DETR: Exploring Explicit Position Relat...
2024-07-16
Code
3
Mr. DETR (Swin-L, 1x, 4scale)
62.8
No
Mr. DETR: Instructive Multi-Route Training for D...
2024-12-13
Code
4
MI-DETR (Swin-L 1x)
62.8
No
MI-DETR: An Object Detection Model with Multi-ti...
2025-03-03
Code
5
Relation-DETR (Swin-L 1x)
62.1
No
Relation DETR: Exploring Explicit Position Relat...
2024-07-16
Code
6
Salience-DETR (Focal-L 1x)
61.8
No
Salience DETR: Enhancing Detection Transformer w...
2024-03-24
Code
7
Salience-DETR (Swin-L 1x)
61.2
No
Salience DETR: Enhancing Detection Transformer w...
2024-03-24
Code
8
Relation-DETR (ResNet50 2x)
56
No
Relation DETR: Exploring Explicit Position Relat...
2024-07-16
Code
9
Relation-DETR (ResNet50 1x)
55.6
No
Relation DETR: Exploring Explicit Position Relat...
2024-07-16
Code
10
Salience-DETR (ResNet50 1x)
54.4
No
Salience DETR: Enhancing Detection Transformer w...
2024-03-24
Code
11
ViDT Swin-base
52.6
No
ViDT: An Efficient and Effective Fully Transform...
2021-10-08
Code
12
ViDT Swin-small
50.7
No
ViDT: An Efficient and Effective Fully Transform...
2021-10-08
Code
13
ViDT Swin-tiny
47.6
No
ViDT: An Efficient and Effective Fully Transform...
2021-10-08
Code
14
ViDT Swin-nano
42.5
No
ViDT: An Efficient and Effective Fully Transform...
2021-10-08
Code
#1
Mr. DETR (Swin-L, 1x, 5cale)
SOTA
65.6
APM
· Augmentations
· 2024-12-13
Mr. DETR: Instructive Multi-Route Training for Detection Transformers
Code
#2
Relation-DETR (Swin-L 2x)
SOTA
63
APM
· 2024-07-16
Relation DETR: Exploring Explicit Position Relation Prior for Object Detection
Code
#3
Mr. DETR (Swin-L, 1x, 4scale)
62.8
APM
· 2024-12-13
Mr. DETR: Instructive Multi-Route Training for Detection Transformers
Code
#4
MI-DETR (Swin-L 1x)
62.8
APM
· 2025-03-03
MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism
Code
#5
Relation-DETR (Swin-L 1x)
62.1
APM
· 2024-07-16
Relation DETR: Exploring Explicit Position Relation Prior for Object Detection
Code
#6
Salience-DETR (Focal-L 1x)
SOTA
61.8
APM
· 2024-03-24
Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement
Code
#7
Salience-DETR (Swin-L 1x)
61.2
APM
· 2024-03-24
Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement
Code
#8
Relation-DETR (ResNet50 2x)
56
APM
· 2024-07-16
Relation DETR: Exploring Explicit Position Relation Prior for Object Detection
Code
#9
Relation-DETR (ResNet50 1x)
55.6
APM
· 2024-07-16
Relation DETR: Exploring Explicit Position Relation Prior for Object Detection
Code
#10
Salience-DETR (ResNet50 1x)
54.4
APM
· 2024-03-24
Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement
Code
#11
ViDT Swin-base
SOTA
52.6
APM
· 2021-10-08
ViDT: An Efficient and Effective Fully Transformer-based Object Detector
Code
#12
ViDT Swin-small
50.7
APM
· 2021-10-08
ViDT: An Efficient and Effective Fully Transformer-based Object Detector
Code
#13
ViDT Swin-tiny
47.6
APM
· 2021-10-08
ViDT: An Efficient and Effective Fully Transformer-based Object Detector
Code
#14
ViDT Swin-nano
42.5
APM
· 2021-10-08
ViDT: An Efficient and Effective Fully Transformer-based Object Detector
Code