2D Object Detection on COCO 2017 val

Metric: AP75 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide augmentations

Sort:

#	Model↕	AP75▼	Augmentations	Paper	Date↕	Code
1	Mr. DETR (Swin-L, 1x, 5cale)	67.6	Yes	Mr. DETR: Instructive Multi-Route Training for D...	2024-12-13	Code
2	Mr. DETR (Swin-L, 1x, 4scale)	63.9	No	Mr. DETR: Instructive Multi-Route Training for D...	2024-12-13	Code
3	Relation-DETR (Swin-L 2x)	63.5	No	Relation DETR: Exploring Explicit Position Relat...	2024-07-16	Code
4	MI-DETR (Swin-L 1x)	63.4	No	MI-DETR: An Object Detection Model with Multi-ti...	2025-03-03	Code
5	Relation-DETR (Swin-L 1x)	62.9	No	Relation DETR: Exploring Explicit Position Relat...	2024-07-16	Code
6	Salience-DETR (Focal-L 1x)	62.3	No	Salience DETR: Enhancing Detection Transformer w...	2024-03-24	Code
7	Salience-DETR (Swin-L 1x)	61.5	No	Salience DETR: Enhancing Detection Transformer w...	2024-03-24	Code
8	Relation-DETR (ResNet50 2x)	56.6	No	Relation DETR: Exploring Explicit Position Relat...	2024-07-16	Code
9	Relation-DETR (ResNet50 1x)	56.3	No	Relation DETR: Exploring Explicit Position Relat...	2024-07-16	Code
10	DyHead (Swin-T, multi scale)	54.3	No	Dynamic Head: Unifying Object Detection Heads wi...	2021-06-15	Code
11	Salience-DETR (ResNet50 1x)	54.2	No	Salience DETR: Enhancing Detection Transformer w...	2024-03-24	Code
12	ViDT Swin-base	53.1	No	ViDT: An Efficient and Effective Fully Transform...	2021-10-08	Code
13	ViDT Swin-small	51.4	No	ViDT: An Efficient and Effective Fully Transform...	2021-10-08	Code
14	ViDT Swin-tiny	48.7	No	ViDT: An Efficient and Effective Fully Transform...	2021-10-08	Code
15	ViDT Swin-nano	43.3	No	ViDT: An Efficient and Effective Fully Transform...	2021-10-08	Code

#1Mr. DETR (Swin-L, 1x, 5cale)SOTA
67.6
AP75· Augmentations· 2024-12-13
Mr. DETR: Instructive Multi-Route Training for Detection Transformers Code
#2Mr. DETR (Swin-L, 1x, 4scale)
63.9
AP75· 2024-12-13
Mr. DETR: Instructive Multi-Route Training for Detection Transformers Code
#3Relation-DETR (Swin-L 2x)SOTA
63.5
AP75· 2024-07-16
Relation DETR: Exploring Explicit Position Relation Prior for Object Detection Code
#4MI-DETR (Swin-L 1x)
63.4
AP75· 2025-03-03
MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism Code
#5Relation-DETR (Swin-L 1x)
62.9
AP75· 2024-07-16
Relation DETR: Exploring Explicit Position Relation Prior for Object Detection Code
#6Salience-DETR (Focal-L 1x)SOTA
62.3
AP75· 2024-03-24
Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement Code
#7Salience-DETR (Swin-L 1x)
61.5
AP75· 2024-03-24
Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement Code
#8Relation-DETR (ResNet50 2x)
56.6
AP75· 2024-07-16
Relation DETR: Exploring Explicit Position Relation Prior for Object Detection Code
#9Relation-DETR (ResNet50 1x)
56.3
AP75· 2024-07-16
Relation DETR: Exploring Explicit Position Relation Prior for Object Detection Code
#10DyHead (Swin-T, multi scale)SOTA
54.3
AP75· 2021-06-15
Dynamic Head: Unifying Object Detection Heads with Attentions Code
#11Salience-DETR (ResNet50 1x)
54.2
AP75· 2024-03-24
Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement Code
#12ViDT Swin-base
53.1
AP75· 2021-10-08
ViDT: An Efficient and Effective Fully Transformer-based Object Detector Code
#13ViDT Swin-small
51.4
AP75· 2021-10-08
ViDT: An Efficient and Effective Fully Transformer-based Object Detector Code
#14ViDT Swin-tiny
48.7
AP75· 2021-10-08
ViDT: An Efficient and Effective Fully Transformer-based Object Detector Code
#15ViDT Swin-nano
43.3
AP75· 2021-10-08
ViDT: An Efficient and Effective Fully Transformer-based Object Detector Code