2D Classification on COCO 2017

Metric: mAP (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	mAP▼	Augmentations	Paper	Date↕	Code
1	UniRepLKNet-XL++	56.4	No	UniRepLKNet: A Universal Perception Large-Kernel...	2023-11-27	Code
2	UniRepLKNet-L++	55.8	No	UniRepLKNet: A Universal Perception Large-Kernel...	2023-11-27	Code
3	UniRepLKNet-B++	54.8	No	UniRepLKNet: A Universal Perception Large-Kernel...	2023-11-27	Code
4	UniRepLKNet-S++	54.3	No	UniRepLKNet: A Universal Perception Large-Kernel...	2023-11-27	Code
5	MixMIM-L	54.1	No	MixMAE: Mixed and Masked Autoencoder for Efficie...	2022-05-26	Code
6	UniRepLKNet-S	53	No	UniRepLKNet: A Universal Perception Large-Kernel...	2023-11-27	Code
7	MixMIM-B	52.2	No	MixMAE: Mixed and Masked Autoencoder for Efficie...	2022-05-26	Code
8	UniRepLKNet-T	51.7	No	UniRepLKNet: A Universal Perception Large-Kernel...	2023-11-27	Code
9	BiFormer-B (IN1k pretrain, MaskRCNN 12ep)	48.6	No	BiFormer: Vision Transformer with Bi-Level Routi...	2023-03-15	Code
10	DeBiFormer-B (IN1k pretrain, MaskRCNN 12ep)	48.5	No	DeBiFormer: Vision Transformer with Deformable A...	2024-10-11	Code
11	BiFormer-S (IN1k pretrain, MaskRCNN 12ep)	47.8	No	BiFormer: Vision Transformer with Bi-Level Routi...	2023-03-15	Code
12	DeBiFormer-S (IN1k pretrain, MaskRCNN 12ep)	47.5	No	DeBiFormer: Vision Transformer with Deformable A...	2024-10-11	Code
13	DeBiFormer-B (IN1k pretrain, Retina)	47.1	No	DeBiFormer: Vision Transformer with Deformable A...	2024-10-11	Code
14	DeBiFormer-S (IN1k pretrain, Retina)	45.6	No	DeBiFormer: Vision Transformer with Deformable A...	2024-10-11	Code
15	YOLO-Drone	35.45	No	YOLO-Drone:Airborne real-time detection of dense...	2023-04-14	-

#1UniRepLKNet-XL++SOTA
56.4
mAP· 2023-11-27
UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition Code
#2UniRepLKNet-L++
55.8
mAP· 2023-11-27
UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition Code
#3UniRepLKNet-B++
54.8
mAP· 2023-11-27
UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition Code
#4UniRepLKNet-S++
54.3
mAP· 2023-11-27
UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition Code
#5MixMIM-LSOTA
54.1
mAP· 2022-05-26
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers Code
#6UniRepLKNet-S
53
mAP· 2023-11-27
UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition Code
#7MixMIM-B
52.2
mAP· 2022-05-26
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers Code
#8UniRepLKNet-T
51.7
mAP· 2023-11-27
UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition Code
#9BiFormer-B (IN1k pretrain, MaskRCNN 12ep)
48.6
mAP· 2023-03-15
BiFormer: Vision Transformer with Bi-Level Routing Attention Code
#10DeBiFormer-B (IN1k pretrain, MaskRCNN 12ep)
48.5
mAP· 2024-10-11
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention Code
#11BiFormer-S (IN1k pretrain, MaskRCNN 12ep)
47.8
mAP· 2023-03-15
BiFormer: Vision Transformer with Bi-Level Routing Attention Code
#12DeBiFormer-S (IN1k pretrain, MaskRCNN 12ep)
47.5
mAP· 2024-10-11
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention Code
#13DeBiFormer-B (IN1k pretrain, Retina)
47.1
mAP· 2024-10-11
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention Code
#14DeBiFormer-S (IN1k pretrain, Retina)
45.6
mAP· 2024-10-11
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention Code
#15YOLO-Drone
35.45
mAP· 2023-04-14
YOLO-Drone:Airborne real-time detection of dense small objects from high-altitude perspective