Object Detection On Coco Minival

评估指标

AP50

AP75

APL

APM

APS

box AP

评测结果

各个模型在此基准测试上的表现结果

							Paper Title	Repository
Co-DETR	-	-	-	-	-	65.9	DETRs with Collaborative Hybrid Assignments Training
M3I Pre-training (InternImage-H)	-	-	-	-	-	65.0	Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
InternImage-H	-	-	-	-	-	65.0	InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Co-DETR (Swin-L)	-	-	-	-	-	64.7	DETRs with Collaborative Hybrid Assignments Training
Focal-Stable-DINO (Focal-Huge, no TTA)	81.5	71.4	78.5	68.5	50.4	64.6	A Strong and Reproducible Object Detector with Only Public Datasets
EVA	82.1	70.8	78.5	68.4	49.4	64.5	EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
ViT-CoMer	-	-	-	-	-	64.3	ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions	-
FocalNet-H (DINO)	-	-	-	-	-	64.2	Focal Modulation Networks
InternImage-XL	-	-	-	-	-	64.2	InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
CP-DETR-L Swin-L(Fine tuning separately in COCO)	-	-	-	-	-	64.1	CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection	-
RevCol-H(DINO)	-	-	-	-	-	63.8	Reversible Column Networks
DINO (Swin-L)	-	-	-	-	-	63.2	DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
Grounding DINO	-	-	-	-	-	63.0	Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
SwinV2-G (HTC++)	-	-	-	-	-	62.5	Swin Transformer V2: Scaling Up Capacity and Resolution
GLEE-Pro	-	-	-	-	-	62.0	General Object Foundation Model for Images and Videos at Scale
Florence-CoSwin-H	-	-	-	-	-	62	Florence: A New Foundation Model for Computer Vision
ViTDet, ViT-H Cascade (multiscale)	-	-	-	-	-	61.3	Exploring Plain Vision Transformer Backbones for Object Detection
GLIP (Swin-L, multi-scale)	-	-	-	-	-	60.8	Grounded Language-Image Pre-training
Soft Teacher + Swin-L (HTC++, multi-scale)	-	-	-	-	-	60.7	End-to-End Semi-Supervised Object Detection with Soft Teacher
UNINEXT-H	77.5	66.7	75.3	64.8	45.1	60.6	Universal Instance Perception as Object Discovery and Retrieval

0 of 219 row(s) selected.