Object Detection On Coco 2017 Val

评估指标

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
Mr. DETR (Swin-L, 1x, 4scale)	58.4	Mr. DETR: Instructive Multi-Route Training for Detection Transformers
MI-DETR (Swin-L 1x)	58.2	MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism
Relation-DETR (Swin-L 2x)	58.1	Relation DETR: Exploring Explicit Position Relation Prior for Object Detection
Relation-DETR (Swin-L 1x)	57.8	Relation DETR: Exploring Explicit Position Relation Prior for Object Detection
Salience-DETR (Focal-L 1x)	57.3	Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement
YOLOv6-L6(46 fps, V100, bs1)	57.2	YOLOv6 v3.0: A Full-Scale Reloading
Salience-DETR (Swin-L 1x)	56.5	Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement
MogaNet-XL (Cascade Mask R-CNN)	56.2	MogaNet: Multi-order Gated Aggregation Network
MogaNet-L (Cascade Mask R-CNN)	53.3	MogaNet: Multi-order Gated Aggregation Network
MogaNet-B (Cascade Mask R-CNN)	52.6	MogaNet: Multi-order Gated Aggregation Network
Relation-DETR (ResNet50 2x)	52.1	Relation DETR: Exploring Explicit Position Relation Prior for Object Detection
Relation-DETR (ResNet50 1x)	51.7	Relation DETR: Exploring Explicit Position Relation Prior for Object Detection
MogaNet-S (Cascade Mask R-CNN)	51.6	MogaNet: Multi-order Gated Aggregation Network
RF-ConvNeXt-T Cascade R-CNN	50.9	RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
Salience-DETR (ResNet50 1x)	50.0	Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement
SQR-Adamixer-R101	49.8	Enhanced Training of Query-Based Object Detection via Selective Query Recollection
MogaNet-L (Mask R-CNN 1x)	49.4	MogaNet: Multi-order Gated Aggregation Network
ViDT Swin-base	49.2	ViDT: An Efficient and Effective Fully Transformer-based Object Detector
SQR-Adamixer-R50	48.9	Enhanced Training of Query-Based Object Detection via Selective Query Recollection
MogaNet-L (RetinaNet 1x)	48.7	MogaNet: Multi-order Gated Aggregation Network

0 of 32 row(s) selected.