HyperAIHyperAI초신경

Command Palette

Search for a command to run...

플랫폼

Object Detection On Coco 2017 Val

평가 지표

AP

평가 결과

이 벤치마크에서 각 모델의 성능 결과

Paper Title
Mr. DETR (Swin-L, 1x, 4scale)58.4Mr. DETR: Instructive Multi-Route Training for Detection Transformers
MI-DETR (Swin-L 1x)58.2MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism
Relation-DETR (Swin-L 2x)58.1Relation DETR: Exploring Explicit Position Relation Prior for Object Detection
Relation-DETR (Swin-L 1x)57.8Relation DETR: Exploring Explicit Position Relation Prior for Object Detection
Salience-DETR (Focal-L 1x)57.3Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement
YOLOv6-L6(46 fps, V100, bs1)57.2YOLOv6 v3.0: A Full-Scale Reloading
Salience-DETR (Swin-L 1x)56.5Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement
MogaNet-XL (Cascade Mask R-CNN)56.2MogaNet: Multi-order Gated Aggregation Network
MogaNet-L (Cascade Mask R-CNN)53.3MogaNet: Multi-order Gated Aggregation Network
MogaNet-B (Cascade Mask R-CNN)52.6MogaNet: Multi-order Gated Aggregation Network
Relation-DETR (ResNet50 2x)52.1Relation DETR: Exploring Explicit Position Relation Prior for Object Detection
Relation-DETR (ResNet50 1x)51.7Relation DETR: Exploring Explicit Position Relation Prior for Object Detection
MogaNet-S (Cascade Mask R-CNN)51.6MogaNet: Multi-order Gated Aggregation Network
RF-ConvNeXt-T Cascade R-CNN50.9RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
Salience-DETR (ResNet50 1x)50.0Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement
SQR-Adamixer-R10149.8Enhanced Training of Query-Based Object Detection via Selective Query Recollection
MogaNet-L (Mask R-CNN 1x)49.4MogaNet: Multi-order Gated Aggregation Network
ViDT Swin-base49.2ViDT: An Efficient and Effective Fully Transformer-based Object Detector
SQR-Adamixer-R5048.9Enhanced Training of Query-Based Object Detection via Selective Query Recollection
MogaNet-L (RetinaNet 1x)48.7MogaNet: Multi-order Gated Aggregation Network
0 of 32 row(s) selected.