HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

Real Time Object Detection On Coco

Metrics

FPS (V100, b=1)
box AP

Results

Performance results of various models on this benchmark

Paper TitleRepository
DEIM-D-FINE-X+78 (T4)59.5DEIM: DETR with Improved Matching for Fast Convergence
D-FINE-X+78 (T4)59.3D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement
YOLOv6-L6(1280)2657.2YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
D-FINE-L+124 (T4)57.10/1 Deep Neural Networks via Block Coordinate Descent-
PRB-FPN6-E-ELAN(1280)3156.9Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection
YOLOv7-E6E(1280)3656.8YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
YOLOv7-D6(1280)4456.6YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
DEIM-D-FINE-X78 (T4)56.5DEIM: DETR with Improved Matching for Fast Convergence
RT-DETR-H(640)40 (T4)56.3DETRs Beat YOLOs on Real-time Object Detection
YOLOv7-E6(1280)5656YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
D-FINE-X78 (T4)55.8D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement
YOLOv9-E-55.6YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
YOLOR-D63055.4You Only Learn One Representation: Unified Network for Multiple Tasks
YOLOv12x85 (T4)55.2YOLOv12: A Breakdown of the Key Architectural Features-
D-FINE-M+178 (T4)55.1D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement
GELAN-E-55.0YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
YOLOv7-W6(1280)8454.9YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
YOLOR-E63754.8You Only Learn One Representation: Unified Network for Multiple Tasks
RT-DETR-X74 (T4)54.8DETRs Beat YOLOs on Real-time Object Detection
PP-YOLOE+_X4554.7PP-YOLOE: An evolved version of YOLO
0 of 82 row(s) selected.