Skip to content

AgbajeAyomipo/DetectionModelVersus

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DetectionModelVersus

A Real-World Benchmark of Modern Object Detection Models

Overview

DetectionModelVersus is a newly-running benchmark project focused on training, evaluating, and comparing state-of-the-art object detection models using both quantitative metrics and real-world video inference.

Every week, two models are trained under identical conditions, evaluated, and compared. Results are published publicly and discussed on LinkedIn.

Models Covered

  • YOLO11 (n, s, m, l, x)
  • YOLO26 (n, s, m, l, x)
  • RT-DETR (l, x)
  • RF-DETR (Nano, Small, Medium, Large, XLarge, 2XLarge)

Weekly Model Pairings:

  • Week 1: YOLO11n vs RFDETRNano

  • Week 2: YOLO26n vs YOLO11s

  • Week 3: YOLO26s vs RFDETRSmall

  • Week 4: YOLO11m vs RFDETRMedium

  • Week 5: YOLO26m vs YOLO11l

  • Week 6: RFDETRLarge vs RTDETRl

  • Week 7: YOLO26l vs YOLO11x

  • Week 8: YOLO26x vs RTDETRx

  • Week 9: RFDETRXLarge vs RFDETR2XLarge

  • Week 10: Final recap & cross-model analysis

Evaluation Focus

Accuracy Metrics

  • mAP@50
  • mAP@50:95
  • Precision
  • Recall

Performance Metrics

  • Inference FPS
  • Latency per frame
  • GPU memory usage

Real-World Video Behavior

  • Stability across frames
  • Performance on motion blur
  • Small object detection
  • Occlusion handling

Weekly Benchmark Format

  • Two models trained per week
  • Identical datasets, augmentations, and training schedules
  • Side-by-side video inference
  • Public metrics tables
  • Results released every Thursday

Hardware

All experiments are run on consistent hardware to ensure fair comparison. See hardware.md for full details.

Results

  • Weekly results are stored in the benchmarks directory
  • Video inference outputs are stored in results/videos

Why This Project?

Most benchmarks focus only on static accuracy metrics. DetectorModelVersus emphasizes:

  • Practical deployment behavior
  • Compute efficiency
  • Visual detection quality in motion

This makes the results more useful for real-world production systems.

Author

Agbaje Ayomipo
Data Scientist | Computer Vision Enthusiast

Weekly insights and breakdowns are shared on LinkedIn. Here

About

A weekly benchmark project focused on training and comparing modern object detection models under identical conditions. The repository evaluates accuracy, speed, resource usage, and real-world video inference behavior, providing practical insights beyond static metrics for deployment-ready computer vision systems.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors