cv-detection

Installation
SKILL.md

Object Detection Best Practice

Architecture families:

  • One-stage: YOLO (v5/v8), SSD, RetinaNet, FCOS
  • Two-stage: Faster R-CNN, Cascade R-CNN
  • Transformer: DETR, DINO, RT-DETR

Training recipe:

  • Use pre-trained backbone (ImageNet)
  • Multi-scale training and testing
  • IoU threshold: 0.5 for mAP50, 0.5:0.95 for mAP
  • Use FPN for multi-scale feature extraction
  • Focal loss for class imbalance in one-stage detectors

Standard benchmarks:

  • COCO val2017: ~37 mAP (Faster R-CNN R50), ~51 mAP (DINO Swin-L)
  • Pascal VOC: ~80 mAP50 (Faster R-CNN)
Related skills
Installs
5
GitHub Stars
12.0K
First Seen
Mar 24, 2026