Skip to content
FunCoding

cv-detection

Best practices for object detection tasks. Use when working on COCO, VOC, or detection architectures like YOLO and DETR.

Star
14,635
Category
Coding & debugging
License
MIT
Last commit
Aug 19, 2026

researchclaw/skills/builtin/domain/cv-detection/SKILL.md

View on GitHub

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)

Similar Skills

receiving-code-review

OBobra/superpowers298k2,631 new stars in the last 7 days

requesting-code-review

OBobra/superpowers298k2,631 new stars in the last 7 days

systematic-debugging

OBobra/superpowers298k2,631 new stars in the last 7 days

code-review

MAmattpocock/skills288k10,178 new stars in the last 7 days

codebase-design

MAmattpocock/skills288k10,178 new stars in the last 7 days

scaffold-exercises

MAmattpocock/skills288k10,178 new stars in the last 7 days