// ◉ Multimodal & Vision
YOLO (Real-Time Object Detection)
Predicts all boxes and classes in a single forward pass – very fast.
YOLO 实时目标检测 2015 Foundational core
IN PLAIN WORDS
Split the image into a grid and have each cell directly regress boxes and class probabilities – no separate proposal stage. Early versions trailed two-stage detectors in accuracy but ran an order of magnitude faster, enough for real-time video. A decade of YOLO successors made it the most widely used detector family in industry.
Used in: Real-time detection in video analytics, drones and inspection (Ultralytics YOLO family)
01Original paper
You Only Look Once: Unified, Real-Time Object Detection
Joseph Redmon, Santosh Divvala, Ross Girshick, et al. · 2015
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Learn first
Then you can learn
- Nothing in the atlas builds on it yet
Related:Faster R-CNN (Object Detection)DETR (Detection Transformer)
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
Official docs
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-22.
- JSON: /api/learn/algorithms.json (id:
yolo)