// ◉ Multimodal & Vision
Faster R-CNN (Object Detection)
Two-stage detector: a network proposes boxes, then classifies and refines them.
Faster R-CNN 目标检测 aka R-CNN / Mask R-CNN / RPN 2015 Intermediate core
IN PLAIN WORDS
Stage one, a Region Proposal Network, slides over the feature map and proposes boxes likely to contain objects; stage two classifies each box and refines it. Handing proposals to a neural network made detection much faster and more accurate; it is the canonical two-stage detector, and Mask R-CNN builds on it for instance segmentation.
Used in: A standard detector in Detectron2 and torchvision; industrial inspection, driving perception
TIMELINE · prerequisites → this → what builds on it
01Original paper
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Shaoqing Ren, Kaiming He, Ross Girshick, et al. · 2015
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Then you can learn
Related:YOLO (Real-Time Object Detection)Segment Anything (SAM)
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-22.
- JSON: /api/learn/algorithms.json (id:
faster-rcnn)