How does a two-stage detector (Faster R-CNN) work?
hardAnswer
- Stage 1: a Region Proposal Network (RPN) sliding a small conv over the backbone's feature map generates ~1k-2k class-agnostic object proposals (anchor boxes + objectness).
- Stage 2: RoIAlign extracts fixed-size features from each proposal, then a small head classifies the region and refines the box.
- Slower but more accurate than one-stage detectors — still SOTA on many benchmarks.
- Feature Pyramid Networks (FPN) extend it to multi-scale features.
Check yourself — multiple choice
- Single classification head
- Stage 1: RPN generates proposals; Stage 2: RoIAlign + head classifies + refines each region — slower but accurate
- Same as YOLO
- No proposals used
Two-stage detection: RPN proposals → RoIAlign → per-region head.
#detection#computer-vision#architectures
Practise Deep Learning
214 interview questions in this topic.