R-CNN Family MCQ 15 Questions
Time: ~25 mins Advanced · Popular

R-CNN Family MCQ

From warped region CNNs to shared-feature ROI pooling and learned proposals—why two-stage was accurate before one-stage speed wars.

Easy: 5 Q Medium: 6 Q Hard: 4 Q
Regions

Warp

ROI pool

Fixed grid

Fast

Shared conv

RPN

Anchors

R-CNN family

R-CNN ran a CNN on thousands of warped proposal windows—slow. Fast R-CNN runs CNN once, pools features per ROI. Faster R-CNN learns proposals with a Region Proposal Network on feature maps.

ROI Pooling

Quantizes each ROI onto the feature grid into a fixed H×W—enables batching FC heads (RoIAlign refines alignment).

Evolution

R-CNN

Proposals + per-ROI forward—redundant compute.

Fast

Shared backbone; ROI pooling gathers features per proposal.

Faster

RPN classifies objectness + regresses boxes from anchors on the feature map.

Tradeoff

Two-stage: often higher mAP; heavier latency than one-stage YOLO-style.

Faster R-CNN

Backbone → FPN (optional) → RPN → RoI head (cls + reg [+ mask])

Pro tip: Anchor scales/aspect ratios should match dataset object statistics.