What is a Feature Pyramid Network (FPN)?
hardAnswer
- A top-down architecture that fuses features from multiple backbone stages (different resolutions and semantic levels) into a pyramid where each level is high-resolution and semantically rich.
- Take the deep low-resolution feature, upsample, add to the mid-resolution feature, and so on.
- Powers most modern detectors (Faster R-CNN + FPN, RetinaNet, YOLOv3+, Mask R-CNN) by giving each RoI head or anchor set the right-scale features.
Check yourself — multiple choice
- Only uses one resolution
- Top-down pyramid fusing multi-scale backbone features → each scale semantically rich, used in most modern detectors
- Same as U-Net decoder
- Removes convolutions
FPN: multi-scale top-down fusion → rich features at every resolution.
#detection#segmentation#computer-vision#architectures
Practise Deep Learning
214 interview questions in this topic.