Understanding Feature Pyramid Networks for object detection (FPN)

Source

Data Flow

FPN (Source)
Feature extraction in FPN (Modified from source)
Modified from source
Reconstruct spatial resolution in the top-down pathway. (Modified from source)
Add skip connections (Source)

Bottom-up pathway

Top-down pathway

FPN with RPN (Region Proposal Network)

Source

FPN with Fast R-CNN or Faster R-CNN

Segmentation

Source

Results

Source
Source
Source

Lessons learned

  • Adding more anchors on a single high-resolution feature map layer is not sufficient to improve accuracy.
  • Top-down pathway restores resolution with rich semantic information.
  • But we need lateral connections to add more precise object spatial information back.
  • Top-down pathway plus lateral connections improve accuracy by 8 points on COCO dataset. For small objects, it improves 12.9 points.

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store