1. 程式人生 > >[Paper note] Feature Pyramid Networks for Object Detection

[Paper note] Feature Pyramid Networks for Object Detection

Intuition

  • Multi-scale is important in traditional methods
  • Current detection system use single shot CNN to save time and memory (Faster R-CNN)
  • CNN is capable of representing higher-level semantics, but not all levels are semantically strong
  • Single Shot Detector (SSD) is one of the first attempts at using ConvNet’s pyramidal feature, but they add new layers after high up layer, which may lose information in high-resolution feature map
  • Main contribution: perform multi-scale in the network

Model

  • Feature Pyramid Network (FPN) building block
    • FPN block
    • The feature maps in the picture above are from the last layer of each stage in ConvNet
    • Nearest neighbor upsampling
    • Denotes final set of feature maps as {P2,P3,P4,P5}, corresponding to {C
      2
      ,C3,C4,C5}
  • FPN in Region Proposal Network (RPN)
    • Replacing single-scale feature map with FPN
    • Anchors with different aspect ratios: 1:2, 1:1, 2:1
    • 15 anchors over the pyramid
  • FPN in Fast R-CNN

Experiment

  • Evaluate on COCO minival set
  • Surpass 2016 COCO winner
  • Lateral and top-down connection is helpful