FA-RPN: Floating Region Proposals for Face Detection

Abstract

We propose a novel approach for generating region proposals for performing face detection. Instead of classifying anchor boxes using features from a pixel in the convolutional feature map, we adopt a pooling-based approach for generating region proposals. However, pooling hundreds of thousands of anchors which are evaluated for generating proposals becomes a computational bottleneck during inference. To this end, an efficient anchor placement strategy for reducing the number of anchor-boxes is proposed. We then show that proposals generated by our network (Floating Anchor Region Proposal Network, FA-RPN) are better than RPN for generating region proposals for face detection. We discuss several beneficial features of FA-RPN proposals (which can be enabled without re-training) like iterative refinement, placement of fractional anchors and changing size/shape of anchors. Our face detector based on FA-RPN obtains 89.4 mAP with a ResNet-50 backbone on the WIDER dataset.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 16, 2019
Accession Number
AD1155446

Entities

People

  • Bharat Singh
  • Larry S. Davis
  • Mahyar Najibi

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Aspect Ratio
  • Computer Vision
  • Computers
  • Convolutional Neural Networks
  • Deep Learning
  • Detection
  • Detectors
  • High Resolution
  • Image Recognition
  • Information Processing
  • Information Science
  • Information Systems
  • Neural Networks
  • Pattern Recognition
  • Recognition

Fields of Study

  • Computer science

Readers

  • Chemistry (specifically Chemical Fluorescence)
  • Geotechnical Engineering.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks