Wide Aspect Ratio Matching for Robust Face Detection

TL;DR

This paper introduces Wide Aspect Ratio Matching (WARM) and Receptive Field Diversity (RFD) modules to improve face detection, especially for extreme aspect ratios, achieving better results on challenging benchmarks.

Contribution

The paper proposes a novel WARM strategy and RFD module to enhance anchor matching and feature diversity for extreme aspect ratio faces in detection.

Findings

Improved detection of extreme aspect ratio faces.

Enhanced performance on WIDER FACE and FDDB datasets.

Effective anchor matching strategy for diverse face shapes.

Abstract

Recently, anchor-based methods have achieved great progress in face detection. Once anchor design and anchor matching strategy determined, plenty of positive anchors will be sampled. However, faces with extreme aspect ratio always fail to be sampled according to standard anchor matching strategy. In fact, the max IoUs between anchors and extreme aspect ratio faces are still lower than fixed sampling threshold. In this paper, we firstly explore the factors that affect the max IoU of each face in theory. Then, anchor matching simulation is performed to evaluate the sampling range of face aspect ratio. Besides, we propose a Wide Aspect Ratio Matching (WARM) strategy to collect more representative positive anchors from ground-truth faces across a wide range of aspect ratio. Finally, we present a novel feature enhancement module, named Receptive Field Diversity (RFD) module, to provide diverse receptive field corresponding to different aspect ratios. Extensive experiments show that our method can help detectors better capture extreme aspect ratio faces and achieve promising detection performance on challenging face detection benchmarks, including WIDER FACE and FDDB datasets.