Knowledge Distillation Hashing for Occluded Face Retrieval

Deep hashing has proven to be efficient and effective for large-scale face retrieval. However, existing hashing methods are designed for normal face images only. They fail to consider the fact that face images may be occluded because of wearing masks, hats, glasses, etc. Retrieval performance of existing face retrieval methods is much worse when dealing with occluded face images. In this work, we propose the knowledge distillation hashing (KDH) to deal with occluded face images. The KDH is a two-stage learning approach with teacher-student model distillation. We first train a teacher hashing network using normal face images and then the knowledge from teacher model is used to guide the optimization of the student model using occluded face images as input only. With knowledge distillation, we build a connection between imperfect face information and the optimal hash codes. Experimental results show that the KDH yields significant improvements and better retrieval performance in comparison to existing state-of-the-art deep hashing retrieval methods under six different face occlusion situations.

I. Introduction

Mask wearing has become a common practice in our daily life because of the epidemic. In addition, wearing a hat or sunglasses are common in public area, which block most of the face information including eyes, nose, and mouth. However, current hashing-based retrieval methods are designed for normal face images only, which ignore occlusion situations. Therefore, they cannot perform well when challenged with imperfect face information such as large-pose variation, varying illumination, low resolution, different facial expressions, and occlusions [1], [2]. Therefore, how to learn an efficient hashing method for better retrieval performance under occlusion has become a challenging problem in current large-scale face retrieval research.