RetinaFaceMask: A Single Stage Face Mask Detector for Assisting Control of the COVID-19 Pandemic

Coronavirus 2019 has made a significant impact on the world. One effective strategy to prevent infection for people is to wear masks in public places. Certain public service providers require clients to use their services only if they properly wear masks. There are, however, only a few research studies on automatic face mask detection. In this paper, we proposed RetinaFaceMask, the first high-performance single stage face mask detector. First, to solve the issue that existing studies did not distinguish between correct and incorrect mask wearing states, we established a new dataset containing these annotations. Second, we proposed a context attention module to focus on learning discriminated features associated with face mask wearing states. Third, we transferred the knowledge from the face detection task, inspired by how humans improve their ability via learning from similar tasks. Ablation studies showed the advantages of the proposed model. Experimental findings on both the public and new datasets demonstrated the stateof-the-art performance of our model.

Automated summary

This paper introduces RetinaFaceMask, a high-performance single-stage face mask detector, with a new dataset containing correct and incorrect mask-wearing states annotations, a context attention module, and knowledge transfer strategy from face detection task. Experimental results show the superiority of the proposed model on both existing and new datasets.