MogFace: Towards a Deeper Appreciation on Face Detection

Fei Wang

Abstract: Benefiting from the pioneering design of generic ob- ject detectors, significant achievements have been made in the field of face detection. Typically, the architectures of the backbone, feature pyramid layer, and detection head module within the face detector all assimilate the excel- lent experience from general object detectors. However, several effective methods, including label assignment and scale-level data augmentation strategy, fail to maintain con- sistent superiority when applying on the face detector di- rectly. Concretely, the former strategy involves a vast body of hyper-parameters and the latter one suffers from the challenge of scale distribution bias between different detec- tion tasks, which both limit their generalization abilities. Furthermore, in order to provide accurate face bounding boxes for facial down-stream tasks, the face detector im- peratively requires the elimination of false alarms. As a result, practical solutions on label assignment, scale-level data augmentation, and reducing false alarms are neces- sary for advancing face detectors. In this paper, we fo- cus on resolving three aforementioned challenges that ex- iting methods are difficult to finish off and present a novel face detector, termed MogFace. In our Mogface, three key components, Adaptive Online Incremental Anchor Mining Strategy, Selective Scale Enhancement Strategy and Hier- archical Context-Aware Module, are separately proposed to boost the performance of face detectors. Finally, to the best of our knowledge, our MogFace is the best face detector on the Wider Face leader-board, achieving all champions across different testing scenarios. The code is available at https://github.com/damo-cv/MogFace.