A Rotation-Invariance Face Detector Based on RetinaNet

The use of deep convolutional neural networks has greatly improved the performance of general face detection. For detecting rotated faces, the mainstream approach is to use multi-stage detectors to gradually adjust the rotated face to a vertical orientation for detection, which increases the complexity of training as multiple networks are involved. In this study, we propose a new method for rotation-invariant face detection, which abandons the previously used cascaded architecture with multiple stages and instead uses a single-stage detector to achieve end-to-end detection of face classification, face box regression, and facial landmark regression. Extensive experiments on FDDB in multiple orientations have shown the effectiveness of our method. The results demonstrate that our method achieves good detection performance and the detection accuracy of our method even exceeds that of other rotated face detectors on the front-facing FDDB dataset.