YOLOv3 Attention Face Detector with High Accuracy and Efficiency

Abstract

In recent years, face detection has attracted much attention and achieved great progress due to its extensively practical applications in the field of face based computer vision. However, the tradeoff between accuracy and efficiency of the face detectors still needs to be further studied. In this paper, using Darknet-53 as backbone, we propose an improved YOLOv3-attention model by introducing attention mechanism and data augmentation to obtain the robust face detector with high accuracy and efficiency. The attention mechanism is introduced to enhance much higher discrimination of the deep features, and the trick of data augmentation is used in the training procedure to achieve higher detection accuracy without significantly affecting the inference speed. The model has been trained and evaluated on the popular and challenging face detection benchmark, i.e., the WIDER FACE training and validation subsets, respectively, achieving AP of 0.942, 0.919 and 0.821 with the speed of 28FPS. This performance exceeds some existing SOTA algorithms, demonstrating acceptable accuracy and near real time detection for VGA resolution images, even in the complex scenarios. In addition, the proposed model shows good generation ability on another public dataset FDDB. The results indicate the proposed model is a promising face detector with high efficiency and accuracy in the wild.