Face R-CNN
This work improves face detection accuracy for applications like security and social media, but it is incremental as it builds on an existing object detection method.
The authors tackled face detection by adapting Faster R-CNN with new techniques like multi-task loss and online hard example mining, achieving state-of-the-art results on benchmarks such as FDDB and WIDER FACE.
Faster R-CNN is one of the most representative and successful methods for object detection, and has been becoming increasingly popular in various objection detection applications. In this report, we propose a robust deep face detection approach based on Faster R-CNN. In our approach, we exploit several new techniques including new multi-task loss function design, online hard example mining, and multi-scale training strategy to improve Faster R-CNN in multiple aspects. The proposed approach is well suited for face detection, so we call it Face R-CNN. Extensive experiments are conducted on two most popular and challenging face detection benchmarks, FDDB and WIDER FACE, to demonstrate the superiority of the proposed approach over state-of-the-arts.