Face Detection Using Improved Faster RCNN
This work addresses face detection for computer vision applications, but it is incremental as it builds on the existing Faster RCNN framework with optimizations.
The authors tackled face detection by proposing FDNet1.0, an improved Faster RCNN method that achieved first place in two tasks and second place in one task on the WIDER FACE validation dataset across easy, medium, and hard sets.
Faster RCNN has achieved great success for generic object detection including PASCAL object detection and MS COCO object detection. In this report, we propose a detailed designed Faster RCNN method named FDNet1.0 for face detection. Several techniques were employed including multi-scale training, multi-scale testing, light-designed RCNN, some tricks for inference and a vote-based ensemble method. Our method achieves two 1th places and one 2nd place in three tasks over WIDER FACE validation dataset (easy set, medium set, hard set).