Face Detection using Deep Learning: An Improved Faster RCNN Approach
This work addresses face detection for computer vision applications, but it is incremental as it builds on an existing framework.
The authors tackled face detection by improving the Faster RCNN framework with strategies like feature concatenation and multi-scale training, achieving state-of-the-art performance on the FDDB benchmark as the best model in ROC curves.
In this report, we present a new face detection scheme using deep learning and achieve the state-of-the-art detection performance on the well-known FDDB face detetion benchmark evaluation. In particular, we improve the state-of-the-art faster RCNN framework by combining a number of strategies, including feature concatenation, hard negative mining, multi-scale training, model pretraining, and proper calibration of key parameters. As a consequence, the proposed scheme obtained the state-of-the-art face detection performance, making it the best model in terms of ROC curves among all the published methods on the FDDB benchmark.