PyramidBox++: High Performance Detector for Finding Tiny Face
This work addresses the challenge of detecting small faces in images, which is important for applications like surveillance and photo tagging, but it is incremental as it builds upon an existing method.
The paper tackles the problem of detecting tiny faces by improving the PyramidBox detector with Balanced-data-anchor-sampling, Dual-PyramidAnchors, and Dense Context Module, achieving state-of-the-art performance on the hard set of the WIDER FACE benchmark.
With the rapid development of deep convolutional neural network, face detection has made great progress in recent years. WIDER FACE dataset, as a main benchmark, contributes greatly to this area. A large amount of methods have been put forward where PyramidBox designs an effective data augmentation strategy (Data-anchor-sampling) and context-based module for face detector. In this report, we improve each part to further boost the performance, including Balanced-data-anchor-sampling, Dual-PyramidAnchors and Dense Context Module. Specifically, Balanced-data-anchor-sampling obtains more uniform sampling of faces with different sizes. Dual-PyramidAnchors facilitate feature learning by introducing progressive anchor loss. Dense Context Module with dense connection not only enlarges receptive filed, but also passes information efficiently. Integrating these techniques, PyramidBox++ is constructed and achieves state-of-the-art performance in hard set.