Detect face in the wild using CNN cascade with feature aggregation at multi-resolution

Face detection in the wild is a challenging vision problem due to large variations and unpredictable ambiguities commonly existed in real world images. Whilst using hand-crafted features is generally problematic, introducing powerful but complex models is often computationally inefficient. Feature aggregation and multi-resolution are two efficient strategies for traditional visual recognition methods. In this paper, we show that such strategies can be integrated into Convolutional Neural Network (CNN) architecture via average pooling and channel-wise feature concatenation. Shallow networks with feature aggregation at multi-resolution enables the traditional cascade framework to tackle the challenging detection problems efficiently. The proposed method is tested on a public benchmark with across dataset evaluation. Both quantitative and qualitative results show promising performance improvements on detecting faces in unconstrained environment.