CenterFace: Joint Face Detection and Alignment Using Face as Point
This addresses efficient face detection and alignment for edge devices with limited resources, representing a strong specific gain but is incremental as it builds on existing anchor-free approaches.
The paper tackles face detection and alignment in unconstrained environments by proposing CenterFace, a one-stage anchor-free method that achieves real-time speeds (e.g., 200 FPS on NVIDIA 2080TI) and high accuracy, with results like 0.935 on WIDER FACE Val-Easy.
Face detection and alignment in unconstrained environment is always deployed on edge devices which have limited memory storage and low computing power. This paper proposes a one-stage method named CenterFace to simultaneously predict facial box and landmark location with real-time speed and high accuracy. The proposed method also belongs to the anchor free category. This is achieved by: (a) learning face existing possibility by the semantic maps, (b) learning bounding box, offsets and five landmarks for each position that potentially contains a face. Specifically, the method can run in real-time on a single CPU core and 200 FPS using NVIDIA 2080TI for VGA-resolution images, and can simultaneously achieve superior accuracy (WIDER FACE Val/Test-Easy: 0.935/0.932, Medium: 0.924/0.921, Hard: 0.875/0.873 and FDDB discontinuous: 0.980, continuous: 0.732). A demo of CenterFace can be available at https://github.com/Star-Clouds/CenterFace.