Faceness-Net: Face Detection through Deep Facial Part Responses
This addresses face detection for computer vision applications, particularly under occlusion and pose variations, but it appears incremental as it builds on existing CNN and attribute-based methods.
The paper tackled face detection by training a CNN to classify facial attributes, which led to the emergence of part detectors without explicit supervision, enabling detection through scoring part responses based on spatial structure and arrangement. It achieved promising performance on benchmarks like FDDB, PASCAL Faces, AFW, and WIDER FACE, though no specific numbers are provided.
We propose a deep convolutional neural network (CNN) for face detection leveraging on facial attributes based supervision. We observe a phenomenon that part detectors emerge within CNN trained to classify attributes from uncropped face images, without any explicit part supervision. The observation motivates a new method for finding faces through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is data-driven, and carefully formulated considering challenging cases where faces are only partially visible. This consideration allows our network to detect faces under severe occlusion and unconstrained pose variations. Our method achieves promising performance on popular benchmarks including FDDB, PASCAL Faces, AFW, and WIDER FACE.