IEEE Trans Pattern Anal Mach Intell. 2018 Aug;40(8):1845-1859. doi: 10.1109/TPAMI.2017.2738644. Epub 2017 Aug 11.
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.
我们提出了一种基于面部属性监督的深度卷积神经网络（CNN）进行人脸检测。我们观察到一个现象，即在没有任何明确的部分监督的情况下，从未经裁剪的人脸图像中训练 CNN 来分类属性时，会出现部分检测器。这一观察结果促使我们提出了一种通过评分面部部分的空间结构和排列来寻找面部的新方法。评分机制是数据驱动的，并在考虑到人脸仅部分可见的具有挑战性的情况下进行了仔细的制定。这种考虑使我们的网络能够在严重遮挡和不受约束的姿势变化下检测人脸。我们的方法在包括 FDDB、PASCAL Faces、AFW 和 WIDER FACE 在内的流行基准测试中取得了有希望的性能。
