Triple Loss for Hard Face Detection

Publication date: Available online 21 February 2020Source: NeurocomputingAuthor(s): Zhenyu Fang, Jinchang Ren, Stephen Marshall, Huimin Zhao, Zheng Wang, Kaizhu Huang, Bing XiaoAbstractAlthough face detection has been well addressed in the last decades, despite the achievements in recent years, effective detection of small, blurred and partially occluded faces in the wild remains a challenging task. Meanwhile, the trade-off between computational cost and accuracy is also an open research problem in this context. To tackle these challenges, in this paper, a novel context enhanced approach is proposed with structural optimization and loss function optimization. For loss function optimization, we introduce a hierarchical loss, referring to triple loss in this paper, to optimize the feature pyramid network (FPN) [1] based face detector. Additional layers are only applied during the training process. As a result, the computational cost is the same as FPN during inference. For structural optimization, we propose a context sensitive structure to increase the capacity of the prediction network to improve the accuracy of the output. In details, a three-branch inception subnet [2] based feature fusion module is employed to refine the original FPN without increasing the computational cost significantly, further improving low-level semantic information, which is originally extracted from a single convolutional layer in the backward pathway of FPN. The proposed approach is evaluated on tw...

Source: Neurocomputing - February 21, 2020 Category: Neuroscience Source Type: research