In this paper, we propose a new multi-scale face detector having an extremely
tiny number of parameters (EXTD),less than 0.1 million, as well as achieving
comparable performance to deep heavy detectors. While existing multi-scale face
detectors extract feature maps with different scales from a single backbone
network, our method generates the feature maps by iteratively reusing a shared
lightweight and shallow backbone network. This iterative sharing of the
backbone network significantly reduces the number of parameters, and also
provides the abstract image semantics captured from the higher stage of the
network layers to the lower-level feature map. The proposed idea is employed by
various model architectures and evaluated by extensive experiments. From the
experiments from WIDER FACE dataset, we show that the proposed face detector
can handle faces with various scale and conditions, and achieved comparable
performance to the more massive face detectors that few hundreds and tens times
heavier in model size and floating point operations.

本文提出了一种新的多尺度人脸检测器 EXTD，参数数量少于 0.1 万，实现了与深度重型检测器相当的性能，采用了轻量级和浅层的骨干网络的共享，从而显著减少了参数数量，并提供了从网络层的高阶抽象图像语义到低级特征图的功能。