人脸检测最新文章解读

1. 京东AI实验室2019CVPR的文章：

Improved Selective Refinement Network for Face Detection

是我目前看到CVPR2019中检测到人脸最多的方法。

这篇文章是在Selective Refinement Network(SRN)基础上的改进，主要使用的策略有： new data augmentation strategy（新的数据增强策略）, improved backbone network（改进的骨架）, MS COCO pretraining（在MS COCO上预训练）, decoupled classification module（解耦分类模块）, segmentation branch （分割分支）and Squeeze-and-Excitation block.

2.中兴的2019CVPR:

Robust and High Performance Face Detector

文章的贡献：

In specific, we exploit more powerful backbone network like DenseNet-121 [2], revisit the data augmentation based on data-anchor-sampling proposed in [3], and use the max-in-out label and anchor matching strategy in [4]. In addition, we also introduce the attention mechanism [5, 6] to provide additional supervision. 

这篇文章提出新的结构：VIM-FD