Revisting Quantization Error in Face Alignment

Abstract

Recently, heatmap regression models have become the mainstream in locating facial landmarks. To keep computation affordable and reduce memory usage, the whole procedure involves downsampling from the raw image to the output heatmap. However, how much impact will the quantization error introduced by downsampling bringƒ The problem is hardly systematically investigated among previous works. This work fills the blank and we are the first to quantitatively analyze the negative gain. The statistical results show the NME generated by quantization error is even larger than 1/3 of the SOTA item, which is a serious obstacle for making a new breakthrough in face alignment. To compensate for the impact of quantization effect, we propose a novel method, called Heatmap In Heatmap (HIH), which leverages two categories of heatmaps as label representation to encode the coordinate. And in HIH, the range of one heatmap represents a pixel of the other category of heatmap. Also, we even combine the face alignment with solutions of other fields to make a comparison. Extensive experiments on various benchmarks show the feasibility of HIH and superior performance than other solutions. Moreover, the mean error reaches to 4.18 on WFLW, which exceeds SOTA a lot.