Abstract
Facial landmark detection is an essential technology for driver status tracking and has been in demand for real-time estimations. As a landmark coordinate prediction, heatmap-based methods are known to achieve a high accuracy, and Lite-HRNet can achieve a fast estimation. However, with Lite-HRNet, the problem of a heavy computational cost of the fusion block, which connects feature maps with different resolutions, has yet to be solved. In addition, the strong output module used in HRNetV2 is not applied to Lite-HRNet. Given these problems, we propose a novel architecture called Lite-HRNet Plus. Lite-HRNet Plus achieves two improvements: a novel fusion block based on a channel attention and a novel output module with less computational intensity using multi-resolution feature maps. Through experiments conducted on two facial landmark datasets, we confirmed that Lite-HRNet Plus further improved the accuracy in comparison with conventional methods, and achieved a state-of-the-art accuracy with a computational complexity with the range of 10M FLOPs.
Abstract (translated)
面部 landmark 检测是司机状态追踪的必备技术,并一直受到实时估计的需求。作为一种 landmark 坐标预测方法,已知通过热图方法可以实现高精度,而 Lite-HRNet 可以实现快速的估计。然而,与 Lite-HRNet 一起使用, Fusion block 的计算成本问题仍然存在,该 block 连接了不同分辨率的特征图。此外,HRNetV2 中使用的强大输出模块不适用于 Lite-HRNet。鉴于这些问题,我们提出了一种新架构称为 Lite-HRNet Plus。 Lite-HRNet Plus 实现了两个改进:基于通道关注的新 fusion block 和使用多分辨率特征图以减少计算强度的新输出模块。通过在两个面部 landmark 数据集上进行实验,我们确认 Lite-HRNet Plus 相对于传统方法进一步提高了精度,并在计算复杂性范围为 10 百万 FLOPs 的情况下实现了先进的精度。
URL
https://arxiv.org/abs/2308.12133