Lite-HRNet Plus: Fast and Accurate Facial Landmark Detection
This work addresses real-time facial landmark detection for applications like driver status tracking, but it is incremental as it builds on existing Lite-HRNet.
The paper tackled the problem of high computational cost in Lite-HRNet for facial landmark detection by proposing Lite-HRNet Plus, which improved accuracy and achieved state-of-the-art results with computational complexity around 10M FLOPs.
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.