IEEE Trans Pattern Anal Mach Intell. 2020 Aug;42(8):2038-2050. doi: 10.1109/TPAMI.2019.2907634. Epub 2019 Mar 26.
In this paper, we propose to couple stacked U-Nets for efficient visual landmark localization. The key idea is to globally reuse features of the same semantic meanings across the stacked U-Nets. The feature reuse makes each U-Net light-weighted. Specially, we propose an order- K coupling design to trim off long-distance shortcuts, together with an iterative refinement and memory sharing mechanism. To further improve the efficiency, we quantize the parameters, intermediate features, and gradients of the coupled U-Nets to low bit-width numbers. We validate our approach in two tasks: human pose estimation and facial landmark localization. The results show that our approach achieves state-of-the-art localization accuracy but using ∼ 70% fewer parameters, ∼ 30% less inference time, ∼ 98% less model size, and saving ∼ 75% training memory compared with benchmark localizers.
在本文中，我们提出了一种堆叠 U-Net 来进行高效的视觉地标定位。其关键思想是在堆叠的 U-Net 之间全局重复使用相同语义的特征。这种特征复用使每个 U-Net 轻量化。具体来说，我们提出了一种 K 阶耦合设计来修剪掉长距离的捷径，同时结合了迭代细化和内存共享机制。为了进一步提高效率，我们对耦合 U-Net 的参数、中间特征和梯度进行量化，以达到低比特宽度的数字。我们在两个任务中验证了我们的方法：人体姿态估计和面部地标定位。结果表明，与基准定位器相比，我们的方法在实现最先进的定位精度的同时，使用的参数减少了约 70%，推理时间减少了约 30%，模型大小减少了约 98%，训练内存节省了约 75%。
