Heatmap regression has became one of the mainstream approaches to localize facial landmarks. As Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) are becoming popular in solving computer vision tasks, extensive research has been done on these architectures. However, the loss function for heatmap regression is rarely studied. In this paper, we analyze the ideal loss function properties for heatmap regression in face alignment problems. Then we propose a novel loss function, named Adaptive Wing loss, that is able to adapt its shape to different types of ground truth heatmap pixels. This adaptability decreases the loss to zero on foreground pixels while leaving some loss on background pixels. To address the imbalance between foreground and background pixels, we also propose Weighted Loss Map, which assigns high weights on foreground and difficult background pixels to help training process focus more on pixels that are crucial to landmark localization. To further improve face alignment accuracy, we introduce boundary prediction and CoordConv with boundary coordinates. Extensive experiments on different benchmarks, including COFW, 300W and WFLW, show our approach outperforms the state-of-the-art by a significant margin on various evaluation metrics. Besides, the Adaptive Wing loss also helps other heatmap regression tasks. Code will be made publicly available.
翻译:热映射回归已成为将面部标志定位的主流方法之一。 随着革命神经网络(CNN)和经常神经网络(RNN)在解决计算机视觉任务时越来越受欢迎, 对这些结构进行了广泛的研究。 然而, 热映射回归的损失函数很少研究。 在本文中, 我们分析热映回归在面临校正问题时的理想损失函数属性。 然后我们提出一个新的损失函数, 名为适应性翅膀损失, 能够将其形状调整为不同类型的地面真象像素。 由于这种适应性将前地像素损失减少到零, 而在背景像素上留下一些损失。 为了解决前地和背景像素之间的不平衡, 我们还提出了高重力和困难背景像素, 以帮助培训进程更多地关注对地标定位至关重要的像素。 为了进一步提高面校正准确性, 我们引入边界预测和 Coord Convil 和边界坐标。 在不同的基准上进行广泛的实验, 包括COFW, 300W 和WFLW, 以显著的平面回归法, 展示了我们的公共标准 。