Heatmap regression with a deep network has become one of the mainstream approaches to localize facial landmarks. 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 penalizes loss more on foreground pixels while less 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 at https://github.com/protossw512/AdaptiveWingLoss.
翻译:深网络的热映射回归已成为将面部标志定位为本地化的主流方法之一。 然而, 热映射回归的损失功能很少研究。 在本文中, 我们分析在对齐问题中热映射回归的理想损失函数属性。 然后我们提出一个新的损失函数, 名为适应性翼损失, 能够使其形状适应不同类型的地面真相热映射像素。 这种适应性会惩罚更深的地表像素损失, 而背景像素则较少。 为了解决地表和背景像素之间的不平衡, 我们还提议 Weightmap 损失映射图, 给地表和困难背景像素分配高的重量, 以帮助培训过程更多关注对地标化至关重要的像素。 为了进一步提高面对地标的精确度, 我们引入边界预测和与边界坐标的coord Convord。 对不同的基准, 包括COFW、 300W和WLFLW, 进行广泛的实验, 显示我们的方法在各种评估指标上大大超越了状态。 此外, 调式的翼映射/ 将帮助其他可用的 MA/ codevelys 。