论文标题
通过级联变压器进行准确的面部标志性检测
Towards Accurate Facial Landmark Detection via Cascaded Transformers
论文作者
论文摘要
准确的面部地标是许多与人面孔有关的任务的重要先决条件。在本文中，提出了基于级联变压器的精确面部标志性检测器。我们将面部标志性检测作为坐标回归任务，以便可以端对端训练该模型。通过在变压器中进行自我注意，我们的模型可以固有地利用地标之间的结构化关系，这将使在挑战性的条件（例如大姿势和遮挡）下受益。在级联精致过程中，我们的模型能够根据可变形的注意机制提取目标地标周围的最相关图像特征，以进行坐标预测，从而带来更准确的对齐。此外，我们提出了一个新颖的解码器，可以同时完善图像特征和地标位置。随着参数增加，检测性能进一步提高。我们的模型在几个标准的面部标准检测基准上实现了新的最新性能，并在跨数据库评估中显示出良好的概括能力。
Accurate facial landmarks are essential prerequisites for many tasks related to human faces. In this paper, an accurate facial landmark detector is proposed based on cascaded transformers. We formulate facial landmark detection as a coordinate regression task such that the model can be trained end-to-end. With self-attention in transformers, our model can inherently exploit the structured relationships between landmarks, which would benefit landmark detection under challenging conditions such as large pose and occlusion. During cascaded refinement, our model is able to extract the most relevant image features around the target landmark for coordinate prediction, based on deformable attention mechanism, thus bringing more accurate alignment. In addition, we propose a novel decoder that refines image features and landmark positions simultaneously. With few parameter increasing, the detection performance improves further. Our model achieves new state-of-the-art performance on several standard facial landmark detection benchmarks, and shows good generalization ability in cross-dataset evaluation.
