基于深度多任务学习的人脸标志点检测-相关数据集

基于深度多任务学习的人脸标志点检测-相关数据集

原文：

Facial Landmark Detection by Deep Multi-task Learning

Facial landmark detection of face alignment has long been impeded by the problems of occlusion and pose variation. Instead of treating the detection task as a single and independent problem, we investigate the possibility of improving detection robustness through multi-task learning. Specifically, we wish to optimize facial landmark detection together with heterogeneous but subtly correlated tasks, e.g., head pose estimation and facial attribute inference. This is non-trivial since different tasks have different learning difficulties and convergence rates. To address this problem, we formulate a novel tasks-constrained deep model, with task-wise early stopping to facilitate learning convergence. Extensive evaluations show that the proposed task-constrained learning (i) outperforms existing methods, especially in dealing with faces with severe occlusion and pose variation, and (ii) reduces model complexity drastically compared to the state-of-the-art method based on cascaded deep model.

We also extend this method to handle more landmark points (68 points instead of 5 major facial points) without either redesigning the deep model or involving significant increase in run time cost. This is made possible by transferring the learned 5-point model to the desired facial landmark configuration, through model fine-tuning with dense landmark annotations. Our new model achieves the state-of-the-art result on the 300-W benchmark dataset (mean error of 9.15% on the challenging IBUG subset).

译：

基于深度多任务学习的人脸标志点检测

长期以来，由于遮挡和姿态变化等问题，人脸定位中的标志点检测一直受到阻碍。我们研究了通过多任务学习提高检测鲁棒性的可能性，而不是将检测任务看作一个单独的独立问题。具体地说，我们希望将面部标志点检测与异构但微妙相关的任务（如头部姿势估计和面部属性推断）一起优化。这是非常重要的，因为不同的任务有不同的学习困难和收敛速度。为了解决这一问题，我们提出了一个新的任务约束深度模型，通过任务提前停止来促进学习收敛。大量的实验结果表明，本文提出的任务约束学习（i）优于现有的方法，尤其是在处理严重遮挡和姿态变化的人脸时；（ii）与基于级联深层模型的最新方法相比，显著降低了模型复杂度。

我们还扩展了这种方法来处理更多的地标点（68点而不是5个主要的面部点），而不需要重新设计深度模型，也不需要显著增加运行时间成本。通过使用密集的地标标注对模型进行微调，将所学的5点模型转换为所需的面部地标配置，从而实现这一点。我们的新模型在300-W基准数据集上达到了最先进的结果（在具有挑战性的IBUG子集上，平均误差为9.15%）。

大家可以到官网地址-数据集，我自己也在百度网盘分享了一份。

链接：​​获取数据集​​

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。