IEEE Trans Image Process. 2017 Apr;26(4):1666-1678. doi: 10.1109/TIP.2017.2657118. Epub 2017 Jan 23.
Face alignment aims at localizing multiple facial landmarks for a given facial image, which usually suffers from large variances of diverse facial expressions, aspect ratios and partial occlusions, especially when face images were captured in wild conditions. Conventional face alignment methods extract local features and then directly concatenate these features for global shape regression. Unlike these methods which cannot explicitly model the correlation of neighbouring landmarks and motivated by the fact that individual landmarks are usually correlated, we propose a deep sharable and structural detectors (DSSD) method for face alignment. To achieve this, we firstly develop a structural feature learning method to explicitly exploit the correlation of neighbouring landmarks, which learns to cover semantic information to disambiguate the neighbouring landmarks. Moreover, our model selectively learns a subset of sharable latent tasks across neighbouring landmarks under the paradigm of the multi-task learning framework, so that the redundancy information of the overlapped patches can be efficiently removed. To better improve the performance, we extend our DSSD to a recurrent DSSD (R-DSSD) architecture by integrating with the complementary information from multi-scale perspectives. Experimental results on the widely used benchmark datasets show that our methods achieve very competitive performance compared to the state-of-the-arts.
人脸对齐旨在定位给定人脸图像中的多个面部地标，这通常会受到不同表情、纵横比和部分遮挡的巨大差异的影响，尤其是当人脸图像在野外环境中捕获时。传统的人脸对齐方法提取局部特征，然后直接将这些特征连接起来进行全局形状回归。与这些方法不同，我们无法显式地对相邻地标之间的相关性进行建模，并且受到这样一个事实的启发，即个别地标通常是相关的，因此我们提出了一种用于人脸对齐的深度可共享和结构探测器 (DSSD) 方法。为了实现这一目标，我们首先开发了一种结构特征学习方法来显式地利用相邻地标之间的相关性，该方法学习覆盖语义信息来区分相邻地标。此外，我们的模型在多任务学习框架的范例下，选择性地学习跨越相邻地标共享的潜在任务的子集，以便有效地去除重叠补丁的冗余信息。为了更好地提高性能，我们通过集成多尺度视角的互补信息，将我们的 DSSD 扩展到一个递归 DSSD (R-DSSD) 架构。在广泛使用的基准数据集上的实验结果表明，与最先进的方法相比，我们的方法具有非常有竞争力的性能。
