Attentional Alignment Networks
Attentional Alignment Networks
复制标题
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Lei Yue;Xin Miao;Pengbo Wang;Baochang Zhang;Xiantong Zhen;Xianbin Cao
中科院分区：
文献类型：
--
作者：
Lei Yue;Xin Miao;Pengbo Wang;Baochang Zhang;Xiantong Zhen;Xianbin Cao
人脸对齐由于其广泛的应用，近年来在计算机视觉领域受到了广泛的关注。级联回归模型在过去的十年中占据了主导地位并取得了很大的进展，但它也存在固有的缺陷，例如，依赖初始化。在这项工作中，我们提出了注意力对齐网络（AAN），这是一种新型的端到端卷积架构，用于直接进行面部对齐，而不依赖于级联回归。AAN将注意力机制融入到卷积回归网络中，该网络为不同的卷积层生成多个注意力图，以不同的粒度捕获不同的特征;通过引入中间监督来创建自上而下的注意力图，AAN关注面部标志周围的区域，这使其能够建立与面部标志密切相关的更具信息性和区分性的表示。在四个常用的基准数据集上进行的大量实验表明，所提出的AAN在所有数据集上都具有很高的性能，大大超过了以前的方法，这表明了它对直接人脸对齐的有效性。
Face alignment has recently generated great popularity in computer vision due to its widespread applications. The cascaded regression model has dominated and achieved great progress in the last decade, which however suffers from innate shortcomings, e.g., reliance on initialization. In this work, we propose attentional alignment networks (AAN), a novel end-to-end convolutional architecture for direct face alignment without relying on cascaded regression. AAN incorporates the attention mechanism into a convolutional regression network, which generates multiple attention maps for different convolutional layers to capture distinctive features in different granularity; by introducing intermediate supervision to create top-down attention maps, AAN attends to regions around facial landmarks, which enables it to establish more informative and discriminative representation closely related to facial landmarks. Extensive experiments on four commonly-used benchmark datasets demonstrate that the proposed AAN consistently delivers high performance on all datasets, surpassing previous methods by large margins, which shows its great effectiveness for direct face alignment.