Learning to Align from Scratch
Learning to Align from Scratch
复制标题
DOI：
--
复制
发表时间：
2012-12
期刊：
影响因子：
--
通讯作者：
Gary B. Huang;Marwan A. Mattar;Honglak Lee;E. Learned-Miller
中科院分区：
文献类型：
--
作者：
Gary B. Huang;Marwan A. Mattar;Honglak Lee;E. Learned-Miller
图像的无监督联合对齐已被证明可以提高识别任务（如人脸验证）的性能。这种对齐减少了由于姿势等因素造成的不期望的变化，同时仅需要以对齐不良的示例的形式进行弱监督。然而，以前的工作对复杂的，真实世界的图像的无监督对齐需要仔细选择的特征表示的基础上手工制作的图像描述符，以实现适当的，平滑的优化景观。在本文中，我们提出了一种新的无监督联合对齐与无监督特征学习的组合。具体来说，我们将深度学习纳入到凝结对齐框架中。通过深度学习，我们获得了可以根据网络深度以不同分辨率表示图像的特征，并且这些特征被调整到正在对齐的特定数据的统计数据。此外，我们修改的学习算法的限制玻尔兹曼机，通过将一组稀疏惩罚，导致拓扑组织的学习过滤器和改善后续的对齐结果。我们将我们的方法应用于野生数据库（LFW）中的标记面孔。使用我们提出的无监督算法产生的对齐图像，我们实现了更高的精度在人脸验证相比，以前的工作在无监督和监督对齐。我们还与最佳商业方法的准确度相匹配。
Unsupervised joint alignment of images has been demonstrated to improve performance on recognition tasks such as face verification. Such alignment reduces undesired variability due to factors such as pose, while only requiring weak supervision in the form of poorly aligned examples. However, prior work on unsupervised alignment of complex, real-world images has required the careful selection of feature representation based on hand-crafted image descriptors, in order to achieve an appropriate, smooth optimization landscape. In this paper, we instead propose a novel combination of unsupervised joint alignment with unsupervised feature learning. Specifically, we incorporate deep learning into the congealing alignment framework. Through deep learning, we obtain features that can represent the image at differing resolutions based on network depth, and that are tuned to the statistics of the specific data being aligned. In addition, we modify the learning algorithm for the restricted Boltzmann machine by incorporating a group sparsity penalty, leading to a topographic organization of the learned filters and improving subsequent alignment results. We apply our method to the Labeled Faces in the Wild database (LFW). Using the aligned images produced by our proposed unsupervised algorithm, we achieve higher accuracy in face verification compared to prior work in both unsupervised and supervised alignment. We also match the accuracy for the best available commercial method.