论文标题
通过解开外观和几何形状来提高深度识别
Boosting Deep Face Recognition via Disentangling Appearance and Geometry
论文作者
论文摘要
在本文中，我们提出了一个框架，用于删除面部识别任务中的外观和几何表示。为了为此目标提供监督，我们通过合并空间转换来产生几何相同的面孔。我们证明，所提出的方法通过两种方式协助训练过程来增强深度识别模型的性能。首先，它强制执行早期和中间卷积层，以学习满足分离嵌入性能的更多代表性特征。其次，它通过几何改变面部改变面部来增强设定的训练。通过广泛的实验，我们证明将提出的方法整合到最先进的面部识别方法中可以有效地提高其在挑战性数据集上的性能，例如LFW，YTF和Megaface。通过消融研究和知识转移任务，严格分析了该方法的理论和实际方面。此外，我们表明，所提出的方法倾斜的知识可以偏爱其他与面部相关的任务，例如属性预测。
In this paper, we propose a framework for disentangling the appearance and geometry representations in the face recognition task. To provide supervision for this aim, we generate geometrically identical faces by incorporating spatial transformations. We demonstrate that the proposed approach enhances the performance of deep face recognition models by assisting the training process in two ways. First, it enforces the early and intermediate convolutional layers to learn more representative features that satisfy the properties of disentangled embeddings. Second, it augments the training set by altering faces geometrically. Through extensive experiments, we demonstrate that integrating the proposed approach into state-of-the-art face recognition methods effectively improves their performance on challenging datasets, such as LFW, YTF, and MegaFace. Both theoretical and practical aspects of the method are analyzed rigorously by concerning ablation studies and knowledge transfer tasks. Furthermore, we show that the knowledge leaned by the proposed method can favor other face-related tasks, such as attribute prediction.
