In recent years, face recognition systems have achieved exceptional success due to promising advances in deep learning architectures. However, they still fail to achieve expected accuracy when matching profile images against a gallery of frontal images. Current approaches either perform pose normalization (i.e., frontalization) or disentangle pose information for face recognition. We instead propose a new approach to utilize pose as an auxiliary information via an attention mechanism. In this paper, we hypothesize that pose attended information using an attention mechanism can guide contextual and distinctive feature extraction from profile faces, which further benefits a better representation learning in an embedded domain. To achieve this, first, we design a unified coupled profile-to-frontal face recognition network. It learns the mapping from faces to a compact embedding subspace via a class-specific contrastive loss. Second, we develop a novel pose attention block (PAB) to specially guide the pose-agnostic feature extraction from profile faces. To be more specific, PAB is designed to explicitly help the network to focus on important features along both channel and spatial dimension while learning discriminative yet pose invariant features in an embedding subspace. To validate the effectiveness of our proposed method, we conduct experiments on both controlled and in the wild benchmarks including Multi-PIE, CFP, IJBC, and show superiority over the state of the arts.
翻译:近些年来,由于深层学习结构取得了令人瞩目的进步,面部识别系统取得了非凡的成功。然而,在将侧面图像与前方图像相匹配时,它们仍然未能达到预期的准确性。当前的做法要么表现为正常化(即正面化),要么表现为脸部识别信息分解。我们建议采用新的方法,通过关注机制将面部信息作为辅助信息。在本文中,我们使用关注机制呈现出所提供信息的虚伪性能,可以指导从侧面面部取出背景和特征特征,这进一步有利于在嵌入领域进行更好的代表性学习。为了实现这一点,我们首先设计了一个统一的组合剖面图和前面面图像识别网络。它通过一个特定类别对比性损失来从脸部到紧紧紧的嵌入子空间。第二,我们提出了一个新的面部位识别块(PABBBB),以特别指导从侧面面部特征提取工作。更具体地说,PAB旨在明确帮助网络关注从侧面面面部和空间两个方面的重要特征,同时学习在嵌入子空间中的差异性特征。为了在嵌入子空间空间,我们在嵌入子空间的子空间的子空间中,我们从面面部次空间空间空间中,我们从脸部、磁部、磁部和磁部控制艺术上进行测试的实验的实验,我们对磁部的实验,我们所拟的多控制性实验,以展示法的实验室法测试,以展示法测试法的法系的测试。