论文标题
小组面：学习潜在组并构建基于组的表征以进行面部识别
GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition
论文作者
论文摘要
在面部识别领域，一个模型学会了区分数百万的面部图像，这些图像具有较少的尺寸嵌入功能，并且这样的庞大信息可能无法在传统模型中与单个分支进行正确编码。我们提出了一种称为GroupFace的新型面部识别特殊体系结构，该体系结构同时利用多个组感知表示，以提高嵌入功能的质量。提出的方法提供了自分配的标签，这些标签平衡了每个组属于每个组的样本的数量，而无需其他人类注释，并了解了可以缩小目标身份搜索空间的群体感知表示。我们通过显示广泛的消融研究和可视化来证明所提出的方法的有效性。所提出的方法的所有组成部分都可以以端到端的方式进行训练，计算复杂性的边缘增加。最后，所提出的方法在以下公共数据集上的1：1面验证和1：n面对识别任务方面取得了显着改善：LFW，YTF，CALFW，CPLFW，CFP，CFP，CFP，AGEDB-30，MEGAFACE，MEGAFACE，IJB-B和IJB-C。
In the field of face recognition, a model learns to distinguish millions of face images with fewer dimensional embedding features, and such vast information may not be properly encoded in the conventional model with a single branch. We propose a novel face-recognition-specialized architecture called GroupFace that utilizes multiple group-aware representations, simultaneously, to improve the quality of the embedding feature. The proposed method provides self-distributed labels that balance the number of samples belonging to each group without additional human annotations, and learns the group-aware representations that can narrow down the search space of the target identity. We prove the effectiveness of the proposed method by showing extensive ablation studies and visualizations. All the components of the proposed method can be trained in an end-to-end manner with a marginal increase of computational complexity. Finally, the proposed method achieves the state-of-the-art results with significant improvements in 1:1 face verification and 1:N face identification tasks on the following public datasets: LFW, YTF, CALFW, CPLFW, CFP, AgeDB-30, MegaFace, IJB-B and IJB-C.
