arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.01559cs.CV
收藏

人脸识别中的类间离散对齐

Inter-class Discrepancy Alignment for Face Recognition

SenseTime Group Limited(商汤集团有限公司)

Jiaheng Liu, Yudong Wu, Yichao Wu, Zhenmao Li, Chen Ken, Ding Liang, Junjie Yan

摘要:

随着深度学习的兴起,人脸识别领域取得了长足的进步。现有的方法主要集中在提取区分性特征上,直接通过点到点的方式计算余弦或L2距离,而不考虑上下文信息。在这项研究中,我们做了一个关键的观察,本地cont-text代表的相似性之间的实例和它的类间neighbors 1起着重要的作用FR。具体地说,我们尝试将特征空间中的局部信息纳入度量中,并提出了一个统一的框架,称为类间差异对齐(IDA),包括两个专用模块,差异对齐算子(IDA-DAO)和支持集估计(IDA-SSE)。IDA-DAO算法利用超球面上的自适应支持集定义图像与相邻图像之间的差异,对相似度进行匹配。对于实际推理,在线推理过程中很难获得支持集。IDA-SSE通过引入由GAN生成的虚拟候选图像,可以提供令人信服的类间邻居。此外,我们提出了可学习IDA-SSE,它可以隐式地给出估计,而不需要任何其他图像在评估过程中。建议IDA可以无缝地和有效地纳入现有的FR系统。大量的实验表明,该框架可以1)显着提高准确性,2)使模型对各种分布的人脸图像具有鲁棒性。没有花里胡哨的,我们的方法在多个标准FR基准上达到了最先进的性能。

英文摘要:

The field of face recognition (FR) has witnessed great progress with the surge of deep learning. Existing methods mainly focus on extracting discriminative features, and directly compute the cosine or L2 distance by the point-to-point way without considering the context information. In this study, we make a key observation that the local con-text represented by the similarities between the instance and its inter-class neighbors1plays an important role forFR. Specifically, we attempt to incorporate the local in-formation in the feature space into the metric, and pro-pose a unified framework calledInter-class DiscrepancyAlignment(IDA), with two dedicated modules, Discrepancy Alignment Operator(IDA-DAO) andSupport Set Estimation(IDA-SSE). IDA-DAO is used to align the similarity scores considering the discrepancy between the images and its neighbors, which is defined by adaptive support sets on the hypersphere. For practical inference, it is difficult to acquire support set during online inference. IDA-SSE can provide convincing inter-class neighbors by introducing virtual candidate images generated with GAN. Further-more, we propose the learnable IDA-SSE, which can implicitly give estimation without the need of any other images in the evaluation process. The proposed IDA can be incorporated into existing FR systems seamlessly and efficiently. Extensive experiments demonstrate that this frame-work can 1) significantly improve the accuracy, and 2) make the model robust to the face images of various distributions.Without bells and whistles, our method achieves state-of-the-art performance on multiple standard FR benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑