Feature fusion plays a crucial role in unconstrained face recognition where inputs (probes) comprise of a set of $N$ low quality images whose individual qualities vary. Advances in attention and recurrent modules have led to feature fusion that can model the relationship among the images in the input set. However, attention mechanisms cannot scale to large $N$ due to their quadratic complexity and recurrent modules suffer from input order sensitivity. We propose a two-stage feature fusion paradigm, Cluster and Aggregate, that can both scale to large $N$ and maintain the ability to perform sequential inference with order invariance. Specifically, Cluster stage is a linear assignment of $N$ inputs to $M$ global cluster centers, and Aggregation stage is a fusion over $M$ clustered features. The clustered features play an integral role when the inputs are sequential as they can serve as a summarization of past features. By leveraging the order-invariance of incremental averaging operation, we design an update rule that achieves batch-order invariance, which guarantees that the contributions of early image in the sequence do not diminish as time steps increase. Experiments on IJB-B and IJB-S benchmark datasets show the superiority of the proposed two-stage paradigm in unconstrained face recognition. Code and pretrained models are available in https://github.com/mk-minchul/caface
翻译:在未经限制的面部识别中,当投入(方案)由一组低质量的低质量图像组成,其个人品质各不相同时,这些特征在不受限制的面部识别中发挥着关键作用。关注和经常模块的进展导致一些特征的融合,能够模拟输入集中图像之间的关系。然而,由于这些机制的二次复杂性和反复模块受到输入顺序敏感性的影响,因此不能将注意力规模扩大到大美元,而经常模块不能成为大美元。我们建议采用一个两阶段的特征融合模式,即集群和集成模式,既可以规模到大美元,也可以保持按顺序顺序进行顺序推断的能力。具体地说,分组阶段是向全球聚集中心直线性地分配美元的投入,聚合阶段是聚在一起,可以模拟输入集集集集的特性。当投入是连续的,因为它们可以作为输入顺序对过去特征的汇总。我们利用递增平均运行的顺序,我们设计了一种更新规则,既可以实现批量顺序,又能够保证序列中早期图像的贡献不会随着时间步骤的增加而减少。在IJ-B阶段前的模型/测试中,在IMS-Cregregnial Regnial 中,可以显示I-Cregnial Stredustrisal Stredustrial Stregnial Stredudustralment Stal Stalment Stalmentalmentalment a lavidustrital