Domain Balancing: Face Recognition on Long-Tailed Domains
This addresses the challenge of imbalanced domain distribution in face recognition, which is incremental as it extends existing long-tailed class methods to domains.
The paper tackles the long-tailed domain distribution problem in face recognition, where a few domains appear frequently while others are rare, by proposing a Domain Balancing mechanism that includes a Domain Frequency Indicator, Residual Balancing Mapping block, and Domain Balancing Margin, achieving superior performance on benchmarks.
Long-tailed problem has been an important topic in face recognition task. However, existing methods only concentrate on the long-tailed distribution of classes. Differently, we devote to the long-tailed domain distribution problem, which refers to the fact that a small number of domains frequently appear while other domains far less existing. The key challenge of the problem is that domain labels are too complicated (related to race, age, pose, illumination, etc.) and inaccessible in real applications. In this paper, we propose a novel Domain Balancing (DB) mechanism to handle this problem. Specifically, we first propose a Domain Frequency Indicator (DFI) to judge whether a sample is from head domains or tail domains. Secondly, we formulate a light-weighted Residual Balancing Mapping (RBM) block to balance the domain distribution by adjusting the network according to DFI. Finally, we propose a Domain Balancing Margin (DBM) in the loss function to further optimize the feature space of the tail domains to improve generalization. Extensive analysis and experiments on several face recognition benchmarks demonstrate that the proposed method effectively enhances the generalization capacities and achieves superior performance.