Lune

CVPR2020Top-tier venue

Domain Balancing: Face Recognition on Long-Tailed Domains

Dong Cao, Xiangyu Zhu, Xingyu Huang, Jianzhu Guo, Zhen Lei

Abstract

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

15 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • DAM: Discrepancy Alignment Metric for Face Recognition cites Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation Network
  • Learning to Learn across Diverse Data Biases in Deep Face Recognition cites DAM: Discrepancy Alignment Metric for Face Recognition
  • Learning to Learn across Diverse Data Biases in Deep Face Recognition cites Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation Network
  • Learning to Learn across Diverse Data Biases in Deep Face Recognition cites Learning Meta Face Recognition in Unseen Domains
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers15

  1. Nested Collaborative Learning for Long-Tailed Visual RecognitionJun Li, Zichang Tan, Jun Wan, Zhen Lei et al.CVPR 2022 · 95 citations
  2. Long-tailed Visual Recognition via Gaussian Clouded Logit AdjustmentMengke Li, Yiu-Ming Cheung, Yang LuCVPR 2022 · 84 citations
  3. Killing Two Birds with One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FCXiang An, Jiankang Deng, Jia Guo, Ziyong Feng et al.CVPR 2022 · 77 citations
  4. Learning to Learn across Diverse Data Biases in Deep Face RecognitionChang Liu, Xiang Yu, Yi-Hsuan Tsai, Masoud Faraki et al.CVPR 2022 · 22 citations
  5. DAM: Discrepancy Alignment Metric for Face RecognitionJiaheng Liu, Yudong Wu, Yichao Wu, Chuming Li et al.ICCV 2021 · 19 citations

Builds on2

  1. Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation NetworkMei Wang, Weihong Deng, Jiani Hu, Xunqiang Tao et al.ICCV 2019 · 379 citations
  2. Learning Meta Face Recognition in Unseen DomainsJianzhu Guo, Xiangyu Zhu, Chenxu Zhao, Dong Cao et al.CVPR 2020

Related papers

  1. Difficulty-aware Balancing Margin Loss for Long-tailed RecognitionMinseok Son, Inyong Koo, Jinyoung Park, Changick KimAAAI 2025 · 9 citations
  2. Long-tailed Distribution AdaptationZhiliang Peng, Wei Huang, Zonghao Guo, Xiaosong Zhang et al.ACM MM 2021 · 8 citations
  3. Long-tailed Recognition with Model RebalancingJiaan Luo, Feng Hong, Qiang Hu, Xiaofeng Cao et al.NeurIPS 2025 · 12 citations
  4. Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition From a Domain Adaptation PerspectiveMuhammad Abdullah Jamal, Matthew Brown, Ming-Hsuan Yang, Liqiang Wang et al.CVPR 2020
  5. Inverse Weight-Balancing for Deep Long-Tailed LearningWenqi Dang, Zhou Yang, Weisheng Dong, Xin Li et al.AAAI 2024 · 8 citations
Dusk over the sea between two cliffs drawn in fine vertical lines