The DOI matches its Crossref record; 64 of the 68 references it cites were found in a registry or an index.
Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation Network
Open accessAbstract
Racial bias is an important issue in biometric, but has not been thoroughly studied in deep face recognition. In this paper, we first contribute a dedicated dataset called Racial Faces in-the-Wild (RFW) database, on which we firmly validated the racial bias of four commercial APIs and four state-of-the-art (SOTA) algorithms. Then, we further present the solution using deep unsupervised domain adaptation and propose a deep information maximization adaptation network (IMAN) to alleviate this bias by using Caucasian as source domain and other races as target domains. This unsupervised method simultaneously aligns global distribution to decrease race gap at domain-level, and learns the discriminative target representations at cluster level. A novel mutual information loss is proposed to further enhance the discriminative ability of network output without label information. Extensive experiments on RFW, GBU, and IJB-A databases show that IMAN successfully learns features that generalize well across different races and across different databases.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Domain adaption techniques are also studied to enhance the generalizability of face recognition models between different data domains [84].”
From Trustworthy AI: From Principles to Practices (2023) · cites this paper as [84]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
Self-citationFaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00482 · Cited by 7,781
Improved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965
Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.41 · Cited by 5,479
Unsupervised Domain Adaptation by BackpropagationPreprint
Ganin, Y., & Lempitsky, V. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1409.7495 · Cited by 5,441
Flagged first, then by citations
4 of the 68 references couldn’t be matched to a known paper.
Research works printed but not linked: 8
- 2015, Freebase Data Dumps
- 0, Are face recognition systems accurate? depends on your race
- 0, Amazon’s rekognition tool
- garvie, 2016, The Perpetual Line-Up Unregulated Police Face Recognition in America
- cafiero, 2006, Integrating structured biological data by kernel maximum mean discrepancy, Bioinformatics, 22, 49e, 10.1093/bioinformatics/btl242 · DOI · Paper page
- 0, Face++ Research Toolkit
- 0, Ms-celeb-1m challenge 3 Face feature test/trillion pairs
- 0, Microsoft Azure
Cited by
Sorted by citations
Items 301–352 of 352
General Perspectives Toward the Impact of AI on Race and Society
Roberts, A. L., Richardson, B., Alikhademi, K., Drobina, E., & Gilbert, J. E. (2021) · Diversity and inclusion research · doi:10.1007/978-3-030-65417-7_18
Visual Recognition with Deep Learning from Biased Image Datasets.Preprint
Vogel, R., Clémençon, S., & Laforgue, P. (2021) · arXiv (Cornell University)
FDEA: Face Dataset with Ethnicity Attribute
Chen, J., Liu, T., Ou, F.-Z., & Wang, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88013-2_36
Wang, T. (2022) · International Conference on Intelligent Computing and Control Systems (ICICCS) · doi:10.1109/iciccs53718.2022.9788169
RetractedFreitas, R. T., Aires, K. R. T., de Paiva, A. C., Veras, R. D. M. S., & Soares, P. L. M. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4154044
A Hierarchical Bayes-Based Evolutionary Ensemble Classification Algorithm
Zhang, L., Chu, Z., Liang, L., & Yang, W.-C. (2022) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai55851.2022.9904224
An Empirical Comparative Analysis of Africans with Asians Using DCNN Facial Biometric Models
Muhammad, J., Wang, Y., Wang, L., Zhang, K., & Sun, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20233-9_14
Fairness von Biometrischen Systemen
Kolberg, J. (2023) · Datenschutz und Datensicherheit - DuD · doi:10.1007/s11623-022-1709-1
Uncovering demographic information on deep-face features
Ribeiro, R. O. (2023) · Journal of Engineering Research · doi:10.22533/at.ed.3173162311059
Face Anti-spoofing Progress Driven by Academic Challenges
Wan, J., Guo, G., Escalera, S., Escalante, H. J., & Li, S. Z. (2023) · Synthesis lectures on computer vision · doi:10.1007/978-3-031-32906-7_1
Evaluation of targeted dataset collection on racial equity in face recognition
Hong, R. S. (2023) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3600211.3604752
Clémençon, S., Laforgue, P., & Vogel, R. (2021) · Journal of nonparametric statistics (Print) · doi:10.1080/10485252.2023.2259011
A Detail Geometry Learning Network for High-Fidelity Face Reconstruction
Ma, K., Zhang, X., Wu, S., Zhang, B., Yang, L., & Yuan, Z. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44210-0_2
Who’s in My Archive? An End-to-End Framework for Automatic Annotation of TV Personalities
Montagnuolo, M., Negro, F., Messina, A., Bruccoleri, A., & Iacoviello, R. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386323
Unveiling Gender Effects in Gait Recognition Using Conditional-Matched Bootstrap Analysis
Ibragimov, A., Segundo, M. P., Sarkar, S., & Bowyer, K. W. (2024) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg59268.2024.10582036
Facial Ethnicity Classification by Efficiently Learning the Spatial Resolution of Feature Maps
Waris, F., & Da, F. (2024) · International Conference on Mechatronics Engineering (ICOM) · doi:10.1109/icom61675.2024.10652499
Improving Commonsense Bias Classification by Mitigating the Influence of Demographic Terms
Lee, J., & Kim, J. (2024) · IEEE Access · doi:10.1109/access.2024.3477599
Zhang, J., Ji, L., Gao, F., Li, M., Zhang, C., & Cui, Y. (2024) · Pattern Recognition Letters · doi:10.1016/j.patrec.2024.11.033
Chandaliya, P. K., Raja, K. B., Zhang, H., Ramachandra, R., & Busch, C. (2024) · IEEE International Workshop on Information Forensics and Security · doi:10.1109/wifs61860.2024.10810684
Societal Bias in Image Captioning: Identifying and Measuring Bias Amplification
HIROTA, Y., Nakashima, Y., & García, N. (2025) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2024edp7116
Mitigating Gender Bias Amplification in Image Captioning
HIROTA, Y., Nakashima, Y., & García, N. (2025) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2024edp7164
Agboada, T., Osunmakinde, I. O., Turner, C., & Nwosu, K. C. (2024) · International Conference on Computer and Applications (ICCA) · doi:10.1109/icca62237.2024.10927782
How Knowledge Distillation Mitigates the Synthetic Gap in Fair Face Recognition
Neto, P. C., Colakovic, I., Karakatič, S., & Sequeira, A. F. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91907-7_21
Fairness Under Cover: Evaluating the Impact of Occlusions on Demographic Bias in Facial Recognition
Mamede, R. M., Neto, P. C., & Sequeira, A. F. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-92648-8_6
A bipartite ranking approach to the two-sample problem
Clémençon, S., Limnios, M., & Vayatis, N. (2025) · Electronic Journal of Statistics · doi:10.1214/25-ejs2392
LossFIQA: A Shortcut Solution to Image Quality Assessment Using Loss for Faces and Beyond
Vaško, M., & Herout, A. (2025) · IEEE Access · doi:10.1109/access.2025.3589778
Improved Face Recognition Algorithm Based on MobilefacenetPreprint
Xu, M., Zhang, Z. Q., & Xia, T. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5384931
Gone with the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images
Qiu, T., Nichani, A., Tadayontahmasebi, R., & Jeong, H. (2025) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit63088.2025.11195694
Rep2Face: Synthetic Face Generation with Identity Representation Sampling
Jin, C., Li, K., Liu, J. H., Duan, J., & Huang, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4395-3_2
Trueskin: Towards Fair and Accurate Skin Tone Recognition and Generation
Lu, H. (2025) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai66417.2025.00104 · Cited by 1
Gender and Ethnicity Bias in Deep LearningPreprint
Islam, A. U., Zarin, I., Tabassum, T., Perera, W. S., & Islam, A. R. (2025) · Research Square · doi:10.21203/rs.3.rs-8321287/v1
Assessing Demographic Bias and Fairness in Facial Recognition Systems: A Framework
Rabanni, D. S. R., Oliveira, I. A. D., Wanderley, M., Silva, C. O., Almeida, R. A. R., Alvim, J. R., Poloni, K. M., Bicalho, G. C., & Pellicer, L. F. A. O. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-15990-8_6
Caldeira, E., Damer, N., & Boutros, F. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00622
Privacy-Preserving Continuous Sign Language Recognition
Xue, W., Tan, B., Guo, L., Yuan, T., Li, Y., Guo, J., & Chen, S. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3668639
Optimization of Data Collection in Facial Recognition Models through Subsampling Strategies
Tayler, S., Fiori, M., & Preciozzi, J. (2025) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb65343.2025.11411157
Holland, R., Rahman, S., Pal, S., Karmakar, C. K., & Pan, L. (2026) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2026.3669432
Refining machine learning evaluation : statistical insights into model performance and fairness
Soumm, M. (2024) · theses.fr (ABES) · doi:10.70675/a653ed6fz3b6ez4629za555z89b7bcadd995
Demographic-Agnostic ECG Biometrics: Addressing Bias in Deep Learning-Based Personal Identification
Pereira, T. M. C., Conceição, R. C., Sencadas, V., & Sebastião, R. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-19096-3_35
Unequal Privacy: Auditing Demographic Bias Vulnerabilities in Visual Protection Systems
Khorzooghi, S. M. S. M., Thota, P., Singhal, M., Asudeh, A., Das, G., & Nilizadeh, S. (2026) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3779208.3785292
Feature-Based Identity Unlearning Evaluation for Biometric Applications
Medvedev, I. O., Muhammed, A., & Gonçalves, N. (2026) · International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf68042.2026.11558178
Zhou, X., Li, B., Zeng, Q., & Chen, H. (2026) · International Conference on Artificial Intelligence and Industrial Technology Applications (AIITA) · doi:10.1109/aiita69518.2026.11567143
Phy-HHMR: Physics-Aware Holistic Human Mesh Reconstruction
Cai, J., Ye, B., Wang, L., Liu, B. Q., Ma, X., & Cheng, J. S. (2026) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2026.3701774
Debiasing Face Recognition with INLP: Fairness and Explainability for Prototype Few-Shot Models
Sherif, S., Ayoub, M., Aidaros, T., Yasser, Y., & Gamal, N. (2026) · IEEE International Conference on Smart Sustainable Systems for Computer and Engineering Applications (3SCEA) · doi:10.1109/3scea68071.2026.11603057
Alghudran, N. (2026) · International Conference on Federated Learning and Intelligent Computing Systems (FLICS) · doi:10.1109/flics70075.2026.11621907
Exploring Backdoor Vulnerabilities and Fairness Challenges in Generative Models: A Survey
Holland, R., Pal, S., & Pan, L. (2026) · ACM Computing Surveys · doi:10.1145/3847107
Muhammed, A., Marcos, J., & Gonçalves, N. (2026) · Pattern Analysis and Applications · doi:10.1007/s10044-026-01766-0
Weakly-Supervised Prompt-Guided Privacy Enhancement for Soft-Biometric Attributes in Facial Images
Hu, R., Chen, Z., Huang, P.-K., Yao, Z., Jin, B., & Ning, J. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3737706
GRoFA: Noise-Gated Adapters for Jointly Fair and Robust Face Embeddings
Suemoto, A., Arakawa, Y., & Mine, T. (2026) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3776574.3831174
Silva, J., Muhammed, A., Cruz, A., Sousa, B., & Gonçalves, N. (2026) · IET Biometrics · doi:10.1049/bme2/7426169
Measuring Hidden Bias within Face Recognition via Racial Phenotypes [other]
Yücer, Ş. (2021) · Durham Research Online (Durham University) · doi:10.15128/r2hm50tr746
Metadata
- Authors
- Wang, M., Deng, W., Hu, J., Tao, X., & Huang, Y.
- Affiliations
- Beijing University of Posts and Telecommunications (CN)
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 692-702
- OpenAlex
- W2982232682
- Cited by
- 353
- References
- 68
- Citations by year
- 2026: 19 · 2025: 47 · 2024: 51 · 2023: 60 · 2022: 69 · 2021: 68 · 2020: 37 · 2019: 2
- FWCI
- 14.34
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face and Expression Recognition
- Keywords
- racial bias, face recognition, deep face recognition, unsupervised domain adaptation, mutual information loss, cross-dataset generalization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
