{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/facegenderid-exploiting-gender-information-in","title":"FaceGenderID: Exploiting Gender Information in DCNNs Face Recognition Systems","arxiv_id":null,"date":"2019-06-28","proceeding":"Computer Vision and Pattern Recognition (CVPR), 2019 2019 6","authors":["Ruben Vera-Rodriguez","Marta Blazquez","Aythami Morales","Ester Gonzalez-Sosa","Joao C. Neves","Hugo Proenca"],"abstract":"This paper addresses the effect of gender as a covariate in face verification systems. Even  though pre-trained models based on Deep Convolutional Neural Networks (DCNNs), such as VGG-Face or ResNet-50, achieve very high performance, they are trained on very large datasets comprising millions of images, which have biases regarding demographic aspects like the gender and the ethnicity among others. In this work, we first analyse the separate performance of these state-of-the-art models for males and females. We observe a gap between face verification performances obtained by both gender classes. These results suggest that features obtained by biased models are affected by the gender covariate. We propose a gender-dependent training approach to improve the feature representation for both genders, and develop both: i) gender specific DCNNs models, and ii) a gender balanced DCNNs model. Our results show significant and consistent improvements in face verification performance for both genders, individually and in general with our proposed approach. Finally, we announce the availability (at GitHub) of the FaceGenderID DCNNs models proposed in this work, which can support further experiments on this topic.","url_abs":"http://openaccess.thecvf.com/content_CVPRW_2019/papers/BEFA/Vera-Rodriguez_FaceGenderID_Exploiting_Gender_Information_in_DCNNs_Face_Recognition_Systems_CVPRW_2019_paper.pdf","url_pdf":"http://openaccess.thecvf.com/content_CVPRW_2019/papers/BEFA/Vera-Rodriguez_FaceGenderID_Exploiting_Gender_Information_in_DCNNs_Face_Recognition_Systems_CVPRW_2019_paper.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"facegenderid-exploiting-gender-information-in","repo_url":"https://github.com/BiDAlab/FaceGenderID","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"face-verification","task_name":"Face Verification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}