{"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/age-group-and-gender-estimation-in-the-wild","title":"Age Group and Gender Estimation in the Wild with Deep RoR Architecture","arxiv_id":"1710.02985","date":"2017-10-09","proceeding":null,"authors":["Ke Zhang","Ce Gao","Liru Guo","Miao Sun","Xingfang Yuan","Tony X. Han","Zhenbing Zhao","Baogang Li"],"abstract":"Automatically predicting age group and gender from face images acquired in\nunconstrained conditions is an important and challenging task in many\nreal-world applications. Nevertheless, the conventional methods with\nmanually-designed features on in-the-wild benchmarks are unsatisfactory because\nof incompetency to tackle large variations in unconstrained images. This\ndifficulty is alleviated to some degree through Convolutional Neural Networks\n(CNN) for its powerful feature representation. In this paper, we propose a new\nCNN based method for age group and gender estimation leveraging Residual\nNetworks of Residual Networks (RoR), which exhibits better optimization ability\nfor age group and gender classification than other CNN architectures.Moreover,\ntwo modest mechanisms based on observation of the characteristics of age group\nare presented to further improve the performance of age estimation.In order to\nfurther improve the performance and alleviate over-fitting problem, RoR model\nis pre-trained on ImageNet firstly, and then it is fune-tuned on the\nIMDB-WIKI-101 data set for further learning the features of face images,\nfinally, it is used to fine-tune on Adience data set. Our experiments\nillustrate the effectiveness of RoR method for age and gender estimation in the\nwild, where it achieves better performance than other CNN methods. Finally, the\nRoR-152+IMDB-WIKI-101 with two mechanisms achieves new state-of-the-art results\non Adience benchmark.","url_abs":"http://arxiv.org/abs/1710.02985v1","url_pdf":"http://arxiv.org/pdf/1710.02985v1.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":[],"tasks":[{"task_slug":"age-and-gender-classification","task_name":"Age And Gender Classification"},{"task_slug":"age-and-gender-estimation","task_name":"Age and Gender Estimation"},{"task_slug":"gender-classification","task_name":"Gender Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/age-and-gender-classification-on-adience-age","task":"Age And Gender Classification","dataset":"Adience Age","model":"RoR-34 + IMDB-WIKI","rank_in_archive_order":6,"of":16,"metrics":{"Accuracy (5-fold)":"66.74"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}