{"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/deep-regression-forests-for-age-estimation","title":"Deep Regression Forests for Age Estimation","arxiv_id":"1712.07195","date":"2017-12-19","proceeding":"CVPR 2018 6","authors":["Wei Shen","Yilu Guo","Yan Wang","Kai Zhao","Bo wang","Alan Yuille"],"abstract":"Age estimation from facial images is typically cast as a nonlinear regression\nproblem. The main challenge of this problem is the facial feature space w.r.t.\nages is heterogeneous, due to the large variation in facial appearance across\ndifferent persons of the same age and the non-stationary property of aging\npatterns. In this paper, we propose Deep Regression Forests (DRFs), an\nend-to-end model, for age estimation. DRFs connect the split nodes to a fully\nconnected layer of a convolutional neural network (CNN) and deal with\nheterogeneous data by jointly learning input-dependant data partitions at the\nsplit nodes and data abstractions at the leaf nodes. This joint learning\nfollows an alternating strategy: First, by fixing the leaf nodes, the split\nnodes as well as the CNN parameters are optimized by Back-propagation; Then, by\nfixing the split nodes, the leaf nodes are optimized by iterating a step-size\nfree and fast-converging update rule derived from Variational Bounding. We\nverify the proposed DRFs on three standard age estimation benchmarks and\nachieve state-of-the-art results on all of them.","url_abs":"http://arxiv.org/abs/1712.07195v1","url_pdf":"http://arxiv.org/pdf/1712.07195v1.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":"deep-regression-forests-for-age-estimation","repo_url":"https://github.com/Kasumigaoka-Utaha/Pytorch-implementation-of-DeepRegressionForests","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-regression-forests-for-age-estimation","repo_url":"https://github.com/shenwei1231/caffe-DeepRegressionForests","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"age-estimation","task_name":"Age Estimation"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/age-estimation-on-fgnet","task":"Age Estimation","dataset":"FGNET","model":"DRFs","rank_in_archive_order":6,"of":8,"metrics":{"MAE":"3.85"},"uses_additional_data":false},{"leaderboard":"/sota/age-estimation-on-morph-album2-caucasian","task":"Age Estimation","dataset":"MORPH album2 (Caucasian)","model":"DRFs","rank_in_archive_order":10,"of":11,"metrics":{"MAE":"2.91"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1712.07195","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}