{"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/bridgenet-a-continuity-aware-probabilistic","title":"BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation","arxiv_id":"1904.03358","date":"2019-04-06","proceeding":"CVPR 2019 6","authors":["Wanhua Li","Jiwen Lu","Jianjiang Feng","Chunjing Xu","Jie zhou","Qi Tian"],"abstract":"Age estimation is an important yet very challenging problem in computer\nvision. Existing methods for age estimation usually apply a divide-and-conquer\nstrategy to deal with heterogeneous data caused by the non-stationary aging\nprocess. However, the facial aging process is also a continuous process, and\nthe continuity relationship between different components has not been\neffectively exploited. In this paper, we propose BridgeNet for age estimation,\nwhich aims to mine the continuous relation between age labels effectively. The\nproposed BridgeNet consists of local regressors and gating networks. Local\nregressors partition the data space into multiple overlapping subspaces to\ntackle heterogeneous data and gating networks learn continuity aware weights\nfor the results of local regressors by employing the proposed bridge-tree\nstructure, which introduces bridge connections into tree models to enforce the\nsimilarity between neighbor nodes. Moreover, these two components of BridgeNet\ncan be jointly learned in an end-to-end way. We show experimental results on\nthe MORPH II, FG-NET and Chalearn LAP 2015 datasets and find that BridgeNet\noutperforms the state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1904.03358v1","url_pdf":"http://arxiv.org/pdf/1904.03358v1.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-estimation","task_name":"Age Estimation"},{"task_slug":"morph","task_name":"MORPH"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/age-estimation-on-chalearn-2015","task":"Age Estimation","dataset":"ChaLearn 2015","model":"BridgeNet","rank_in_archive_order":2,"of":7,"metrics":{"MAE":"2.87","e-error":"0.255140"},"uses_additional_data":false},{"leaderboard":"/sota/age-estimation-on-fgnet","task":"Age Estimation","dataset":"FGNET","model":"BridgeNet","rank_in_archive_order":2,"of":8,"metrics":{"MAE":"2.56"},"uses_additional_data":false},{"leaderboard":"/sota/age-estimation-on-morph-album2-caucasian","task":"Age Estimation","dataset":"MORPH album2 (Caucasian)","model":"BridgeNet","rank_in_archive_order":7,"of":11,"metrics":{"MAE":"2.38"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.03358","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}