{"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-progressionregression-by-conditional","title":"Age Progression/Regression by Conditional Adversarial Autoencoder","arxiv_id":"1702.08423","date":"2017-02-27","proceeding":"CVPR 2017 7","authors":["Zhifei Zhang","Yang song","Hairong Qi"],"abstract":"\"If I provide you a face image of mine (without telling you the actual age\nwhen I took the picture) and a large amount of face images that I crawled\n(containing labeled faces of different ages but not necessarily paired), can\nyou show me what I would look like when I am 80 or what I was like when I was\n5?\" The answer is probably a \"No.\" Most existing face aging works attempt to\nlearn the transformation between age groups and thus would require the paired\nsamples as well as the labeled query image. In this paper, we look at the\nproblem from a generative modeling perspective such that no paired samples is\nrequired. In addition, given an unlabeled image, the generative model can\ndirectly produce the image with desired age attribute. We propose a conditional\nadversarial autoencoder (CAAE) that learns a face manifold, traversing on which\nsmooth age progression and regression can be realized simultaneously. In CAAE,\nthe face is first mapped to a latent vector through a convolutional encoder,\nand then the vector is projected to the face manifold conditional on age\nthrough a deconvolutional generator. The latent vector preserves personalized\nface features (i.e., personality) and the age condition controls progression\nvs. regression. Two adversarial networks are imposed on the encoder and\ngenerator, respectively, forcing to generate more photo-realistic faces.\nExperimental results demonstrate the appealing performance and flexibility of\nthe proposed framework by comparing with the state-of-the-art and ground truth.","url_abs":"http://arxiv.org/abs/1702.08423v2","url_pdf":"http://arxiv.org/pdf/1702.08423v2.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":"age-progressionregression-by-conditional","repo_url":"https://bitbucket.org/aicip/face-aging-caae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"age-progressionregression-by-conditional","repo_url":"https://github.com/aicip/utkface","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"age-progressionregression-by-conditional","repo_url":"https://github.com/mattans/AgeProgression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"age-progressionregression-by-conditional","repo_url":"https://github.com/yeefan1999/Explainable-Health-Prediction-with-Transfer-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"age-progressionregression-by-conditional","repo_url":"https://github.com/dslisleedh/GenerativeAutoencoders-tensorflow2/blob/main/caae.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[{"slug":"utkface","name":"UTKFace","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.08423","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}