{"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/learning-hierarchical-features-from","title":"Learning Hierarchical Features from Generative Models","arxiv_id":"1702.08396","date":"2017-02-27","proceeding":null,"authors":["Shengjia Zhao","Jiaming Song","Stefano Ermon"],"abstract":"Deep neural networks have been shown to be very successful at learning\nfeature hierarchies in supervised learning tasks. Generative models, on the\nother hand, have benefited less from hierarchical models with multiple layers\nof latent variables. In this paper, we prove that hierarchical latent variable\nmodels do not take advantage of the hierarchical structure when trained with\nexisting variational methods, and provide some limitations on the kind of\nfeatures existing models can learn. Finally we propose an alternative\narchitecture that do not suffer from these limitations. Our model is able to\nlearn highly interpretable and disentangled hierarchical features on several\nnatural image datasets with no task specific regularization or prior knowledge.","url_abs":"http://arxiv.org/abs/1702.08396v2","url_pdf":"http://arxiv.org/pdf/1702.08396v2.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":"learning-hierarchical-features-from","repo_url":"https://github.com/ShengjiaZhao/Variational-Ladder-Autoencoder","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"learning-hierarchical-features-from","repo_url":"https://github.com/Michedev/VLAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"learning-hierarchical-features-from","repo_url":"https://github.com/ermongroup/Variational-Ladder-Autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.08396","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}