{"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/classification-by-re-generation-towards","title":"Classification by Re-generation: Towards Classification Based on Variational Inference","arxiv_id":"1809.03259","date":"2018-09-10","proceeding":null,"authors":["Shideh Rezaeifar","Olga Taran","Slava Voloshynovskiy"],"abstract":"As Deep Neural Networks (DNNs) are considered the state-of-the-art in many\nclassification tasks, the question of their semantic generalizations has been\nraised. To address semantic interpretability of learned features, we introduce\na novel idea of classification by re-generation based on variational\nautoencoder (VAE) in which a separate encoder-decoder pair of VAE is trained\nfor each class. Moreover, the proposed architecture overcomes the scalability\nissue in current DNN networks as there is no need to re-train the whole network\nwith the addition of new classes and it can be done for each class separately.\nWe also introduce a criterion based on Kullback-Leibler divergence to reject\ndoubtful examples. This rejection criterion should improve the trust in the\nobtained results and can be further exploited to reject adversarial examples.","url_abs":"http://arxiv.org/abs/1809.03259v1","url_pdf":"http://arxiv.org/pdf/1809.03259v1.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":"classification-by-re-generation-towards","repo_url":"https://github.com/StijnVerdenius/Boosting_Text_Classifiers_by_Generative_Modelling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}