{"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/distillation-techniques-for-pseudo-rehearsal","title":"Distillation Techniques for Pseudo-rehearsal Based Incremental Learning","arxiv_id":"1807.02799","date":"2018-07-08","proceeding":null,"authors":["Haseeb Shah","Khurram Javed","Faisal Shafait"],"abstract":"The ability to learn from incrementally arriving data is essential for any\nlife-long learning system. However, standard deep neural networks forget the\nknowledge about the old tasks, a phenomenon called catastrophic forgetting,\nwhen trained on incrementally arriving data. We discuss the biases in current\nGenerative Adversarial Networks (GAN) based approaches that learn the\nclassifier by knowledge distillation from previously trained classifiers. These\nbiases cause the trained classifier to perform poorly. We propose an approach\nto remove these biases by distilling knowledge from the classifier of AC-GAN.\nExperiments on MNIST and CIFAR10 show that this method is comparable to current\nstate of the art rehearsal based approaches. The code for this paper is\navailable at https://bit.ly/incremental-learning","url_abs":"http://arxiv.org/abs/1807.02799v3","url_pdf":"http://arxiv.org/pdf/1807.02799v3.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":"distillation-techniques-for-pseudo-rehearsal","repo_url":"https://github.com/haseebs/Pseudo-rehearsal-Incremental-Learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1807.02799","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}