{"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-deep-representations-with","title":"Learning Deep Representations with Probabilistic Knowledge Transfer","arxiv_id":"1803.10837","date":"2018-03-28","proceeding":"ECCV 2018 9","authors":["Nikolaos Passalis","Anastasios Tefas"],"abstract":"Knowledge Transfer (KT) techniques tackle the problem of transferring the\nknowledge from a large and complex neural network into a smaller and faster\none. However, existing KT methods are tailored towards classification tasks and\nthey cannot be used efficiently for other representation learning tasks. In\nthis paper a novel knowledge transfer technique, that is capable of training a\nstudent model that maintains the same amount of mutual information between the\nlearned representation and a set of (possible unknown) labels as the teacher\nmodel, is proposed. Apart from outperforming existing KT techniques, the\nproposed method allows for overcoming several limitations of existing methods\nproviding new insight into KT as well as novel KT applications, ranging from\nknowledge transfer from handcrafted feature extractors to {cross-modal} KT from\nthe textual modality into the representation extracted from the visual modality\nof the data.","url_abs":"http://arxiv.org/abs/1803.10837v3","url_pdf":"http://arxiv.org/pdf/1803.10837v3.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-deep-representations-with","repo_url":"https://github.com/yoshitomo-matsubara/torchdistill","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.10837","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}