{"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/training-compact-deep-learning-models-for","title":"Training compact deep learning models for video classification using circulant matrices","arxiv_id":"1810.01140","date":"2018-10-02","proceeding":null,"authors":["Alexandre Araujo","Benjamin Negrevergne","Yann Chevaleyre","Jamal Atif"],"abstract":"In real world scenarios, model accuracy is hardly the only factor to\nconsider. Large models consume more memory and are computationally more\nintensive, which makes them difficult to train and to deploy, especially on\nmobile devices. In this paper, we build on recent results at the crossroads of\nLinear Algebra and Deep Learning which demonstrate how imposing a structure on\nlarge weight matrices can be used to reduce the size of the model. We propose\nvery compact models for video classification based on state-of-the-art network\narchitectures such as Deep Bag-of-Frames, NetVLAD and NetFisherVectors. We then\nconduct thorough experiments using the large YouTube-8M video classification\ndataset. As we will show, the circulant DBoF embedding achieves an excellent\ntrade-off between size and accuracy.","url_abs":"http://arxiv.org/abs/1810.01140v2","url_pdf":"http://arxiv.org/pdf/1810.01140v2.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":"training-compact-deep-learning-models-for","repo_url":"https://github.com/araujoalexandre/youtube8m-circulant","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"video-classification","task_name":"Video Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}