{"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/momentum-2-teacher-momentum-teacher-with","title":"Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning","arxiv_id":"2101.07525","date":"2021-01-19","proceeding":null,"authors":["Zeming Li","Songtao Liu","Jian Sun"],"abstract":"In this paper, we present a novel approach, Momentum$^2$ Teacher, for student-teacher based self-supervised learning. The approach performs momentum update on both network weights and batch normalization (BN) statistics. The teacher's weight is a momentum update of the student, and the teacher's BN statistics is a momentum update of those in history. The Momentum$^2$ Teacher is simple and efficient. It can achieve the state of the art results (74.5\\%) under ImageNet linear evaluation protocol using small-batch size(\\eg, 128), without requiring large-batch training on special hardware like TPU or inefficient across GPU operation (\\eg, shuffling BN, synced BN). Our implementation and pre-trained models will be given on GitHub\\footnote{https://github.com/zengarden/momentum2-teacher}.","url_abs":"https://arxiv.org/abs/2101.07525v1","url_pdf":"https://arxiv.org/pdf/2101.07525v1.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":"momentum-2-teacher-momentum-teacher-with","repo_url":"https://github.com/zengarden/momentum2-teacher","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"linear-evaluation","task_name":"Linear evaluation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.07525","atlas_url":"https://app.syntology.ai/?focus=2101.07525","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}