{"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/how-mask-matters-towards-theoretical","title":"How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders","arxiv_id":"2210.08344","date":"2022-10-15","proceeding":null,"authors":["Qi Zhang","Yifei Wang","Yisen Wang"],"abstract":"Masked Autoencoders (MAE) based on a reconstruction task have risen to be a promising paradigm for self-supervised learning (SSL) and achieve state-of-the-art performance across different benchmark datasets. However, despite its impressive empirical success, there is still limited theoretical understanding of it. In this paper, we propose a theoretical understanding of how masking matters for MAE to learn meaningful features. We establish a close connection between MAE and contrastive learning, which shows that MAE implicit aligns the mask-induced positive pairs. Built upon this connection, we develop the first downstream guarantees for MAE methods, and analyze the effect of mask ratio. Besides, as a result of the implicit alignment, we also point out the dimensional collapse issue of MAE, and propose a Uniformity-enhanced MAE (U-MAE) loss that can effectively address this issue and bring significant improvements on real-world datasets, including CIFAR-10, ImageNet-100, and ImageNet-1K. Code is available at (https://github.com/zhangq327/U-MAE).","url_abs":"https://arxiv.org/abs/2210.08344v2","url_pdf":"https://arxiv.org/pdf/2210.08344v2.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":"how-mask-matters-towards-theoretical","repo_url":"https://github.com/zhangq327/u-mae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"how-mask-matters-towards-theoretical","repo_url":"https://github.com/yifanzhang-pro/m-mae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"mae","method_name":"MAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.08344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08344"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhangq327/u-mae","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yifanzhang-pro/m-mae","reach":null}],"summary":{"ran_honours":1,"ran_fixture":3},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"433cf34e0c3df1ab","entry":"centering_matrix","repo":"yifanzhang-pro/m-mae","repo_kind":"listed","path":"loss_func.py","file_url":"https://github.com/yifanzhang-pro/m-mae/blob/HEAD/loss_func.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"433cf34e0c3df1ab"}},{"code_sha256_prefix":"7b54aea2aebcf716","entry":"uniformity_loss","repo":"zhangq327/u-mae","repo_kind":"official","path":"loss_func.py","file_url":"https://github.com/zhangq327/u-mae/blob/HEAD/loss_func.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7b54aea2aebcf716"}},{"code_sha256_prefix":"17b779940935b91a","entry":"uniformity_loss_TCR","repo":"yifanzhang-pro/m-mae","repo_kind":"listed","path":"loss_func.py","file_url":"https://github.com/yifanzhang-pro/m-mae/blob/HEAD/loss_func.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"17b779940935b91a"}},{"code_sha256_prefix":"7669b99521c26a25","entry":"uniformity_loss_square","repo":"yifanzhang-pro/m-mae","repo_kind":"listed","path":"loss_func.py","file_url":"https://github.com/yifanzhang-pro/m-mae/blob/HEAD/loss_func.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7669b99521c26a25"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}