{"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/masked-siamese-networks-for-label-efficient","title":"Masked Siamese Networks for Label-Efficient Learning","arxiv_id":"2204.07141","date":"2022-04-14","proceeding":null,"authors":["Mahmoud Assran","Mathilde Caron","Ishan Misra","Piotr Bojanowski","Florian Bordes","Pascal Vincent","Armand Joulin","Michael Rabbat","Nicolas Ballas"],"abstract":"We propose Masked Siamese Networks (MSN), a self-supervised learning framework for learning image representations. Our approach matches the representation of an image view containing randomly masked patches to the representation of the original unmasked image. This self-supervised pre-training strategy is particularly scalable when applied to Vision Transformers since only the unmasked patches are processed by the network. As a result, MSNs improve the scalability of joint-embedding architectures, while producing representations of a high semantic level that perform competitively on low-shot image classification. For instance, on ImageNet-1K, with only 5,000 annotated images, our base MSN model achieves 72.4% top-1 accuracy, and with 1% of ImageNet-1K labels, we achieve 75.7% top-1 accuracy, setting a new state-of-the-art for self-supervised learning on this benchmark. Our code is publicly available.","url_abs":"https://arxiv.org/abs/2204.07141v1","url_pdf":"https://arxiv.org/pdf/2204.07141v1.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":"masked-siamese-networks-for-label-efficient","repo_url":"https://github.com/facebookresearch/msn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"masked-siamese-networks-for-label-efficient","repo_url":"https://github.com/lightly-ai/lightly","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"MSN (ViT-L/7)","rank_in_archive_order":20,"of":144,"metrics":{"Number of Params":"306M","Top 1 Accuracy":"80.7%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"MSN (ViT-B/4)","rank_in_archive_order":12,"of":65,"metrics":{"Top 1 Accuracy":"75.7%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.07141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.07141"}},"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/lightly-ai/lightly","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/facebookresearch/msn","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2,"ran_fixture":1},"by_repo_kind":{"listed":{"samples":4,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"40a07efc5d195b6d","entry":"MSNLoss","repo":"lightly-ai/lightly","repo_kind":"listed","path":"lightly/loss/msn_loss.py","file_url":"https://github.com/lightly-ai/lightly/blob/HEAD/lightly/loss/msn_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40a07efc5d195b6d"}},{"code_sha256_prefix":"66b516f40140d7c6","entry":"prototype_probabilities","repo":"lightly-ai/lightly","repo_kind":"listed","path":"lightly/loss/msn_loss.py","file_url":"https://github.com/lightly-ai/lightly/blob/HEAD/lightly/loss/msn_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"66b516f40140d7c6"}},{"code_sha256_prefix":"65d0b05308ec2373","entry":"sharpen","repo":"lightly-ai/lightly","repo_kind":"listed","path":"lightly/loss/msn_loss.py","file_url":"https://github.com/lightly-ai/lightly/blob/HEAD/lightly/loss/msn_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65d0b05308ec2373"}},{"code_sha256_prefix":"c1dff37f3b19bb53","entry":"sinkhorn","repo":"lightly-ai/lightly","repo_kind":"listed","path":"lightly/loss/msn_loss.py","file_url":"https://github.com/lightly-ai/lightly/blob/HEAD/lightly/loss/msn_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1dff37f3b19bb53"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}