{"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-image-modeling-with-local-multi-scale","title":"Masked Image Modeling with Local Multi-Scale Reconstruction","arxiv_id":"2303.05251","date":"2023-03-09","proceeding":"CVPR 2023 1","authors":["Haoqing Wang","Yehui Tang","Yunhe Wang","Jianyuan Guo","Zhi-Hong Deng","Kai Han"],"abstract":"Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their industrial applications. Although the lower layers play the key role in MIM, existing MIM models conduct reconstruction task only at the top layer of encoder. The lower layers are not explicitly guided and the interaction among their patches is only used for calculating new activations. Considering the reconstruction task requires non-trivial inter-patch interactions to reason target signals, we apply it to multiple local layers including lower and upper layers. Further, since the multiple layers expect to learn the information of different scales, we design local multi-scale reconstruction, where the lower and upper layers reconstruct fine-scale and coarse-scale supervision signals respectively. This design not only accelerates the representation learning process by explicitly guiding multiple layers, but also facilitates multi-scale semantical understanding to the input. Extensive experiments show that with significantly less pre-training burden, our model achieves comparable or better performance on classification, detection and segmentation tasks than existing MIM models.","url_abs":"https://arxiv.org/abs/2303.05251v1","url_pdf":"https://arxiv.org/pdf/2303.05251v1.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-image-modeling-with-local-multi-scale","repo_url":"https://github.com/huawei-noah/Efficient-Computing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"mim","method_name":"MIM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.05251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05251"}},"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/huawei-noah/Efficient-Computing","reach":null}],"summary":{"ran":4,"ran_honours":1,"unverified":5},"by_repo_kind":{"official":{"samples":9,"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":10,"samples":[{"code_sha256_prefix":"3a03ac228cdf3d69","entry":"GroupingModule","repo":"huawei-noah/Efficient-Computing","repo_kind":"official","path":"Self-supervised/LocalMIM/Swin/models_mim.py","file_url":"https://github.com/huawei-noah/Efficient-Computing/blob/HEAD/Self-supervised/LocalMIM/Swin/models_mim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3a03ac228cdf3d69"}},{"code_sha256_prefix":"976d9a296d256407","entry":"HOGLayer","repo":"huawei-noah/Efficient-Computing","repo_kind":"official","path":"Self-supervised/LocalMIM/Swin/models_mim.py","file_url":"https://github.com/huawei-noah/Efficient-Computing/blob/HEAD/Self-supervised/LocalMIM/Swin/models_mim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"976d9a296d256407"}},{"code_sha256_prefix":"df31273be2dcb4cf","entry":"PatchMerging","repo":"huawei-noah/Efficient-Computing","repo_kind":"official","path":"Self-supervised/LocalMIM/Swin/models_mim.py","file_url":"https://github.com/huawei-noah/Efficient-Computing/blob/HEAD/Self-supervised/LocalMIM/Swin/models_mim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"df31273be2dcb4cf"}},{"code_sha256_prefix":"7ae6eb99ab3a983c","entry":"WindowAttention","repo":"huawei-noah/Efficient-Computing","repo_kind":"official","path":"Self-supervised/LocalMIM/Swin/models_mim.py","file_url":"https://github.com/huawei-noah/Efficient-Computing/blob/HEAD/Self-supervised/LocalMIM/Swin/models_mim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7ae6eb99ab3a983c"}},{"code_sha256_prefix":"f1e430fd7c285ebd","entry":"get_coordinates","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f1e430fd7c285ebd"}},{"code_sha256_prefix":"ec180995b19188ee","entry":"BasicLayer","repo":"huawei-noah/Efficient-Computing","repo_kind":"official","path":"Self-supervised/LocalMIM/Swin/models_mim.py","file_url":"https://github.com/huawei-noah/Efficient-Computing/blob/HEAD/Self-supervised/LocalMIM/Swin/models_mim.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ec180995b19188ee"}},{"code_sha256_prefix":"f6040e454b341952","entry":"MaskedAutoencoderSwin","repo":"huawei-noah/Efficient-Computing","repo_kind":"official","path":"Self-supervised/LocalMIM/Swin/models_mim.py","file_url":"https://github.com/huawei-noah/Efficient-Computing/blob/HEAD/Self-supervised/LocalMIM/Swin/models_mim.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f6040e454b341952"}},{"code_sha256_prefix":"c3b0332f8e54ac49","entry":"SwinTransformer","repo":"huawei-noah/Efficient-Computing","repo_kind":"official","path":"Self-supervised/LocalMIM/Swin/models_mim.py","file_url":"https://github.com/huawei-noah/Efficient-Computing/blob/HEAD/Self-supervised/LocalMIM/Swin/models_mim.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c3b0332f8e54ac49"}},{"code_sha256_prefix":"34d5dbbb06999f1b","entry":"SwinTransformerBlock","repo":"huawei-noah/Efficient-Computing","repo_kind":"official","path":"Self-supervised/LocalMIM/Swin/models_mim.py","file_url":"https://github.com/huawei-noah/Efficient-Computing/blob/HEAD/Self-supervised/LocalMIM/Swin/models_mim.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"34d5dbbb06999f1b"}},{"code_sha256_prefix":"b9a796b8a8ee957a","entry":"ViT_Decoder","repo":"huawei-noah/Efficient-Computing","repo_kind":"official","path":"Self-supervised/LocalMIM/Swin/models_mim.py","file_url":"https://github.com/huawei-noah/Efficient-Computing/blob/HEAD/Self-supervised/LocalMIM/Swin/models_mim.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b9a796b8a8ee957a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}