{"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/metaformer-a-unified-meta-framework-for-fine","title":"MetaFormer: A Unified Meta Framework for Fine-Grained Recognition","arxiv_id":"2203.02751","date":"2022-03-05","proceeding":null,"authors":["Qishuai Diao","Yi Jiang","Bin Wen","Jia Sun","Zehuan Yuan"],"abstract":"Fine-Grained Visual Classification(FGVC) is the task that requires recognizing the objects belonging to multiple subordinate categories of a super-category. Recent state-of-the-art methods usually design sophisticated learning pipelines to tackle this task. However, visual information alone is often not sufficient to accurately differentiate between fine-grained visual categories. Nowadays, the meta-information (e.g., spatio-temporal prior, attribute, and text description) usually appears along with the images. This inspires us to ask the question: Is it possible to use a unified and simple framework to utilize various meta-information to assist in fine-grained identification? To answer this problem, we explore a unified and strong meta-framework(MetaFormer) for fine-grained visual classification. In practice, MetaFormer provides a simple yet effective approach to address the joint learning of vision and various meta-information. Moreover, MetaFormer also provides a strong baseline for FGVC without bells and whistles. Extensive experiments demonstrate that MetaFormer can effectively use various meta-information to improve the performance of fine-grained recognition. In a fair comparison, MetaFormer can outperform the current SotA approaches with only vision information on the iNaturalist2017 and iNaturalist2018 datasets. Adding meta-information, MetaFormer can exceed the current SotA approaches by 5.9% and 5.3%, respectively. Moreover, MetaFormer can achieve 92.3% and 92.7% on CUB-200-2011 and NABirds, which significantly outperforms the SotA approaches. The source code and pre-trained models are released athttps://github.com/dqshuai/MetaFormer.","url_abs":"https://arxiv.org/abs/2203.02751v1","url_pdf":"https://arxiv.org/pdf/2203.02751v1.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":"metaformer-a-unified-meta-framework-for-fine","repo_url":"https://github.com/dqshuai/metaformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"metaformer-a-unified-meta-framework-for-fine","repo_url":"https://github.com/salluru007/papers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"metaformer","method_name":"MetaFormer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-nabirds","task":"Fine-Grained Image Classification","dataset":"NABirds","model":"MetaFormer\n(MetaFormer-2,384)","rank_in_archive_order":1,"of":30,"metrics":{"Accuracy":"93.0%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-inaturalist","task":"Image Classification","dataset":"iNaturalist","model":"MetaFormer\n(MetaFormer-2,384,extra_info)","rank_in_archive_order":4,"of":19,"metrics":{"Top 1 Accuracy":"83.4%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-inaturalist","task":"Image Classification","dataset":"iNaturalist","model":"MetaFormer\n(MetaFormer-2,384)","rank_in_archive_order":7,"of":19,"metrics":{"Top 1 Accuracy":"80.4%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"MetaFormer\n(MetaFormer-2,384,extra_info)","rank_in_archive_order":5,"of":60,"metrics":{"Top-1 Accuracy":"88.7%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"MetaFormer\n(MetaFormer-2,384)","rank_in_archive_order":10,"of":60,"metrics":{"Top-1 Accuracy":"84.3%"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2203.02751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.02751"}},"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/salluru007/papers","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dqshuai/metaformer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":13},"by_repo_kind":{"official":{"samples":14,"ran":1,"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":"2dd5dfa94542911e","entry":"drop_connect","repo":"dqshuai/metaformer","repo_kind":"official","path":"models/MBConv.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/models/MBConv.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2dd5dfa94542911e"}},{"code_sha256_prefix":"79a40d44aa98d47d","entry":"build_model","repo":"dqshuai/metaformer","repo_kind":"official","path":"models/build.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/models/build.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"79a40d44aa98d47d"}},{"code_sha256_prefix":"afd8b4308fca3c67","entry":"build_optimizer","repo":"dqshuai/metaformer","repo_kind":"official","path":"optimizer.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/optimizer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"afd8b4308fca3c67"}},{"code_sha256_prefix":"c02cc4e0b5720211","entry":"build_scheduler","repo":"dqshuai/metaformer","repo_kind":"official","path":"lr_scheduler.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/lr_scheduler.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c02cc4e0b5720211"}},{"code_sha256_prefix":"b0a5beb34716d5a6","entry":"check_keywords_in_name","repo":"dqshuai/metaformer","repo_kind":"official","path":"optimizer.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/optimizer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0a5beb34716d5a6"}},{"code_sha256_prefix":"cf5708fb94a7cddc","entry":"create_logger","repo":"dqshuai/metaformer","repo_kind":"official","path":"logger.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/logger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf5708fb94a7cddc"}},{"code_sha256_prefix":"f784c84ccdc6c1da","entry":"get_config","repo":"dqshuai/metaformer","repo_kind":"official","path":"config.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f784c84ccdc6c1da"}},{"code_sha256_prefix":"3b3b0cbad6bcc582","entry":"get_flops","repo":"dqshuai/metaformer","repo_kind":"official","path":"get_flops.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/get_flops.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3b3b0cbad6bcc582"}},{"code_sha256_prefix":"5dacd306c910a28b","entry":"get_inference_config","repo":"dqshuai/metaformer","repo_kind":"official","path":"config.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5dacd306c910a28b"}},{"code_sha256_prefix":"753d2f3182ddbe08","entry":"get_same_padding_conv2d","repo":"dqshuai/metaformer","repo_kind":"official","path":"models/MBConv.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/models/MBConv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"753d2f3182ddbe08"}},{"code_sha256_prefix":"0210f333cd18e2c2","entry":"get_width_and_height_from_size","repo":"dqshuai/metaformer","repo_kind":"official","path":"models/MBConv.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/models/MBConv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0210f333cd18e2c2"}},{"code_sha256_prefix":"9804456677a8bef6","entry":"make_blocks","repo":"dqshuai/metaformer","repo_kind":"official","path":"models/MetaFG.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/models/MetaFG.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9804456677a8bef6"}},{"code_sha256_prefix":"b70882103f8140eb","entry":"read_class_names","repo":"dqshuai/metaformer","repo_kind":"official","path":"inference.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/inference.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b70882103f8140eb"}},{"code_sha256_prefix":"eac7e5fdc70e5cc9","entry":"set_weight_decay","repo":"dqshuai/metaformer","repo_kind":"official","path":"optimizer.py","file_url":"https://github.com/dqshuai/metaformer/blob/HEAD/optimizer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eac7e5fdc70e5cc9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}