{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/multigrain-a-unified-image-embedding-for","title":"MultiGrain: a unified image embedding for classes and instances","arxiv_id":"1902.05509","date":"2019-02-14","proceeding":null,"authors":["Maxim Berman","Hervé Jégou","Andrea Vedaldi","Iasonas Kokkinos","Matthijs Douze"],"abstract":"MultiGrain is a network architecture producing compact vector representations\nthat are suited both for image classification and particular object retrieval.\nIt builds on a standard classification trunk. The top of the network produces\nan embedding containing coarse and fine-grained information, so that images can\nbe recognized based on the object class, particular object, or if they are\ndistorted copies. Our joint training is simple: we minimize a cross-entropy\nloss for classification and a ranking loss that determines if two images are\nidentical up to data augmentation, with no need for additional labels. A key\ncomponent of MultiGrain is a pooling layer that takes advantage of\nhigh-resolution images with a network trained at a lower resolution.\n  When fed to a linear classifier, the learned embeddings provide\nstate-of-the-art classification accuracy. For instance, we obtain 79.4% top-1\naccuracy with a ResNet-50 learned on Imagenet, which is a +1.8% absolute\nimprovement over the AutoAugment method. When compared with the cosine\nsimilarity, the same embeddings perform on par with the state-of-the-art for\nimage retrieval at moderate resolutions.","url_abs":"http://arxiv.org/abs/1902.05509v2","url_pdf":"http://arxiv.org/pdf/1902.05509v2.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":"multigrain-a-unified-image-embedding-for","repo_url":"https://github.com/facebookresearch/multigrain","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multigrain-a-unified-image-embedding-for","repo_url":"https://github.com/leehangyu/MultiGrain_Application","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multigrain-a-unified-image-embedding-for","repo_url":"https://github.com/2023-MindSpore-1/ms-code-62","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"object","task_name":"Object"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"autoaugment","method_name":"AutoAugment"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"colorjitter","method_name":"ColorJitter"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"cutout","method_name":"Cutout"},{"method_slug":"generalized-mean-pooling","method_name":"Generalized Mean Pooling"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"multigrain","method_name":"MultiGrain"},{"method_slug":"pca-whitening","method_name":"PCA Whitening"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[{"slug":"multigrain","name":"MultiGrain","full_name":"MultiGrain"}],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MultiGrain PNASNet (500px)","rank_in_archive_order":407,"of":1060,"metrics":{"Top 1 Accuracy":"83.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MultiGrain PNASNet (450px)","rank_in_archive_order":447,"of":1060,"metrics":{"Top 1 Accuracy":"83.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MultiGrain SENet154 (450px)","rank_in_archive_order":462,"of":1060,"metrics":{"Top 1 Accuracy":"83.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MultiGrain SENet154 (400px)","rank_in_archive_order":473,"of":1060,"metrics":{"Top 1 Accuracy":"83.0%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MultiGrain SENet154 (500px)","rank_in_archive_order":506,"of":1060,"metrics":{"Top 1 Accuracy":"82.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MultiGrain PNASNet (400px)","rank_in_archive_order":519,"of":1060,"metrics":{"Top 1 Accuracy":"82.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MultiGrain PNASNet (300px)","rank_in_archive_order":648,"of":1060,"metrics":{"Top 1 Accuracy":"81.3%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MultiGrain R50-AA-500","rank_in_archive_order":755,"of":1060,"metrics":{"Top 1 Accuracy":"79.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MultiGrain R50-AA-224","rank_in_archive_order":845,"of":1060,"metrics":{"Top 1 Accuracy":"78.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"MultiGrain NASNet-A-Mobile (350px)","rank_in_archive_order":958,"of":1060,"metrics":{"Top 1 Accuracy":"75.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-inria-holidays","task":"Image Retrieval","dataset":"INRIA Holidays","model":"MultiGrain R50 @ 800","rank_in_archive_order":1,"of":2,"metrics":{"Mean mAP":"92.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-inria-holidays","task":"Image Retrieval","dataset":"INRIA Holidays","model":"MultiGrain R50 @ 500","rank_in_archive_order":2,"of":2,"metrics":{"Mean mAP":"91.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.05509","atlas_url":"https://app.syntology.ai/?focus=1902.05509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.05509"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1902.05509"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1902.05509"},"call":"get_harvested_code_for_paper(arxiv_id=\"1902.05509\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"1902.05509"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1902.05509\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1902.05509"},"call":"get_concepts_for_paper(arxiv_id=\"1902.05509\")"}],"by_repo":[{"repo":"facebookresearch/multigrain","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"leehangyu/MultiGrain_Application","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"2023-MindSpore-1/ms-code-62","kind":"listed","samples":4,"ran":4,"instrument":1,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/1902.05509.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/1902.05509.svg"},"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/2023-MindSpore-1/ms-code-62","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leehangyu/MultiGrain_Application","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/multigrain","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":3,"ran_draft_wrong":1},"n_samples":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":4,"ran":4,"n_ran_checked":3,"n_instrument":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"},"official_not_harvested":{"repositories":["facebookresearch/multigrain"],"harvested_for_other_papers":[0],"samples_from_other_repositories":4,"other_repositories":1,"samples_unlocated":0},"n_pointer_only_for_licence":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":4,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"1e7dce39d953aaa5","code_sha256_prefix":"1e7dce39d953aaa5","entry":"get_instance_features","repo":"2023-MindSpore-1/ms-code-62","repo_kind":"listed","path":"src/create_data.py","file_url":"https://github.com/2023-MindSpore-1/ms-code-62/blob/HEAD/src/create_data.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"instance:SampleInstance/0/?, tokenizer_src:MockTokenizer/0/?, tokenizer_trg:MockTokenizer/0/?, max_seq_length:int/0/int, bucket:list/1/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T22:24:42.659479+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1e7dce39d953aaa5"}},{"code_sha256":"b9e24c3e3e0e88a7","code_sha256_prefix":"b9e24c3e3e0e88a7","entry":"merge","repo":"2023-MindSpore-1/ms-code-62","repo_kind":"listed","path":"model_utils/config.py","file_url":"https://github.com/2023-MindSpore-1/ms-code-62/blob/HEAD/model_utils/config.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"args:Namespace/0/?, cfg:dict/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/merge","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b9e24c3e3e0e88a7"}},{"code_sha256":"738456e1b7388e7e","code_sha256_prefix":"738456e1b7388e7e","entry":"parse_cli_to_yaml","repo":"2023-MindSpore-1/ms-code-62","repo_kind":"listed","path":"model_utils/config.py","file_url":"https://github.com/2023-MindSpore-1/ms-code-62/blob/HEAD/model_utils/config.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"parser:ArgumentParser/0/?, cfg:dict/0/?, helper:dict/0/?, choices:dict/0/?, cfg_path:str/0/str","fixture_out_type":"Namespace","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":"/code/parse-cli-to-yaml","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"738456e1b7388e7e"}},{"code_sha256":"96a9939953d5992d","code_sha256_prefix":"96a9939953d5992d","entry":"parse_yaml","repo":"2023-MindSpore-1/ms-code-62","repo_kind":"listed","path":"model_utils/config.py","file_url":"https://github.com/2023-MindSpore-1/ms-code-62/blob/HEAD/model_utils/config.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"yaml_path:str/0/str","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T04:00:33.621019+00:00","code_page":"/code/parse-yaml","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"96a9939953d5992d"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b59cf4739c458d6b63118bf2a730abb45672559ea4ef7489225837394c4aec85","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}