{"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/long-tailed-recognition-using-class-balanced","title":"Long-Tailed Recognition Using Class-Balanced Experts","arxiv_id":"2004.03706","date":"2020-04-07","proceeding":null,"authors":["Saurabh Sharma","Ning Yu","Mario Fritz","Bernt Schiele"],"abstract":"Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced distributions, yielding two main challenges: relative imbalance amongst the classes and data scarcity for mediumshot or fewshot classes. In this work, we address the problem of long-tailed recognition wherein the training set is highly imbalanced and the test set is kept balanced. Differently from existing paradigms relying on data-resampling, cost-sensitive learning, online hard example mining, loss objective reshaping, and/or memory-based modeling, we propose an ensemble of class-balanced experts that combines the strength of diverse classifiers. Our ensemble of class-balanced experts reaches results close to state-of-the-art and an extended ensemble establishes a new state-of-the-art on two benchmarks for long-tailed recognition. We conduct extensive experiments to analyse the performance of the ensembles, and discover that in modern large-scale datasets, relative imbalance is a harder problem than data scarcity. The training and evaluation code is available at https://github.com/ssfootball04/class-balanced-experts.","url_abs":"https://arxiv.org/abs/2004.03706v2","url_pdf":"https://arxiv.org/pdf/2004.03706v2.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":"long-tailed-recognition-using-class-balanced","repo_url":"https://github.com/ssfootball04/class-balanced-experts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"CBExperts","rank_in_archive_order":63,"of":69,"metrics":{"Top-1 Accuracy":"39.2"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"CBExperts","rank_in_archive_order":21,"of":29,"metrics":{"Top-1 Accuracy":"38.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.03706","atlas_url":"https://app.syntology.ai/?focus=2004.03706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.03706"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.03706"},"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":"2004.03706"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.03706\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2004.03706"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2004.03706\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2004.03706"},"call":"get_concepts_for_paper(arxiv_id=\"2004.03706\")"}],"by_repo":[{"repo":"ssfootball04/class-balanced-experts","kind":"official","samples":9,"ran":4,"instrument":1,"unverified":5}],"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/2004.03706.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/2004.03706.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/ssfootball04/class-balanced-experts","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"ran":3,"unverified":5},"n_samples":9,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":5,"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":{"official":{"samples":9,"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"},"n_pointer_only_for_licence":1,"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":1,"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":3,"n_ran_without_level_date":1,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-25","last":"2026-09-26","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":"fac5364e2f53c6db","code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"ssfootball04/class-balanced-experts","repo_kind":"official","path":"models.py","file_url":"https://github.com/ssfootball04/class-balanced-experts/blob/HEAD/models.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":"in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int","fixture_out_type":"Conv2d","code_page":"/code/conv3x3","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256":"f2095c01f04f3991","code_sha256_prefix":"f2095c01f04f3991","entry":"gen_features_and_probs","repo":"ssfootball04/class-balanced-experts","repo_kind":"official","path":"generate_features.py","file_url":"https://github.com/ssfootball04/class-balanced-experts/blob/HEAD/generate_features.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"args:Args/0/?, feature_extractor:callable/0/?, classifier:callable/0/?, device:device/0/?, loader:MockLoader/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T10:37:12.143382+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":"f2095c01f04f3991"}},{"code_sha256":"5972fbbf620ba327","code_sha256_prefix":"5972fbbf620ba327","entry":"gen_logits","repo":"ssfootball04/class-balanced-experts","repo_kind":"official","path":"gen_logits.py","file_url":"https://github.com/ssfootball04/class-balanced-experts/blob/HEAD/gen_logits.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"args:Args/0/?, feature_extractor:callable/0/?, classifier:callable/0/?, device:device/0/?, loader:MinimalLoader/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T09:05:34.340272+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":"5972fbbf620ba327"}},{"code_sha256":"07cca9631fe4f26a","code_sha256_prefix":"07cca9631fe4f26a","entry":"source_import","repo":"ssfootball04/class-balanced-experts","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ssfootball04/class-balanced-experts/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"file_path:str/0/str","fixture_out_type":"module","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":"/code/source-import","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"07cca9631fe4f26a"}},{"code_sha256":"80503a6a89030538","code_sha256_prefix":"80503a6a89030538","entry":"create_model_resnet10","repo":"ssfootball04/class-balanced-experts","repo_kind":"official","path":"models.py","file_url":"https://github.com/ssfootball04/class-balanced-experts/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"80503a6a89030538"}},{"code_sha256":"fd8416b029ac1ee5","code_sha256_prefix":"fd8416b029ac1ee5","entry":"create_model_resnet152","repo":"ssfootball04/class-balanced-experts","repo_kind":"official","path":"models.py","file_url":"https://github.com/ssfootball04/class-balanced-experts/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"fd8416b029ac1ee5"}},{"code_sha256":"4826cd3596c12660","code_sha256_prefix":"4826cd3596c12660","entry":"init_weights","repo":"ssfootball04/class-balanced-experts","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ssfootball04/class-balanced-experts/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/init-weights","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4826cd3596c12660"}},{"code_sha256":"6e5cdfaf59c333f7","code_sha256_prefix":"6e5cdfaf59c333f7","entry":"test","repo":"ssfootball04/class-balanced-experts","repo_kind":"official","path":"jointCalibration.py","file_url":"https://github.com/ssfootball04/class-balanced-experts/blob/HEAD/jointCalibration.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/test","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6e5cdfaf59c333f7"}},{"code_sha256":"077e42d8357a996a","code_sha256_prefix":"077e42d8357a996a","entry":"train","repo":"ssfootball04/class-balanced-experts","repo_kind":"official","path":"jointCalibration.py","file_url":"https://github.com/ssfootball04/class-balanced-experts/blob/HEAD/jointCalibration.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/train","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"077e42d8357a996a"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7c3b7e249d3ff63ea3d830eee5b203f9a1e18f7e222f0aa642778ba61090ced3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}