{"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/test-agnostic-long-tailed-recognition-by-test","title":"Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition","arxiv_id":"2107.09249","date":"2021-07-20","proceeding":null,"authors":["Yifan Zhang","Bryan Hooi","Lanqing Hong","Jiashi Feng"],"abstract":"Existing long-tailed recognition methods, aiming to train class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution. However, practical test class distributions often violate this assumption (e.g., being either long-tailed or even inversely long-tailed), which may lead existing methods to fail in real applications. In this paper, we study a more practical yet challenging task, called test-agnostic long-tailed recognition, where the training class distribution is long-tailed while the test class distribution is agnostic and not necessarily uniform. In addition to the issue of class imbalance, this task poses another challenge: the class distribution shift between the training and test data is unknown. To tackle this task, we propose a novel approach, called Self-supervised Aggregation of Diverse Experts, which consists of two strategies: (i) a new skill-diverse expert learning strategy that trains multiple experts from a single and stationary long-tailed dataset to separately handle different class distributions; (ii) a novel test-time expert aggregation strategy that leverages self-supervision to aggregate the learned multiple experts for handling unknown test class distributions. We theoretically show that our self-supervised strategy has a provable ability to simulate test-agnostic class distributions. Promising empirical results demonstrate the effectiveness of our method on both vanilla and test-agnostic long-tailed recognition. Code is available at \\url{https://github.com/Vanint/SADE-AgnosticLT}.","url_abs":"https://arxiv.org/abs/2107.09249v4","url_pdf":"https://arxiv.org/pdf/2107.09249v4.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":"test-agnostic-long-tailed-recognition-by-test","repo_url":"https://github.com/Vanint/TADE-AgnosticLT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"test-agnostic-long-tailed-recognition-by-test","repo_url":"https://github.com/vanint/sade-agnosticlt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"},{"task_slug":"test-agnostic-long-tailed-learning","task_name":"Test Agnostic Long-Tailed Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"TADE (ResNet-50)","rank_in_archive_order":33,"of":60,"metrics":{"Top-1 Accuracy":"72.9%"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=10)","model":"TADE","rank_in_archive_order":15,"of":50,"metrics":{"Error Rate":"9.2"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=10)","model":"RIDE","rank_in_archive_order":23,"of":50,"metrics":{"Error Rate":"10.3"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=100)","model":"TADE","rank_in_archive_order":13,"of":28,"metrics":{"Error Rate":"16.2"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=10)","model":"TADE","rank_in_archive_order":16,"of":31,"metrics":{"Error Rate":"36.4"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=100)","model":"TADE","rank_in_archive_order":29,"of":66,"metrics":{"Error Rate":"50.2"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-50","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=50)","model":"TADE","rank_in_archive_order":18,"of":25,"metrics":{"Error Rate":"46.1"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"TADE(ResNeXt101-32x4d)","rank_in_archive_order":13,"of":69,"metrics":{"Top-1 Accuracy":"61.4"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"TADE(ResNeXt-50)","rank_in_archive_order":18,"of":69,"metrics":{"Top-1 Accuracy":"58.8"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"TADE","rank_in_archive_order":15,"of":29,"metrics":{"Top 1 Accuracy":"40.9","Top-1 Accuracy":"41.3"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"TADE(ResNet-152)","rank_in_archive_order":9,"of":43,"metrics":{"Top-1 Accuracy":"77%"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"TADE","rank_in_archive_order":24,"of":43,"metrics":{"Top-1 Accuracy":"72.9%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.09249","atlas_url":"https://app.syntology.ai/?focus=2107.09249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09249"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/Vanint/TADE-AgnosticLT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vanint/sade-agnosticlt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"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":"1c1fdcd838303a0d","entry":"accuracy","repo":"Vanint/TADE-AgnosticLT","repo_kind":"official","path":"model/metric.py","file_url":"https://github.com/Vanint/TADE-AgnosticLT/blob/HEAD/model/metric.py","link_basis":"harvester_set","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":"1c1fdcd838303a0d"}},{"code_sha256_prefix":"4dcf06ba28983266","entry":"focal_loss","repo":"Vanint/TADE-AgnosticLT","repo_kind":"official","path":"model/loss.py","file_url":"https://github.com/Vanint/TADE-AgnosticLT/blob/HEAD/model/loss.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4dcf06ba28983266"}},{"code_sha256_prefix":"23198d10b9f73030","entry":"learing_rate_scheduler","repo":"Vanint/TADE-AgnosticLT","repo_kind":"official","path":"train_places.py","file_url":"https://github.com/Vanint/TADE-AgnosticLT/blob/HEAD/train_places.py","link_basis":"plan_row","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":"23198d10b9f73030"}},{"code_sha256_prefix":"c642158604bebe8a","entry":"top_k_acc","repo":"Vanint/TADE-AgnosticLT","repo_kind":"official","path":"model/metric.py","file_url":"https://github.com/Vanint/TADE-AgnosticLT/blob/HEAD/model/metric.py","link_basis":"harvester_set","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":"c642158604bebe8a"}},{"code_sha256_prefix":"0933d643f92c12aa","entry":"init_weights","repo":"Vanint/TADE-AgnosticLT","repo_kind":"official","path":"model/model.py","file_url":"https://github.com/Vanint/TADE-AgnosticLT/blob/HEAD/model/model.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":"0933d643f92c12aa"}},{"code_sha256_prefix":"bf3d5219dca41ccd","entry":"transform_convert","repo":"Vanint/TADE-AgnosticLT","repo_kind":"official","path":"selection_from_cifar_pool_balance.py","file_url":"https://github.com/Vanint/TADE-AgnosticLT/blob/HEAD/selection_from_cifar_pool_balance.py","link_basis":"first_harvest_node","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":"bf3d5219dca41ccd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}