{"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/nested-collaborative-learning-for-long-tailed","title":"Nested Collaborative Learning for Long-Tailed Visual Recognition","arxiv_id":"2203.15359","date":"2022-03-29","proceeding":"CVPR 2022 1","authors":["Jun Li","Zichang Tan","Jun Wan","Zhen Lei","Guodong Guo"],"abstract":"The networks trained on the long-tailed dataset vary remarkably, despite the same training settings, which shows the great uncertainty in long-tailed learning. To alleviate the uncertainty, we propose a Nested Collaborative Learning (NCL), which tackles the problem by collaboratively learning multiple experts together. NCL consists of two core components, namely Nested Individual Learning (NIL) and Nested Balanced Online Distillation (NBOD), which focus on the individual supervised learning for each single expert and the knowledge transferring among multiple experts, respectively. To learn representations more thoroughly, both NIL and NBOD are formulated in a nested way, in which the learning is conducted on not just all categories from a full perspective but some hard categories from a partial perspective. Regarding the learning in the partial perspective, we specifically select the negative categories with high predicted scores as the hard categories by using a proposed Hard Category Mining (HCM). In the NCL, the learning from two perspectives is nested, highly related and complementary, and helps the network to capture not only global and robust features but also meticulous distinguishing ability. Moreover, self-supervision is further utilized for feature enhancement. Extensive experiments manifest the superiority of our method with outperforming the state-of-the-art whether by using a single model or an ensemble.","url_abs":"https://arxiv.org/abs/2203.15359v2","url_pdf":"https://arxiv.org/pdf/2203.15359v2.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":"nested-collaborative-learning-for-long-tailed","repo_url":"https://github.com/bazinga699/ncl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"}],"methods":[{"method_slug":"ncl","method_name":"NCL"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=100)","model":"NCL(ResNet32)","rank_in_archive_order":11,"of":28,"metrics":{"Error Rate":"15.3"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-50","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=50)","model":"NCL(ResNet32)","rank_in_archive_order":7,"of":8,"metrics":{"Error Rate":"13.2"},"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":"NCL(ResNet32)","rank_in_archive_order":18,"of":66,"metrics":{"Error Rate":"46.7"},"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":"NCL(ResNet32)","rank_in_archive_order":16,"of":25,"metrics":{"Error Rate":"43.2"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"NCL(ResNeXt-50)","rank_in_archive_order":21,"of":69,"metrics":{"Top-1 Accuracy":"58.4"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"NCL(ResNet-50)","rank_in_archive_order":29,"of":69,"metrics":{"Top-1 Accuracy":"57.4"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"NCL(ResNet-152)","rank_in_archive_order":14,"of":29,"metrics":{"Top-1 Accuracy":"41.5"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"NCL(ResNet-50)","rank_in_archive_order":19,"of":43,"metrics":{"Top-1 Accuracy":"74.2%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.15359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15359"}},"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/bazinga699/ncl","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Bazinga699/NCL","reach":null}],"summary":{"ran_draft_wrong":1,"ran":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"270dd46baf67536e","entry":"NBOD_NCL_plus","repo":"Bazinga699/NCL","repo_kind":"official","path":"lib/loss/loss.py","file_url":"https://github.com/Bazinga699/NCL/blob/HEAD/lib/loss/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"270dd46baf67536e"}},{"code_sha256_prefix":"59b7f5f78d055951","entry":"NIL_NBOD_plus","repo":"Bazinga699/NCL","repo_kind":"official","path":"lib/loss/loss.py","file_url":"https://github.com/Bazinga699/NCL/blob/HEAD/lib/loss/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"59b7f5f78d055951"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}