{"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/harnessing-hierarchical-label-distribution","title":"Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition","arxiv_id":"2405.07780","date":"2024-05-13","proceeding":null,"authors":["Zhiyong Yang","Qianqian Xu","Zitai Wang","Sicong Li","Boyu Han","Shilong Bao","Xiaochun Cao","Qingming Huang"],"abstract":"This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced. We argue that the variation in these distributions can be broken down hierarchically into global and local levels. The global ones reflect a broad range of diversity, while the local ones typically arise from milder changes, often focused on a particular neighbor. Traditional methods predominantly use a Mixture-of-Expert (MoE) approach, targeting a few fixed test label distributions that exhibit substantial global variations. However, the local variations are left unconsidered. To address this issue, we propose a new MoE strategy, $\\mathsf{DirMixE}$, which assigns experts to different Dirichlet meta-distributions of the label distribution, each targeting a specific aspect of local variations. Additionally, the diversity among these Dirichlet meta-distributions inherently captures global variations. This dual-level approach also leads to a more stable objective function, allowing us to sample different test distributions better to quantify the mean and variance of performance outcomes. Theoretically, we show that our proposed objective benefits from enhanced generalization by virtue of the variance-based regularization. Comprehensive experiments across multiple benchmarks confirm the effectiveness of $\\mathsf{DirMixE}$. The code is available at \\url{https://github.com/scongl/DirMixE}.","url_abs":"https://arxiv.org/abs/2405.07780v1","url_pdf":"https://arxiv.org/pdf/2405.07780v1.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":"harnessing-hierarchical-label-distribution","repo_url":"https://github.com/scongl/dirmixe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"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":[{"method_slug":"moe","method_name":"MoE"}],"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":"DirMixE","rank_in_archive_order":14,"of":28,"metrics":{"Error Rate":"16.74"},"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":"DirMixE","rank_in_archive_order":34,"of":66,"metrics":{"Error Rate":"51.62"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"DirMixE(ResNeXt-50)","rank_in_archive_order":20,"of":69,"metrics":{"Top-1 Accuracy":"58.61"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"DirMixE","rank_in_archive_order":23,"of":43,"metrics":{"Top-1 Accuracy":"73.21%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.07780","atlas_url":"https://app.syntology.ai/?focus=2405.07780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.07780"}},"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/scongl/dirmixe","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"4029ad7e226bb131","entry":"DiverseExpertLoss","repo":"scongl/dirmixe","repo_kind":"official","path":"model/loss.py","file_url":"https://github.com/scongl/dirmixe/blob/HEAD/model/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4029ad7e226bb131"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}