{"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/difficulty-net-learning-to-predict-difficulty","title":"Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition","arxiv_id":"2209.02960","date":"2022-09-07","proceeding":null,"authors":["Saptarshi Sinha","Hiroki Ohashi"],"abstract":"Long-tailed datasets, where head classes comprise much more training samples than tail classes, cause recognition models to get biased towards the head classes. Weighted loss is one of the most popular ways of mitigating this issue, and a recent work has suggested that class-difficulty might be a better clue than conventionally used class-frequency to decide the distribution of weights. A heuristic formulation was used in the previous work for quantifying the difficulty, but we empirically find that the optimal formulation varies depending on the characteristics of datasets. Therefore, we propose Difficulty-Net, which learns to predict the difficulty of classes using the model's performance in a meta-learning framework. To make it learn reasonable difficulty of a class within the context of other classes, we newly introduce two key concepts, namely the relative difficulty and the driver loss. The former helps Difficulty-Net take other classes into account when calculating difficulty of a class, while the latter is indispensable for guiding the learning to a meaningful direction. Extensive experiments on popular long-tailed datasets demonstrated the effectiveness of the proposed method, and it achieved state-of-the-art performance on multiple long-tailed datasets.","url_abs":"https://arxiv.org/abs/2209.02960v1","url_pdf":"https://arxiv.org/pdf/2209.02960v1.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":"difficulty-net-learning-to-predict-difficulty","repo_url":"https://github.com/hitachi-rd-cv/Difficulty_Net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=10)","model":"Difficulty-Net","rank_in_archive_order":12,"of":31,"metrics":{"Error Rate":"34.78"},"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":"Difficulty-Net","rank_in_archive_order":22,"of":66,"metrics":{"Error Rate":"47.04"},"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":"Difficulty-Net","rank_in_archive_order":15,"of":25,"metrics":{"Error Rate":"43.1"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"Difficulty-Net (ResNet-50 using RandAugment, single model)","rank_in_archive_order":30,"of":69,"metrics":{"Top-1 Accuracy":"57.4"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"Difficulty-Net (ResNet-50 w/o using RandAugment, single model)","rank_in_archive_order":40,"of":69,"metrics":{"Top-1 Accuracy":"54.0"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"Difficulty-Net (ResNet-10 w/o using RandAugment, single model","rank_in_archive_order":58,"of":69,"metrics":{"Top-1 Accuracy":"44.6"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"Difficulty-Net (ResNet-152)","rank_in_archive_order":12,"of":29,"metrics":{"Top-1 Accuracy":"41.7"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"hitachi-rd-cv/Difficulty_Net","kind":"official","samples":0,"ran":0,"instrument":0,"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"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"74b0f4488f19d182455db370f2e1f4f3a6b21489e10b0a9f8740453cbfe1e3cb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}