{"url":"/task/classifier-calibration","name":"Classifier calibration","slug":"classifier-calibration","description_markdown":"Confidence calibration – the problem of predicting probability estimates representative of the true correctness likelihood – is important for classification models in many applications. The two common calibration metrics are Expected Calibration Error (ECE) and Maximum Calibration Error (MCE).","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Audio","url":"/area/audio"},{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"},{"name":"Medical","url":"/area/medical"},{"name":"Methodology","url":"/area/methodology"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":29,"papers_with_code":19,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/classifier-calibration-on-cifar-100","slug":"classifier-calibration-on-cifar-100","dataset":"CIFAR-100","dataset_url":"/dataset/cifar-100","rows_in_archive":1,"metrics":["Expected Calibration Error"],"first_row_in_archive_order":{"model":"R-Mix (PreActResNet-18)","paper_title":"Expeditious Saliency-guided Mix-up through Random Gradient Thresholding","paper_url":"/paper/expeditious-saliency-guided-mix-up-through","paper_date":"2022-12-09","arxiv_id":"2212.04875","code_links":[{"title":"minhlong94/random-mixup","url":"https://github.com/minhlong94/random-mixup"}],"syntology":null}}],"datasets":[{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045}],"subtasks":[],"parent_tasks":[{"url":"/task/classification-1","name":"Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":19,"of":19,"tagged_in_all":29,"items":[{"url":"/paper/masksembles-for-uncertainty-estimation","title":"Masksembles for Uncertainty Estimation","date":"2020-12-15","arxiv_id":"2012.08334","repositories_listed":4,"syntology":null},{"url":"/paper/no-fear-of-heterogeneity-classifier","title":"No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data","date":"2021-06-09","arxiv_id":"2106.05001","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/preprompt-predictive-prompting-for-class","title":"PrePrompt: Predictive prompting for class incremental learning","date":"2025-05-13","arxiv_id":"2505.08586","repositories_listed":1,"syntology":null},{"url":"/paper/long-tailed-medical-diagnosis-with-relation","title":"Long-tailed Medical Diagnosis with Relation-aware Representation Learning and Iterative Classifier Calibration","date":"2025-02-05","arxiv_id":"2502.03238","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-generalized-few-shot-semantic","title":"Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer","date":"2024-12-20","arxiv_id":"2412.15835","repositories_listed":1,"syntology":null},{"url":"/paper/improved-user-identification-through","title":"Improved User Identification through Calibrated Monte-Carlo Dropout","date":"2024-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/accuracy-preserving-calibration-via","title":"Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex","date":"2024-02-21","arxiv_id":"2402.13765","repositories_listed":1,"syntology":null},{"url":"/paper/no-fear-of-classifier-biases-neural-collapse","title":"No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier","date":"2023-03-17","arxiv_id":"2303.10058","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/expeditious-saliency-guided-mix-up-through","title":"Expeditious Saliency-guided Mix-up through Random Gradient Thresholding","date":"2022-12-09","arxiv_id":"2212.04875","repositories_listed":1,"syntology":null},{"url":"/paper/fedfa-federated-learning-with-feature-anchors","title":"FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data","date":"2022-11-17","arxiv_id":"2211.09299","repositories_listed":1,"syntology":null},{"url":"/paper/packed-ensembles-for-efficient-uncertainty","title":"Packed-Ensembles for Efficient Uncertainty Estimation","date":"2022-10-17","arxiv_id":"2210.09184","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/class-wise-and-reduced-calibration-methods","title":"Class-wise and reduced calibration methods","date":"2022-10-07","arxiv_id":"2210.03702","repositories_listed":1,"syntology":null},{"url":"/paper/hidden-heterogeneity-when-to-choose","title":"Hidden Heterogeneity: When to Choose Similarity-Based Calibration","date":"2022-02-03","arxiv_id":"2202.01840","repositories_listed":1,"syntology":null},{"url":"/paper/generalized-and-incremental-few-shot-learning","title":"Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting","date":"2021-08-18","arxiv_id":"2108.08165","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/danish-fungi-2020-not-just-another-image","title":"Danish Fungi 2020 -- Not Just Another Image Recognition Dataset","date":"2021-03-18","arxiv_id":"2103.10107","repositories_listed":1,"syntology":null},{"url":"/paper/classifier-calibration-with-implications-to","title":"Classifier Calibration: with application to threat scores in cybersecurity","date":"2021-02-09","arxiv_id":"2102.05143","repositories_listed":1,"syntology":null},{"url":"/paper/how-well-do-self-supervised-models-transfer","title":"How Well Do Self-Supervised Models Transfer?","date":"2020-11-26","arxiv_id":"2011.13377","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/multivariate-confidence-calibration-for","title":"Multivariate Confidence Calibration for Object Detection","date":"2020-04-28","arxiv_id":"2004.13546","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/multi-class-probabilistic-classification","title":"Multi-class probabilistic classification using inductive and cross Venn-Abers predictors","date":"2017-06-16","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":6,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}