{"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/calibration-of-neural-networks-using-splines","title":"Calibration of Neural Networks using Splines","arxiv_id":"2006.12800","date":"2020-06-23","proceeding":"ICLR 2021 1","authors":["Kartik Gupta","Amir Rahimi","Thalaiyasingam Ajanthan","Thomas Mensink","Cristian Sminchisescu","Richard Hartley"],"abstract":"Calibrating neural networks is of utmost importance when employing them in safety-critical applications where the downstream decision making depends on the predicted probabilities. Measuring calibration error amounts to comparing two empirical distributions. In this work, we introduce a binning-free calibration measure inspired by the classical Kolmogorov-Smirnov (KS) statistical test in which the main idea is to compare the respective cumulative probability distributions. From this, by approximating the empirical cumulative distribution using a differentiable function via splines, we obtain a recalibration function, which maps the network outputs to actual (calibrated) class assignment probabilities. The spine-fitting is performed using a held-out calibration set and the obtained recalibration function is evaluated on an unseen test set. We tested our method against existing calibration approaches on various image classification datasets and our spline-based recalibration approach consistently outperforms existing methods on KS error as well as other commonly used calibration measures. Our Code is available at https://github.com/kartikgupta-at-anu/spline-calibration.","url_abs":"https://arxiv.org/abs/2006.12800v2","url_pdf":"https://arxiv.org/pdf/2006.12800v2.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":"calibration-of-neural-networks-using-splines","repo_url":"https://github.com/kartikgupta-at-anu/spline-calibration","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.12800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.12800"}},"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/kartikgupta-at-anu/spline-calibration","reach":null}],"summary":{"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"2bd69793c2565f55","entry":"ensure_numpy","repo":"kartikgupta-at-anu/spline-calibration","repo_kind":"official","path":"recalibrate.py","file_url":"https://github.com/kartikgupta-at-anu/spline-calibration/blob/HEAD/recalibrate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2bd69793c2565f55"}},{"code_sha256_prefix":"6e568fe936bc7131","entry":"first_above","repo":"kartikgupta-at-anu/spline-calibration","repo_kind":"official","path":"recalibrate.py","file_url":"https://github.com/kartikgupta-at-anu/spline-calibration/blob/HEAD/recalibrate.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":"6e568fe936bc7131"}},{"code_sha256_prefix":"1dd42ccce10f052e","entry":"get_recalibration_function","repo":"kartikgupta-at-anu/spline-calibration","repo_kind":"official","path":"recalibrate.py","file_url":"https://github.com/kartikgupta-at-anu/spline-calibration/blob/HEAD/recalibrate.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":"1dd42ccce10f052e"}},{"code_sha256_prefix":"e9108e0765233758","entry":"interpolated_function","repo":"kartikgupta-at-anu/spline-calibration","repo_kind":"official","path":"recalibrate.py","file_url":"https://github.com/kartikgupta-at-anu/spline-calibration/blob/HEAD/recalibrate.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":"e9108e0765233758"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}