{"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/post-training-uncertainty-calibration-of-deep","title":"Post Training Uncertainty Calibration of Deep Networks For Medical Image Segmentation","arxiv_id":"2010.14290","date":"2020-10-27","proceeding":null,"authors":["Axel-Jan Rousseau","Thijs Becker","Jeroen Bertels","Matthew B. Blaschko","Dirk Valkenborg"],"abstract":"Neural networks for automated image segmentation are typically trained to achieve maximum accuracy, while less attention has been given to the calibration of their confidence scores. However, well-calibrated confidence scores provide valuable information towards the user. We investigate several post hoc calibration methods that are straightforward to implement, some of which are novel. They are compared to Monte Carlo (MC) dropout. They are applied to neural networks trained with cross-entropy (CE) and soft Dice (SD) losses on BraTS 2018 and ISLES 2018. Surprisingly, models trained on SD loss are not necessarily less calibrated than those trained on CE loss. In all cases, at least one post hoc method improves the calibration. There is limited consistency across the results, so we can't conclude on one method being superior. In all cases, post hoc calibration is competitive with MC dropout. Although average calibration improves compared to the base model, subject-level variance of the calibration remains similar.","url_abs":"http://arxiv.org/abs/2010.14290v1","url_pdf":"http://arxiv.org/pdf/2010.14290v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"post-training-uncertainty-calibration-of-deep","repo_url":"https://github.com/AxelJanRousseau/PostTrainCalibration","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.14290","atlas_url":"https://app.syntology.ai/?focus=2010.14290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.14290"}},"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/AxelJanRousseau/PostTrainCalibration","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":"21b6802a3a6fc58e","entry":"create_unet_like_model","repo":"AxelJanRousseau/PostTrainCalibration","repo_kind":"official","path":"my_utils/unet_generalized.py","file_url":"https://github.com/AxelJanRousseau/PostTrainCalibration/blob/HEAD/my_utils/unet_generalized.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":"21b6802a3a6fc58e"}},{"code_sha256_prefix":"11428da06cc416b1","entry":"get_dataLoader","repo":"AxelJanRousseau/PostTrainCalibration","repo_kind":"official","path":"aux_scripts/save_aux_segmaps.py","file_url":"https://github.com/AxelJanRousseau/PostTrainCalibration/blob/HEAD/aux_scripts/save_aux_segmaps.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":"11428da06cc416b1"}},{"code_sha256_prefix":"0c26b1456347d493","entry":"sDice","repo":"AxelJanRousseau/PostTrainCalibration","repo_kind":"official","path":"u-net_model_scripts/retrain_dropout.py","file_url":"https://github.com/AxelJanRousseau/PostTrainCalibration/blob/HEAD/u-net_model_scripts/retrain_dropout.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":"0c26b1456347d493"}},{"code_sha256_prefix":"cd5ce6539f54a651","entry":"train_loop","repo":"AxelJanRousseau/PostTrainCalibration","repo_kind":"official","path":"u-net_model_scripts/finetune_base_model.py","file_url":"https://github.com/AxelJanRousseau/PostTrainCalibration/blob/HEAD/u-net_model_scripts/finetune_base_model.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":"cd5ce6539f54a651"}},{"code_sha256_prefix":"d7a8367bbcba0130","entry":"train_loop","repo":"AxelJanRousseau/PostTrainCalibration","repo_kind":"official","path":"u-net_model_scripts/retrain_dropout.py","file_url":"https://github.com/AxelJanRousseau/PostTrainCalibration/blob/HEAD/u-net_model_scripts/retrain_dropout.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":"d7a8367bbcba0130"}},{"code_sha256_prefix":"32b55ab704551fca","entry":"train_loop","repo":"AxelJanRousseau/PostTrainCalibration","repo_kind":"official","path":"aux_scripts/Train_aux.py","file_url":"https://github.com/AxelJanRousseau/PostTrainCalibration/blob/HEAD/aux_scripts/Train_aux.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":"32b55ab704551fca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}