{"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/from-noisy-prediction-to-true-label-noisy","title":"From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model","arxiv_id":"2205.00690","date":"2022-05-02","proceeding":null,"authors":["HeeSun Bae","Seungjae Shin","Byeonghu Na","JoonHo Jang","Kyungwoo Song","Il-Chul Moon"],"abstract":"Noisy labels are inevitable yet problematic in machine learning society. It ruins the generalization of a classifier by making the classifier over-fitted to noisy labels. Existing methods on noisy label have focused on modifying the classifier during the training procedure. It has two potential problems. First, these methods are not applicable to a pre-trained classifier without further access to training. Second, it is not easy to train a classifier and regularize all negative effects from noisy labels, simultaneously. We suggest a new branch of method, Noisy Prediction Calibration (NPC) in learning with noisy labels. Through the introduction and estimation of a new type of transition matrix via generative model, NPC corrects the noisy prediction from the pre-trained classifier to the true label as a post-processing scheme. We prove that NPC theoretically aligns with the transition matrix based methods. Yet, NPC empirically provides more accurate pathway to estimate true label, even without involvement in classifier learning. Also, NPC is applicable to any classifier trained with noisy label methods, if training instances and its predictions are available. Our method, NPC, boosts the classification performances of all baseline models on both synthetic and real-world datasets. The implemented code is available at https://github.com/BaeHeeSun/NPC.","url_abs":"https://arxiv.org/abs/2205.00690v3","url_pdf":"https://arxiv.org/pdf/2205.00690v3.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":"from-noisy-prediction-to-true-label-noisy","repo_url":"https://github.com/BaeHeeSun/NPC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"from-noisy-prediction-to-true-label-noisy","repo_url":"https://github.com/debajyotid2/noisy_prediction_calibration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"learning-with-noisy-labels","task_name":"Learning with noisy labels"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.00690","atlas_url":"https://app.syntology.ai/?focus=2205.00690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.00690"}},"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":"deterministic:regex_extraction","url":"https://github.com/BaeHeeSun/NPC","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/debajyotid2/noisy_prediction_calibration","reach":null}],"summary":{"ran":5,"ran_fixture":1,"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":3,"repositories":1},"listed":{"samples":6,"ran":3,"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":6,"samples":[{"code_sha256_prefix":"4662422f1e547580","entry":"CNN_CIFAR","repo":"debajyotid2/noisy_prediction_calibration","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/debajyotid2/noisy_prediction_calibration/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4662422f1e547580"}},{"code_sha256_prefix":"fe28cec2cd7f89f9","entry":"ConvBlock","repo":"debajyotid2/noisy_prediction_calibration","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/debajyotid2/noisy_prediction_calibration/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fe28cec2cd7f89f9"}},{"code_sha256_prefix":"82388716b0f85ec7","entry":"DataIterator","repo":"BaeHeeSun/NPC","repo_kind":"official","path":"train_npc.py","file_url":"https://github.com/BaeHeeSun/NPC/blob/HEAD/train_npc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"82388716b0f85ec7"}},{"code_sha256_prefix":"31ad9bc4fd47fd15","entry":"food_dataset","repo":"BaeHeeSun/NPC","repo_kind":"official","path":"train_npc.py","file_url":"https://github.com/BaeHeeSun/NPC/blob/HEAD/train_npc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"31ad9bc4fd47fd15"}},{"code_sha256_prefix":"6a560b8f68587e88","entry":"revised_dataset","repo":"BaeHeeSun/NPC","repo_kind":"official","path":"train_npc.py","file_url":"https://github.com/BaeHeeSun/NPC/blob/HEAD/train_npc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a560b8f68587e88"}},{"code_sha256_prefix":"71abe0c234120e1b","entry":"softplus","repo":"debajyotid2/noisy_prediction_calibration","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/debajyotid2/noisy_prediction_calibration/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"71abe0c234120e1b"}},{"code_sha256_prefix":"e5ea23e56cf9eb88","entry":"CNN_MNIST","repo":"debajyotid2/noisy_prediction_calibration","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/debajyotid2/noisy_prediction_calibration/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e5ea23e56cf9eb88"}},{"code_sha256_prefix":"bfad4989b977aff9","entry":"CVAE","repo":"debajyotid2/noisy_prediction_calibration","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/debajyotid2/noisy_prediction_calibration/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bfad4989b977aff9"}},{"code_sha256_prefix":"bfcfe8973219bd4f","entry":"NPC","repo":"BaeHeeSun/NPC","repo_kind":"official","path":"train_npc.py","file_url":"https://github.com/BaeHeeSun/NPC/blob/HEAD/train_npc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bfcfe8973219bd4f"}},{"code_sha256_prefix":"26a607b925ac39f3","entry":"clothing_dataset","repo":"BaeHeeSun/NPC","repo_kind":"official","path":"train_npc.py","file_url":"https://github.com/BaeHeeSun/NPC/blob/HEAD/train_npc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"26a607b925ac39f3"}},{"code_sha256_prefix":"e32fce1e6402e49a","entry":"load_cnn","repo":"debajyotid2/noisy_prediction_calibration","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/debajyotid2/noisy_prediction_calibration/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e32fce1e6402e49a"}},{"code_sha256_prefix":"4756d2ddfddd1ef2","entry":"load_dataset","repo":"BaeHeeSun/NPC","repo_kind":"official","path":"train_npc.py","file_url":"https://github.com/BaeHeeSun/NPC/blob/HEAD/train_npc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4756d2ddfddd1ef2"}},{"code_sha256_prefix":"04a2edcea2dabed9","entry":"plot_","repo":"BaeHeeSun/NPC","repo_kind":"official","path":"train_npc.py","file_url":"https://github.com/BaeHeeSun/NPC/blob/HEAD/train_npc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"04a2edcea2dabed9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}