{"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/consistent-rank-logits-for-ordinal-regression","title":"Rank consistent ordinal regression for neural networks with application to age estimation","arxiv_id":"1901.07884","date":"2019-01-20","proceeding":null,"authors":["Wenzhi Cao","Vahid Mirjalili","Sebastian Raschka"],"abstract":"In many real-world prediction tasks, class labels include information about the relative ordering between labels, which is not captured by commonly-used loss functions such as multi-category cross-entropy. Recently, the deep learning community adopted ordinal regression frameworks to take such ordering information into account. Neural networks were equipped with ordinal regression capabilities by transforming ordinal targets into binary classification subtasks. However, this method suffers from inconsistencies among the different binary classifiers. To resolve these inconsistencies, we propose the COnsistent RAnk Logits (CORAL) framework with strong theoretical guarantees for rank-monotonicity and consistent confidence scores. Moreover, the proposed method is architecture-agnostic and can extend arbitrary state-of-the-art deep neural network classifiers for ordinal regression tasks. The empirical evaluation of the proposed rank-consistent method on a range of face-image datasets for age prediction shows a substantial reduction of the prediction error compared to the reference ordinal regression network.","url_abs":"https://arxiv.org/abs/1901.07884v7","url_pdf":"https://arxiv.org/pdf/1901.07884v7.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":"consistent-rank-logits-for-ordinal-regression","repo_url":"https://github.com/Raschka-research-group/coral-cnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"consistent-rank-logits-for-ordinal-regression","repo_url":"https://github.com/axeber01/dold","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"consistent-rank-logits-for-ordinal-regression","repo_url":"https://github.com/ck37/coral-ordinal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"consistent-rank-logits-for-ordinal-regression","repo_url":"https://github.com/mshehrozsajjad/Age-Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"age-and-gender-classification","task_name":"Age And Gender Classification"},{"task_slug":"age-estimation","task_name":"Age Estimation"},{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"gender-prediction","task_name":"Gender Prediction"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/age-estimation-on-afad","task":"Age Estimation","dataset":"AFAD","model":"CORAL","rank_in_archive_order":1,"of":10,"metrics":{"MAE":"3.48"},"uses_additional_data":false},{"leaderboard":"/sota/age-estimation-on-cacd","task":"Age Estimation","dataset":"CACD","model":"CORAL","rank_in_archive_order":13,"of":13,"metrics":{"MAE":"5.35"},"uses_additional_data":false},{"leaderboard":"/sota/age-estimation-on-morph-album2","task":"Age Estimation","dataset":"MORPH Album2","model":"CORAL","rank_in_archive_order":9,"of":9,"metrics":{"MAE":"2.59"},"uses_additional_data":false},{"leaderboard":"/sota/age-estimation-on-utkface","task":"Age Estimation","dataset":"UTKFace","model":"CORAL","rank_in_archive_order":14,"of":14,"metrics":{"MAE":"5.39"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.07884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07884"}},"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/mshehrozsajjad/Age-Classification","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/axeber01/dold","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Raschka-research-group/coral-cnn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ck37/coral-ordinal","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":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":"fac5364e2f53c6db","entry":"conv3x3","repo":"Raschka-research-group/coral-cnn","repo_kind":"official","path":"model-code/afad-coral.py","file_url":"https://github.com/Raschka-research-group/coral-cnn/blob/HEAD/model-code/afad-coral.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"6d83316de6056027","entry":"compute_mae_and_mse","repo":"Raschka-research-group/coral-cnn","repo_kind":"official","path":"model-code/afad-ce.py","file_url":"https://github.com/Raschka-research-group/coral-cnn/blob/HEAD/model-code/afad-ce.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":"6d83316de6056027"}},{"code_sha256_prefix":"22ea8e687086303e","entry":"compute_mae_and_mse","repo":"Raschka-research-group/coral-cnn","repo_kind":"official","path":"model-code/cacd-ce.py","file_url":"https://github.com/Raschka-research-group/coral-cnn/blob/HEAD/model-code/cacd-ce.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":"22ea8e687086303e"}},{"code_sha256_prefix":"5e80e5c6046f04bf","entry":"compute_mae_and_mse","repo":"Raschka-research-group/coral-cnn","repo_kind":"official","path":"model-code/morph-ce.py","file_url":"https://github.com/Raschka-research-group/coral-cnn/blob/HEAD/model-code/morph-ce.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":"5e80e5c6046f04bf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}