{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:13:12Z","timestamp":1778249592738,"version":"3.51.4"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:00:00Z","timestamp":1776384000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133638","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T23:19:34Z","timestamp":1776467974000},"page":"133638","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Loss function assessment: Towards learning hard-to-learn classes"],"prefix":"10.1016","volume":"686","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1863-0520","authenticated-orcid":false,"given":"Bozhao","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marius","family":"Pedersen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kiran","family":"Raja","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"10","key":"10.1016\/j.neucom.2026.133638_bib0005","doi-asserted-by":"crossref","first-page":"3365","DOI":"10.1109\/TPAMI.2020.2982166","article-title":"Deep learning for image super-resolution: a survey","volume":"43","author":"Wang","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"9","key":"10.1016\/j.neucom.2026.133638_bib0010","doi-asserted-by":"crossref","first-page":"10795","DOI":"10.1109\/TPAMI.2023.3268118","article-title":"Deep long-tailed learning: a survey","volume":"45","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.neucom.2026.133638_bib0015","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/JBHI.2016.2636665","article-title":"Deep learning for health informatics","volume":"21","author":"Rav\u00ec","year":"2017","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"7","key":"10.1016\/j.neucom.2026.133638_bib0020","doi-asserted-by":"crossref","first-page":"2113","DOI":"10.1148\/rg.2017170077","article-title":"Deep learning: a primer for radiologists","volume":"37","author":"Chartrand","year":"2017","journal-title":"Radiographics"},{"key":"10.1016\/j.neucom.2026.133638_bib0025","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part v 24","first-page":"323","article-title":"Balanced-mixup for highly imbalanced medical image classification","author":"Galdran","year":"2021"},{"key":"10.1016\/j.neucom.2026.133638_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111680","article-title":"Improving imbalanced medical image classification through gan-based data augmentation methods","volume":"166","author":"Ding","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133638_bib0035","doi-asserted-by":"crossref","DOI":"10.3389\/fpubh.2017.00307","article-title":"Sensitivity, specificity, and predictive values: foundations, pliabilities, and pitfalls in research and practice","volume":"5","author":"Trevethan","year":"2017","journal-title":"Front. Public Health"},{"issue":"1","key":"10.1016\/j.neucom.2026.133638_bib0040","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1136\/ebnurs-2019-103225","article-title":"What are sensitivity and specificity?","volume":"23","author":"Swift","year":"2020","journal-title":"Evidence-Based Nursing"},{"key":"10.1016\/j.neucom.2026.133638_bib0045","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.neunet.2018.07.011","article-title":"A systematic study of the class imbalance problem in convolutional neural networks","volume":"106","author":"Buda","year":"2018","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.133638_bib0050","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1016\/j.jmsy.2023.10.014","article-title":"Systematic review of class imbalance problems in manufacturing","volume":"71","author":"de Giorgio","year":"2023","journal-title":"J. Manuf. Syst."},{"key":"10.1016\/j.neucom.2026.133638_bib0055","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s13755-020-00112-w","article-title":"Rsmote: improving classification performance over imbalanced medical datasets","volume":"8","author":"Naseriparsa","year":"2020","journal-title":"Health Inf. Sci. Syst."},{"key":"10.1016\/j.neucom.2026.133638_bib0060","series-title":"2015 IEEE International Conference on Computer Vision","first-page":"3730","article-title":"Deep learning face attributes in the wild","author":"Liu","year":"2015"},{"key":"10.1016\/j.neucom.2026.133638_bib0065","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.133638_bib0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2023.110415","article-title":"A broad review on class imbalance learning techniques","volume":"143","author":"Rezvani","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.neucom.2026.133638_bib0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111677","article-title":"Skew-probabilistic neural networks for learning from imbalanced data","volume":"165","author":"Naik","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133638_bib0080","first-page":"1","article-title":"A systematic review on long-tailed learning","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.133638_bib0085","doi-asserted-by":"crossref","first-page":"31842","DOI":"10.1109\/ACCESS.2025.3538917","article-title":"Adaptive focal loss for keypoint-based deep learning detectors addressing class imbalance","volume":"13","author":"Su","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.neucom.2026.133638_bib0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109842","article-title":"Hierarchical long-tailed classification based on multi-granularity knowledge transfer driven by multi-scale feature fusion","volume":"145","author":"Zhao","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133638_bib0095","series-title":"2020 25th International Conference on Pattern Recognition (ICPR)","first-page":"2490","article-title":"A close look at deep learning with small data","author":"Brigato","year":"2021"},{"key":"10.1016\/j.neucom.2026.133638_bib0100","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"1371","article-title":"Deep learning on small datasets without pre-training using cosine loss","author":"Barz","year":"2020"},{"key":"10.1016\/j.neucom.2026.133638_bib0105","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110138","article-title":"Convgen: a convex space learning approach for deep-generative oversampling and imbalanced classification of small tabular datasets","volume":"147","author":"Schultz","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133638_bib0110","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110806","article-title":"Few-shot learning with long-tailed labels","volume":"156","author":"Zhang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133638_bib0115","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"82","article-title":"Asymmetric loss for multi-label classification","author":"Ridnik","year":"2021"},{"issue":"2","key":"10.1016\/j.neucom.2026.133638_bib0120","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal loss for dense object detection","volume":"42","author":"Lin","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"10.1016\/j.neucom.2026.133638_bib0125","doi-asserted-by":"crossref","DOI":"10.1007\/s10462-025-11198-7","article-title":"A comprehensive survey of loss functions and metrics in deep learning","volume":"58","author":"Terven","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.neucom.2026.133638_bib0130","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110881","article-title":"A new data complexity measure for multi-class imbalanced classification tasks","volume":"157","author":"Han","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133638_bib0135","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.107146","article-title":"F-measure curves: a tool to visualize classifier performance under imbalance","volume":"100","author":"Soleymani","year":"2020","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133638_bib0140","article-title":"Binary cross entropy with deep learning technique for image classification","volume":"9","author":"Ruby","year":"2020","journal-title":"Int. J. Adv. Trends Comput. Sci. Eng."},{"key":"10.1016\/j.neucom.2026.133638_bib0145","series-title":"2022 International Conference on Robotics and Automation (ICRA)","first-page":"5063","article-title":"Striking the right balance: recall loss for semantic segmentation","author":"Tian","year":"2022"},{"key":"10.1016\/j.neucom.2026.133638_bib0150","author":"Schuurmans"},{"key":"10.1016\/j.neucom.2026.133638_bib0155","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume":"32","author":"Cao","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133638_bib0160","series-title":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","first-page":"1696","article-title":"Enlarged large margin loss for imbalanced classification","author":"Kato","year":"2023"},{"key":"10.1016\/j.neucom.2026.133638_bib0165","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131601","article-title":"Long-tail learning with rebalanced contrastive loss","volume":"657","author":"De Alvis","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133638_bib0170","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.neucom.2023.01.023","article-title":"Neural collapse inspired attraction\u2013repulsion-balanced loss for imbalanced learning","volume":"527","author":"Xie","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133638_bib0175","doi-asserted-by":"crossref","first-page":"3088","DOI":"10.1109\/TMM.2023.3306968","article-title":"Balanced classification: a unified framework for long-tailed object detection","volume":"26","author":"Qi","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.133638_bib0180","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.107997","article-title":"Scale-balanced loss for object detection","volume":"117","author":"Shuang","year":"2021","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133638_bib0185","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5375","article-title":"Learning deep representation for imbalanced classification","author":"Huang","year":"2016"},{"key":"10.1016\/j.neucom.2026.133638_bib0190","series-title":"Advances in Neural Information Processing Systems","first-page":"7032","article-title":"Learning to model the tail","volume":"vol. 30","author":"Wang","year":"2017"},{"key":"10.1016\/j.neucom.2026.133638_bib0195","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11662","article-title":"Equalization loss for long-tailed object recognition","author":"Tan","year":"2020"},{"key":"10.1016\/j.neucom.2026.133638_bib0200","series-title":"Advances in Neural Information Processing Systems","first-page":"3163","article-title":"Autobalance: optimized loss functions for imbalanced data","volume":"vol. 34","author":"Li","year":"2021"},{"key":"10.1016\/j.neucom.2026.133638_bib0205","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5598","article-title":"Decoupling representation and classifier for long-tailed recognition","author":"Kang","year":"2019"},{"key":"10.1016\/j.neucom.2026.133638_bib0210","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2537","article-title":"Large-scale long-tailed recognition in an open world","author":"Liu","year":"2019"},{"key":"10.1016\/j.neucom.2026.133638_bib0215","series-title":"Advances in Neural Information Processing Systems","first-page":"1513","article-title":"Long-tailed classification by keeping the good and removing the bad momentum causal effect","volume":"vol. 33","author":"Tang","year":"2020"},{"key":"10.1016\/j.neucom.2026.133638_bib0220","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9695","article-title":"Seesaw loss for long-tailed instance segmentation","author":"Wang","year":"2021"},{"issue":"8","key":"10.1016\/j.neucom.2026.133638_bib0225","first-page":"9812","article-title":"Balanced normalization for long-tailed visual recognition","volume":"45","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.133638_bib0230","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13896","article-title":"M2m: imbalanced classification via major-to-minor translation","author":"Kim","year":"2020"},{"key":"10.1016\/j.neucom.2026.133638_bib0235","article-title":"Feature-mix: class-dependent feature augmentation for long-tailed recognition","volume":"141","author":"Yang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133638_bib0240","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7610","article-title":"Rethinking class-balanced methods for long-tailed visual recognition from a meta-learning perspective","author":"Jamal","year":"2020"},{"key":"10.1016\/j.neucom.2026.133638_bib0245","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9719","article-title":"BBN: bilateral-branch network with cumulative learning for long-tailed visual recognition","author":"Zhou","year":"2020"},{"key":"10.1016\/j.neucom.2026.133638_bib0250","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9268","article-title":"Class-balanced loss based on effective number of samples","author":"Cui","year":"2019"},{"key":"10.1016\/j.neucom.2026.133638_bib0255","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7610","article-title":"Rethinking class-balanced methods for long-tailed visual recognition from a domain adaptation perspective","author":"Jamal","year":"2020"},{"key":"10.1016\/j.neucom.2026.133638_bib0260","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"735","article-title":"Influence-balanced loss for imbalanced visual classification","author":"Park","year":"2021"},{"key":"10.1016\/j.neucom.2026.133638_bib0265","series-title":"Learning Multiple Layers of Features from Tiny Images","first-page":"32","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.neucom.2026.133638_bib0270","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"issue":"3","key":"10.1016\/j.neucom.2026.133638_bib0275","doi-asserted-by":"crossref","first-page":"E415","DOI":"10.1055\/a-1035-9088","article-title":"Cad-cap: a 25, 000-image database serving the development of artificial intelligence for capsule endoscopy","volume":"8","author":"Leenhardt","year":"2020","journal-title":"Endosc. Int. Open"},{"issue":"1","key":"10.1016\/j.neucom.2026.133638_bib0280","doi-asserted-by":"crossref","first-page":"29","DOI":"10.4103\/2153-3539.186902","article-title":"Deep learning for digital pathology image analysis: a comprehensive tutorial with selected use cases","volume":"7","author":"Janowczyk","year":"2016","journal-title":"J. Pathol. Inform."},{"issue":"1","key":"10.1016\/j.neucom.2026.133638_bib0285","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-022-19675-7","article-title":"From labels to priors in capsule endoscopy: a prior guided approach for improving generalization with few labels","volume":"12","author":"Vats","year":"2022","journal-title":"Sci. Rep."},{"key":"10.1016\/j.neucom.2026.133638_bib0290","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4700","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"10.1016\/j.neucom.2026.133638_bib0295","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16519","article-title":"Bottleneck Transformers for visual recognition","author":"Srinivas","year":"2021"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226010350?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226010350?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T13:29:32Z","timestamp":1778246972000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226010350"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":59,"alternative-id":["S0925231226010350"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133638","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Loss function assessment: Towards learning hard-to-learn classes","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133638","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"133638"}}