{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T13:30:52Z","timestamp":1762608652271,"version":"build-2065373602"},"reference-count":29,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2022,3,18]],"date-time":"2022-03-18T00:00:00Z","timestamp":1647561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Mathematics"],"abstract":"<jats:p>Ordinal classification tasks are present in a large number of different domains. However, common losses for deep neural networks, such as cross-entropy, do not properly weight the relative ordering between classes. For that reason, many losses have been proposed in the literature, which model the output probabilities as following a unimodal distribution. This manuscript reviews many of these losses on three different datasets and suggests a potential improvement that focuses the unimodal constraint on the neighborhood around the true class, allowing for a more flexible distribution, aptly called quasi-unimodal loss. For this purpose, two constraints are proposed: A first constraint concerns the relative order of the top-three probabilities, and a second constraint ensures that the remaining output probabilities are not higher than the top three. Therefore, gradient descent focuses on improving the decision boundary around the true class in detriment to the more distant classes. The proposed loss is found to be competitive in several cases.<\/jats:p>","DOI":"10.3390\/math10060980","type":"journal-article","created":{"date-parts":[[2022,3,20]],"date-time":"2022-03-20T21:34:27Z","timestamp":1647812067000},"page":"980","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Quasi-Unimodal Distributions for Ordinal Classification"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3246-7206","authenticated-orcid":false,"given":"Tom\u00e9","family":"Albuquerque","sequence":"first","affiliation":[{"name":"Institute for Systems and Computer Engineering, Technology and Science, 4200-465 Porto, Portugal"},{"name":"Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"}]},{"given":"Ricardo","family":"Cruz","sequence":"additional","affiliation":[{"name":"Institute for Systems and Computer Engineering, Technology and Science, 4200-465 Porto, Portugal"},{"name":"Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3760-2473","authenticated-orcid":false,"given":"Jaime S.","family":"Cardoso","sequence":"additional","affiliation":[{"name":"Institute for Systems and Computer Engineering, Technology and Science, 4200-465 Porto, Portugal"},{"name":"Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2022,3,18]]},"reference":[{"key":"ref_1","unstructured":"Belharbi, S., Ayed, I.B., McCaffrey, L., and Granger, E. (2020). Non-parametric Uni-modality Constraints for Deep Ordinal Classification. arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e457","DOI":"10.7717\/peerj-cs.457","article-title":"Ordinal losses for classification of cervical cancer risk","volume":"7","author":"Albuquerque","year":"2021","journal-title":"PeerJ Comput. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Liu, H., Lu, J., Feng, J., and Zhou, J. (June, January 30). Ordinal Deep Feature Learning for Facial Age Estimation. Proceedings of the 2017 12th IEEE International Conference on Automatic Face Gesture Recognition (FG 2017), Washington, DC, USA.","DOI":"10.1109\/FG.2017.28"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Pan, H., Han, H., Shan, S., and Chen, X. (2018, January 18\u201323). Mean-Variance Loss for Deep Age Estimation from a Face. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00554"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"120102","DOI":"10.1007\/s11432-019-2733-4","article-title":"Ordinal Distribution Regression for Gait-based Age Estimation","volume":"63","author":"Zhu","year":"2020","journal-title":"Sci. China Inf. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Dietterich, T., Becker, S., and Ghahramani, Z. (2002). Pranking with Ranking. Advances in Neural Information Processing Systems, MIT Press.","DOI":"10.7551\/mitpress\/1120.001.0001"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Koren, Y., and Sill, J. (2011, January 23\u201327). OrdRec: An ordinal model for predicting personalized item rating distributions. Proceedings of the Fifth ACM Conference on Recommender Systems, Chicago, IL, USA.","DOI":"10.1145\/2043932.2043956"},{"key":"ref_8","first-page":"201","article-title":"Penalized Ordinal Regression Methods for Predicting Stage of Cancer in High-Dimensional Covariate Spaces","volume":"14","author":"Gentry","year":"2015","journal-title":"Cancer Inform."},{"key":"ref_9","unstructured":"Moody, J.E., and Utans, J. (December, January 27). Architecture Selection Strategies for Neural Networks: Application to Corporate Bond Rating Predicti. Proceedings of the Neural Networks in the Capital Markets, NIPS 1995, Denver, CO, USA."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Jia, X., Zheng, X., Li, W., Zhang, C., and Li, Z. (2019, January 15\u201320). Facial Emotion Distribution Learning by Exploiting Low-Rank Label Correlations Locally. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01007"},{"key":"ref_11","first-page":"363","article-title":"Structured and Sparse Annotations for Image Emotion Distribution Learning","volume":"33","author":"Xiong","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Xue, H., and Geng, X. (2015, January 26\u201330). Emotion Distribution Recognition from Facial Expressions. Proceedings of the MM \u201915: Proceedings of the 23rd ACM International Conference on Multimedia, New York, NY, USA.","DOI":"10.1145\/2733373.2806328"},{"key":"ref_13","first-page":"499","article-title":"Dating Historical Color Images","volume":"Volume 7577","author":"Palermo","year":"2012","journal-title":"European Conference on Computer Vision"},{"key":"ref_14","first-page":"411","article-title":"Unimodal Probability Distributions for Deep Ordinal Classification","volume":"Volume 70","author":"Precup","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref_15","first-page":"1393","article-title":"Learning to Classify Ordinal Data: The Data Replication Method","volume":"8","author":"Cardoso","year":"2007","journal-title":"J. Mach. Learn. Res."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Costa, J., and Cardoso, J. (2005). Classification of Ordinal Data Using Neural Networks. European Conference on Machine Learning, Springer.","DOI":"10.1007\/11564096_70"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Frank, E., and Hall, M. (2001). A simple approach to ordinal classification. European Conference on Machine Learning, Springer.","DOI":"10.1007\/3-540-44795-4_13"},{"key":"ref_18","unstructured":"Cheng, J., Wang, Z., and Pollastri, G. (2008, January 1\u20138). A neural network approach to ordinal regression. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Cardoso, J.S., and Sousa, R. (2010, January 12\u201314). Classification Models with Global Constraints for Ordinal Data. Proceedings of the 2010 Ninth International Conference on Machine Learning and Applications, Washington, DC, USA.","DOI":"10.1109\/ICMLA.2010.18"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Sousa, R., and Cardoso, J.S. (2011, January 22\u201324). Ensemble of decision trees with global constraints for ordinal classification. Proceedings of the 2011 11th International Conference on Intelligent Systems Design and Applications, C\u00f3rdoba, Spain.","DOI":"10.1109\/ISDA.2011.6121816"},{"key":"ref_21","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_23","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_24","unstructured":"Jantzen, J., and Dounias, G. (December, January 29). Analysis of Pap-smear image data. Proceedings of the Nature-Inspired Smart Information Systems 2nd Annual Symposium, Austria."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4510","DOI":"10.1109\/TIP.2019.2906582","article-title":"Encoding Visual Sensitivity by MaxPol Convolution Filters for Image Sharpness Assessment","volume":"28","author":"Hosseini","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Niu, Z., Zhou, M., Wang, L., Gao, X., and Hua, G. (2016, January 27\u201330). Ordinal Regression With Multiple Output CNN for Age Estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.532"},{"key":"ref_27","unstructured":"Gao, Y., and Japkowicz, N. (2009). Evaluation Methods for Ordinal Classification. Advances in Artificial Intelligence, Springer."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Silva, W., Pinto, J.R., and Cardoso, J.S. (2018, January 8\u201313). A Uniform Performance Index for Ordinal Classification with Imbalanced Classes. Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.","DOI":"10.1109\/IJCNN.2018.8489327"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1142\/S0218001411009093","article-title":"Measuring the Performance of Ordinal Classification","volume":"25","author":"Cardoso","year":"2011","journal-title":"Int. J. Pattern Recognit. Artif. Intell."}],"container-title":["Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2227-7390\/10\/6\/980\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:39:00Z","timestamp":1760135940000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2227-7390\/10\/6\/980"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,18]]},"references-count":29,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2022,3]]}},"alternative-id":["math10060980"],"URL":"https:\/\/doi.org\/10.3390\/math10060980","relation":{},"ISSN":["2227-7390"],"issn-type":[{"type":"electronic","value":"2227-7390"}],"subject":[],"published":{"date-parts":[[2022,3,18]]}}}