{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T20:44:43Z","timestamp":1789764283783,"version":"4.0.1"},"reference-count":34,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2023,4,1]]},"DOI":"10.1587\/transinf.2022edp7200","type":"journal-article","created":{"date-parts":[[2023,3,31]],"date-time":"2023-03-31T22:27:53Z","timestamp":1680301673000},"page":"523-537","source":"Crossref","is-referenced-by-count":1,"title":["CAMRI Loss: Improving the Recall of a Specific Class without Sacrificing Accuracy"],"prefix":"10.1587","volume":"E106.D","author":[{"given":"Daiki","family":"NISHIYAMA","sequence":"first","affiliation":[{"name":"Master's Program in Computer Science, Degree Programs in Systems and Information Engineering, Graduate School of Science and Technology, University of Tsukuba"},{"name":"RIKEN Center for Advanced Intelligence Project"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuto","family":"FUKUCHI","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project"},{"name":"Department of Computer Science, Faculty of Engineering, Information and Systems, University of Tsukuba"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youhei","family":"AKIMOTO","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project"},{"name":"Department of Computer Science, Faculty of Engineering, Information and Systems, University of Tsukuba"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"SAKUMA","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project"},{"name":"Department of Computer Science, Faculty of Engineering, Information and Systems, University of Tsukuba"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] Y. LeCun, L.e.o. Bottou, Y. Bengio, and P. Haffner, \u201cGradient-based learning applied to document recognition,\u201d Proc. IEEE, vol.86, no.11, pp.2278-2324, Nov. 1998. 10.1109\/5.726791","DOI":"10.1109\/5.726791"},{"key":"2","unstructured":"[2] A. Krizhevsky, I. Sutskever, and G.E. Hinton, \u201cImagenet classification with deep convolutional neural networks,\u201d Advances in Neural Information Processing Systems, vol.25, 2012."},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] Y. LeCun, Y. Bengio, and G. Hinton, \u201cDeep learning,\u201d nature, vol.521, no.7553, pp.436-444, May 2015. 10.1038\/nature14539","DOI":"10.1038\/nature14539"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] E. Yurtsever, J. Lambert, A. Carballo, and K. Takeda, \u201cA survey of autonomous driving: Common practices and emerging technologies,\u201d IEEE Access, vol.8, pp.58443-58469, 2020. 10.1109\/ACCESS.2020.2983149","DOI":"10.1109\/ACCESS.2020.2983149"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] M. Bakator and D. Radosav, \u201cDeep learning and medical diagnosis: A review of literature,\u201d Multimodal Technologies and Interaction, vol.2, no.3, p.47, Aug. 2018. 10.3390\/mti2030047","DOI":"10.3390\/mti2030047"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] P. Saranya and P. Asha, \u201cSurvey on big data analytics in health care,\u201d 2019 Int. Conf. Smart Systems and Inventive Technology (ICSSIT), pp.46-51, IEEE, 2019. 10.1109\/ICSSIT46314.2019.8987882","DOI":"10.1109\/ICSSIT46314.2019.8987882"},{"key":"7","unstructured":"[7] D.D. Margineantu and T.G. Dietterich, \u201cBootstrap methods for the cost-sensitive evaluation of classifiers,\u201d Int. Conf. Mach. Learn., pp.583-590, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, June 2000."},{"key":"8","unstructured":"[8] C. Elkan, \u201cThe foundations of cost-sensitive learning,\u201d Proc. 17th International Joint Conference on Artificial Intelligence, vol.2, pp.973-978, Aug. 2001."},{"key":"9","unstructured":"[9] M. Kukar and I. Kononenko, \u201cCost-sensitive learning with neural networks,\u201d 13th European Conference on Artificial Intelligence, pp.445-449, 1998."},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] S. Panchapagesan, M. Sun, A. Khare, S. Matsoukas, A. Mandal, B. Hoffmeister, and S. Vitaladevuni, \u201cMulti-task learning and weighted cross-entropy for dnn-based keyword spotting,\u201d Interspeech, pp.760-764, 2016. 10.21437\/Interspeech.2016-1485","DOI":"10.21437\/Interspeech.2016-1485"},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] Y.S. Aurelio, G.M. de Almeida, C.L. de Castro, and A.P. Braga, \u201cLearning from imbalanced data sets with weighted cross-entropy function,\u201d Neural Process. Lett., vol.50, no.2, pp.1937-1949, Jan. 2019. 10.1007\/s11063-018-09977-1","DOI":"10.1007\/s11063-018-09977-1"},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] Y. Ho and S. Wookey, \u201cThe real-world-weight cross-entropy loss function: Modeling the costs of mislabeling,\u201d IEEE Access, vol.8, pp.4806-4813, 2019. 10.1109\/ACCESS.2019.2962617","DOI":"10.1109\/ACCESS.2019.2962617"},{"key":"13","unstructured":"[13] C. Frogner, C. Zhang, H. Mobahi, M. Araya, and T.A. Poggio, \u201cLearning with a wasserstein loss,\u201d Advances in Neural Information Processing Systems, pp.2053-2061, Dec. 2015."},{"key":"14","unstructured":"[14] W. Liu, Y. Wen, Z. Yu, and M. Yang, \u201cLarge-margin softmax loss for convolutional neural networks,\u201d Int. Conf. Mach. Learn., pp.507-516, PMLR, June 2016."},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] W. Liu, Y. Wen, Z. Yu, M. Li, B. Raj, and L. Song, \u201cSphereface: Deep hypersphere embedding for face recognition,\u201d Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp.212-220, 2017. 10.1109\/CVPR.2017.713","DOI":"10.1109\/CVPR.2017.713"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] X. Liang, X. Wang, Z. Lei, S. Liao, and S.Z. Li, \u201cSoft-margin softmax for deep classification,\u201d Int. Conf. Neural Information Processing, pp.413-421, Springer, Oct. 2017. 10.1007\/978-3-319-70096-0_43","DOI":"10.1007\/978-3-319-70096-0_43"},{"key":"17","doi-asserted-by":"publisher","unstructured":"[17] F. Wang, J. Cheng, W. Liu, and H. Liu, \u201cAdditive margin softmax for face verification,\u201d IEEE Signal Process. Lett., vol.25, no.7, pp.926-930, July 2018. 10.1109\/LSP.2018.2822810","DOI":"10.1109\/LSP.2018.2822810"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] H. Wang, Y. Wang, Z. Zhou, X. Ji, D. Gong, J. Zhou, Z. Li, and W. Liu, \u201cCosface: Large margin cosine loss for deep face recognition,\u201d Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit., pp.5265-5274, 2018. 10.1109\/CVPR.2018.00552","DOI":"10.1109\/CVPR.2018.00552"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] J. Deng, J. Guo, N. Xue, and S. Zafeiriou, \u201cArcface: Additive angular margin loss for deep face recognition,\u201d Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit., pp.4690-4699, 2019. 10.1109\/CVPR.2019.00482","DOI":"10.1109\/CVPR.2019.00482"},{"key":"20","unstructured":"[20] A. Zhai and H.Y. Wu, \u201cClassification is a strong baseline for deep metric learning,\u201d arXiv preprint arXiv:1811.12649, 2018. 10.48550\/arXiv.1811.12649"},{"key":"21","unstructured":"[21] R. Ranjan, C.D. Castillo, and R. Chellappa, \u201cL2-constrained softmax loss for discriminative face verification,\u201d arXiv preprint arXiv:1703.09507, 2017. 10.48550\/arXiv.1703.09507"},{"key":"22","doi-asserted-by":"publisher","unstructured":"[22] A. Torralba, R. Fergus, and W.T. Freeman, \u201c80 million tiny images: A large data set for nonparametric object and scene recognition,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.30, no.11, pp.1958-1970, Nov. 2008. 10.1109\/TPAMI.2008.128","DOI":"10.1109\/TPAMI.2008.128"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel, \u201cThe German traffic sign recognition benchmark: A multi-class classification competition,\u201d IEEE International Joint Conference on Neural Netw., pp.1453-1460, 2011. 10.1109\/IJCNN.2011.6033395","DOI":"10.1109\/IJCNN.2011.6033395"},{"key":"24","doi-asserted-by":"publisher","unstructured":"[24] Y. Xian, C.H. Lampert, B. Schiele, and Z. Akata, \u201cZero-shot learning \u2014 a comprehensive evaluation of the good, the bad and the ugly,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.41, no.9, pp.2251-2265, Sept. 2019. 10.1109\/TPAMI.2018.2857768","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"25","unstructured":"[25] A. Krizhevsky, \u201cLearning multiple layers of features from tiny images,\u201d Technical Report, University of Tront, 2009."},{"key":"26","unstructured":"[26] M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G.S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Jozefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Mane, R. Monga, S. Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Viegas, O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu, and X. Zheng, \u201cTensorflow: Large-scale machine learning on heterogeneous distributed systems,\u201d arXiv preprint arXiv:1603.04467, 2016. 10.48550\/arXiv.1603.04467"},{"key":"27","unstructured":"[27] S. Ioffe and C. Szegedy, \u201cBatch normalization: Accelerating deep network training by reducing internal covariate shift,\u201d Int. Conf. Mach. Learn., pp.448-456, PMLR, July 2015."},{"key":"28","unstructured":"[28] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, \u201cDropout: a simple way to prevent neural networks from overfitting,\u201d J. Mach. Learn Res., vol.15, no.1, pp.1929-1958, 2014."},{"key":"29","unstructured":"[29] M. Lin, Q. Chen, and S. Yan, \u201cNetwork in network,\u201d arXiv preprint arXiv:1312.4400, 2013. 10.48550\/arXiv.1312.4400"},{"key":"30","unstructured":"[30] V. Nair and G.E. Hinton, \u201cRectified linear units improve restricted boltzmann machines,\u201d Int. Conf. Mach. Learn., pp.807-814, June 2010."},{"key":"31","unstructured":"[31] D.P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d arXiv preprint arXiv:1412.6980, 2014. 10.48550\/arXiv.1412.6980"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, \u201cA fast and elitist multiobjective genetic algorithm: Nsga-ii,\u201d IEEE Trans. Evol. Comput., vol.6, no.2, pp.182-197, April 2002. 10.1109\/4235.996017","DOI":"10.1109\/4235.996017"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, \u201cOptuna: A next-generation hyperparameter optimization framework,\u201d Proc. 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.2623-2631, July 2019. 10.1145\/3292500.3330701","DOI":"10.1145\/3292500.3330701"},{"key":"34","unstructured":"[34] M. Tan and Q. Le, \u201cEfficientnet: Rethinking model scaling for convolutional neural networks,\u201d Int. Conf. Mach. Learn., pp.6105-6114, PMLR, 2019."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/4\/E106.D_2022EDP7200\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T04:55:43Z","timestamp":1715316943000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/4\/E106.D_2022EDP7200\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,1]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2022edp7200","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,1]]},"article-number":"2022EDP7200"}}