{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T03:56:47Z","timestamp":1775447807397,"version":"3.50.1"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T00:00:00Z","timestamp":1722038400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T00:00:00Z","timestamp":1722038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006595","name":"UEFISCDI","doi-asserted-by":"crossref","award":["PN-III-P2-2.1-PED-2021-0195"],"award-info":[{"award-number":["PN-III-P2-2.1-PED-2021-0195"]}],"id":[{"id":"10.13039\/501100006595","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Most curriculum learning methods require an approach to sort the data samples by difficulty, which is often cumbersome to perform. In this work, we propose a novel curriculum learning approach termed Learning Rate Curriculum (LeRaC), which leverages the use of a different learning rate for each layer of a neural network to create a data-agnostic curriculum during the initial training epochs. More specifically, LeRaC assigns higher learning rates to neural layers closer to the input, gradually decreasing the learning rates as the layers are placed farther away from the input. The learning rates increase at various paces during the first training iterations, until they all reach the same value. From this point on, the neural model is trained as usual. This creates a model-level curriculum learning strategy that does not require sorting the examples by difficulty and is compatible with any neural network, generating higher performance levels regardless of the architecture. We conduct comprehensive experiments on 12 data sets from the computer vision (CIFAR-10, CIFAR-100, Tiny ImageNet, ImageNet-1K, Food-101, UTKFace, PASCAL VOC), language (BoolQ, QNLI, RTE) and audio (ESC-50, CREMA-D) domains, considering various convolutional (ResNet-18, Wide-ResNet-50, DenseNet-121, YOLOv5), recurrent (LSTM) and transformer (CvT, BERT, SepTr) architectures. We compare our approach with the conventional training regime, as well as with Curriculum by Smoothing (CBS), a state-of-the-art data-agnostic curriculum learning approach. Unlike CBS, our performance improvements over the standard training regime are consistent across all data sets and models. Furthermore, we significantly surpass CBS in terms of training time (there is no additional cost over the standard training regime for LeRaC). Our code is freely available at: <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/CroitoruAlin\/LeRaC\">https:\/\/github.com\/CroitoruAlin\/LeRaC<\/jats:ext-link>.<\/jats:p>","DOI":"10.1007\/s11263-024-02186-5","type":"journal-article","created":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T11:02:03Z","timestamp":1722078123000},"page":"291-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Learning Rate Curriculum"],"prefix":"10.1007","volume":"133","author":[{"given":"Florinel-Alin","family":"Croitoru","sequence":"first","affiliation":[]},{"given":"Nicolae-C\u0103t\u0103lin","family":"Ristea","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9301-1950","authenticated-orcid":false,"given":"Radu Tudor","family":"Ionescu","sequence":"additional","affiliation":[]},{"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,27]]},"reference":[{"key":"2186_CR1","unstructured":"Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., et\u00a0al. (2016). Deep speech 2: End-to-end speech recognition in English and Mandarin. In Proceedings of ICML (pp. 173\u2013182)."},{"key":"2186_CR2","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009). Curriculum learning. In Proceedings of ICML (pp. 41\u201348).","DOI":"10.1145\/1553374.1553380"},{"key":"2186_CR3","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., & Van\u00a0Gool, L. (2014). Food-101\u2014Mining discriminative components with random forests. In Proceedings of ECCV (pp. 446\u2013461).","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"2186_CR4","doi-asserted-by":"crossref","unstructured":"Burduja, M., & Ionescu, R.T. (2021). Unsupervised medical image alignment with curriculum learning. In Proceedings of ICIP (pp. 3787\u20133791).","DOI":"10.1109\/ICIP42928.2021.9506067"},{"issue":"4","key":"2186_CR5","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","volume":"5","author":"H Cao","year":"2014","unstructured":"Cao, H., Cooper, D. G., Keutmann, M. K., Gur, R. C., Nenkova, A., & Verma, R. (2014). CREMA-D: Crowd-sourced emotional multimodal actors dataset. IEEE Transactions on Affective Computing, 5(4), 377\u2013390.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"2186_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., & Gupta, A. (2015). Webly supervised learning of convolutional networks. In Proceedings of ICCV (pp. 1431\u20131439).","DOI":"10.1109\/ICCV.2015.168"},{"key":"2186_CR7","unstructured":"Cirik, V., Hovy, E., & Morency, L.P. (2016). Visualizing and understanding curriculum learning for long short-term memory networks. arXiv preprint arXiv:1611.06204."},{"key":"2186_CR8","doi-asserted-by":"crossref","unstructured":"Clark, C., Lee, K., Chang, M.W., Kwiatkowski, T., Collins, M., & Toutanova, K. (2019). BoolQ: Exploring the surprising difficulty of natural yes\/no questions. In Proceedings of NAACL (pp. 2924\u20132936).","DOI":"10.18653\/v1\/N19-1300"},{"key":"2186_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL (pp. 4171\u20134186)."},{"issue":"7","key":"2186_CR10","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1162\/089976698300017197","volume":"10","author":"TG Dietterich","year":"1998","unstructured":"Dietterich, T. G. (1998). Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation, 10(7), 1895\u20131923.","journal-title":"Neural Computation"},{"key":"2186_CR11","doi-asserted-by":"crossref","unstructured":"Dogan, \u00dc., Deshmukh, A. A, Machura, M. B., & Igel, C. (2020). Label-similarity curriculum learning. In Proceedings of ECCV (pp. 174\u2013190).","DOI":"10.1007\/978-3-030-58526-6_11"},{"issue":"2","key":"2186_CR12","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The PASCAL visual object classes (VOC) challenge. Intenational Journal of Computer Vision, 88(2), 303\u2013338.","journal-title":"Intenational Journal of Computer Vision"},{"key":"2186_CR13","doi-asserted-by":"crossref","unstructured":"Fan, Y., He, R., Liang, J., & Hu, B. G. (2017). Self-paced learning: An implicit regularization perspective. In Proceedings of AAAI (pp. 1877\u20131883).","DOI":"10.1609\/aaai.v31i1.10809"},{"key":"2186_CR14","unstructured":"Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In Proceedings of AISTATS (pp. 249\u2013256)."},{"issue":"7","key":"2186_CR15","doi-asserted-by":"publisher","first-page":"3249","DOI":"10.1109\/TIP.2016.2563981","volume":"25","author":"C Gong","year":"2016","unstructured":"Gong, C., Tao, D., Maybank, S. J., Liu, W., Kang, G., & Yang, J. (2016). Multi-modal curriculum learning for semi-supervised image classification. IEEE Transactions on Image Processing, 25(7), 3249\u20133260.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"2","key":"2186_CR16","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1109\/TEVC.2018.2850769","volume":"23","author":"M Gong","year":"2019","unstructured":"Gong, M., Li, H., Meng, D., Miao, Q., & Liu, J. (2019). Decomposition-based evolutionary multiobjective optimization to self-paced learning. IEEE Transactions on Evolutionary Computation, 23(2), 288\u2013302.","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"2186_CR17","unstructured":"Gotmare, A., Keskar, N. S., Xiong, C., & Socher, R. (2019). A closer look at deep learning heuristics: Learning rate restarts, warmup and distillation. In Proceedings of ICLR."},{"key":"2186_CR18","doi-asserted-by":"crossref","unstructured":"Gui, L., Baltru\u0161aitis, T., & Morency, L.P. (2017). Curriculum learning for facial expression recognition. In Proceedings of FG (pp. 505\u2013511).","DOI":"10.1109\/FG.2017.68"},{"key":"2186_CR19","unstructured":"Hacohen, G., & Weinshall, D. (2019). On the power of curriculum learning in training deep networks. In Proceedings of ICML (pp. 2535\u20132544)."},{"key":"2186_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of CVPR (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"2186_CR21","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computing, 9(8), 1735\u20131780.","journal-title":"Neural Computing"},{"key":"2186_CR22","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of CVPR (pp. 2261\u20132269).","DOI":"10.1109\/CVPR.2017.243"},{"key":"2186_CR23","doi-asserted-by":"crossref","unstructured":"Ionescu, R.T., Alexe, B., Leordeanu, M., Popescu, M., Papadopoulos, D. P., & Ferrari, V. (2016). How hard can it be? Estimating the difficulty of visual search in an image. In Proceedings of CVPR (pp. 2157\u20132166).","DOI":"10.1109\/CVPR.2016.237"},{"key":"2186_CR24","unstructured":"Jiang, L., Meng, D., Yu, S.I., Lan, Z., Shan, S., & Hauptmann, A. G. (2014). Self-paced learning with diversity. In Proceedings of NIPS (pp. 2078\u20132086)."},{"key":"2186_CR25","doi-asserted-by":"crossref","unstructured":"Jiang, L., Meng, D., Zhao, Q., Shan, S., & Hauptmann, A. G. (2015). Self-paced curriculum learning. In Proceedings of AAAI (pp. 2694\u20132700).","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"2186_CR26","unstructured":"Jiang, L., Zhou, Z., Leung, T., Li, L.J,. & Fei-Fei, L. (2018). MentorNet: learning data-driven curriculum for very deep neural networks on corrupted labels. In Proceedings of ICML (pp. 2304\u20132313)."},{"key":"2186_CR27","doi-asserted-by":"crossref","unstructured":"Jim\u00e9nez-S\u00e1nchez, A., Mateus, D., Kirchhoff, S., Kirchhoff, C., Biberthaler, P., Navab, N. et\u00a0al. (2019). Medical-based deep curriculum learning for improved fracture classification. In Proceedings of MICCAI (pp. 694\u2013702).","DOI":"10.1007\/978-3-030-32226-7_77"},{"key":"2186_CR28","unstructured":"Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., NanoCode012, Kwon Y, et\u00a0al. (2022). ultralytics\/yolov5: v7.0\u2014YOLOv5 SOTA Realtime Instance Segmentation. Zenodo."},{"key":"2186_CR29","unstructured":"Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2018). Progressive growing of GANs for improved quality, stability, and variation. In Proceedings of ICLR."},{"key":"2186_CR30","doi-asserted-by":"crossref","unstructured":"Khan, M., Hamila, R., & Menouar, H. (2023a). CLIP: Train faster with less data. In Proceedings of BigComp (pp. 34\u201339).","DOI":"10.1109\/BigComp57234.2023.00014"},{"key":"2186_CR31","doi-asserted-by":"crossref","unstructured":"Khan, M. A., Menouar, H., & Hamila, R. (2023b). LCDnet: A lightweight crowd density estimation model for real-time video surveillance. Journal of Real-Time Image Processing, 20(2), 29.","DOI":"10.1007\/s11554-023-01286-8"},{"key":"2186_CR32","doi-asserted-by":"crossref","unstructured":"Khan, M.A., Menouar, H., & Hamila, R. (2024). Curriculum for crowd counting\u2014Is it worthy? In Proceedings of VISAPP (pp. 583\u2013590).","DOI":"10.5220\/0012414700003660"},{"key":"2186_CR33","unstructured":"Kingma, D. P., & Ba, J. L. (2015). Adam: A method for stochastic gradient descent. In Proceedings of ICLR."},{"key":"2186_CR34","doi-asserted-by":"crossref","unstructured":"Kocmi, T., & Bojar, O. (2017). Curriculum learning and minibatch bucketing in neural machine translation. In Proceedings of RANLP (pp. 379\u2013386).","DOI":"10.26615\/978-954-452-049-6_050"},{"key":"2186_CR35","volume-title":"Learning multiple layers of features from tiny images","author":"A Krizhevsky","year":"2009","unstructured":"Krizhevsky, A. (2009). Learning multiple layers of features from tiny images. University of Toronto."},{"key":"2186_CR36","unstructured":"Kumar, M., Packer, B., & Koller, D. (2010). Self-paced learning for latent variable models. In Proceedings of NIPS (Vol. 23, pp. 1189\u20131197)."},{"key":"2186_CR37","doi-asserted-by":"crossref","unstructured":"Li, H., Gong, M., Meng, D., & Miao, Q. (2016). Multi-objective self-paced learning. In Proceedings of AAAI (pp. 1802\u20131808).","DOI":"10.1609\/aaai.v30i1.10255"},{"key":"2186_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., et\u00a0al. (2014). Microsoft COCO: Common objects in context. In Proceedings of ECCV (pp. 740\u2013755).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2186_CR39","doi-asserted-by":"crossref","unstructured":"Liu, C., He, S., Liu, K., & Zhao, J. (2018). Curriculum learning for natural answer generation. In Proceedings of IJCAI (pp. 4223\u20134229).","DOI":"10.24963\/ijcai.2018\/587"},{"key":"2186_CR40","unstructured":"Loshchilov, I., & Hutter, F. (2019). Decoupled weight decay regularization. In Proceedings of ICLR."},{"key":"2186_CR41","unstructured":"Ma, F., Meng, D., Xie, Q., Li, Z., & Dong, X. (2017). Self-paced co-training. In Proceedings of ICML (Vol. 70, pp. 2275\u20132284)."},{"key":"2186_CR42","volume-title":"Machine learning","author":"TM Mitchell","year":"1997","unstructured":"Mitchell, T. M. (1997). Machine learning. New York: McGraw-Hill."},{"key":"2186_CR43","doi-asserted-by":"crossref","unstructured":"Park, D. S., Chan, W., Zhang, Y., Chiu, C. C., Zoph, B., Cubuk, E. D., et\u00a0al. (2019). SpecAugment: A simple data augmentation method for automatic speech recognition. In Proceedings of INTERSPEECH (pp. 2613\u20132617).","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"2186_CR44","doi-asserted-by":"crossref","unstructured":"Pentina, A., Sharmanska, V., & Lampert, C.H. (2015). Curriculum Learning of Multiple Tasks. In Proceedings of CVPR (pp. 5492\u20135500).","DOI":"10.1109\/CVPR.2015.7299188"},{"key":"2186_CR45","doi-asserted-by":"crossref","unstructured":"Piczak, K.J. (2015). ESC: Dataset for environmental sound classification. In Proceedings of ACMMM (pp. 1015\u20131018).","DOI":"10.1145\/2733373.2806390"},{"key":"2186_CR46","doi-asserted-by":"crossref","unstructured":"Platanios, E.A., Stretcu, O., Neubig, G., Poczos, B., & Mitchell, T. (2019). Competence-based curriculum learning for neural machine translation. In Proceedings of NAACL (pp. 1162\u20131172).","DOI":"10.18653\/v1\/N19-1119"},{"key":"2186_CR47","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016). SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of EMNLP (pp. 2383\u20132392).","DOI":"10.18653\/v1\/D16-1264"},{"key":"2186_CR48","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1109\/TASLP.2017.2765832","volume":"26","author":"S Ranjan","year":"2018","unstructured":"Ranjan, S., & Hansen, J. H. L. (2018). Curriculum learning based approaches for noise robust speaker recognition. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 26, 197\u2013210.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"2186_CR49","doi-asserted-by":"crossref","unstructured":"Ristea, N. C., & Ionescu, R. T. (2021). Self-paced ensemble learning for speech and audio classification. In Proceedings of INTERSPEECH (pp. 2836\u20132840).","DOI":"10.21437\/Interspeech.2021-155"},{"key":"2186_CR50","doi-asserted-by":"crossref","unstructured":"Ristea, N.C., Ionescu, R. T., & Khan, F. S. (2022). SepTr: Separable transformer for audio spectrogram processing. In Proceedings of INTERSPEECH (pp. 4103\u20134107).","DOI":"10.21437\/Interspeech.2022-249"},{"issue":"3","key":"2186_CR51","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., et al. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"2186_CR52","doi-asserted-by":"crossref","unstructured":"Shi, M., & Ferrari, V. (2016). Weakly supervised object localization using size estimates. In Proceedings of ECCV (pp. 105\u2013121).","DOI":"10.1007\/978-3-319-46454-1_7"},{"key":"2186_CR53","doi-asserted-by":"crossref","unstructured":"Singh, B., De, S., Zhang, Y., Goldstein, T., & Taylor, G. (2015). Layer-specific adaptive learning rates for deep networks. In Proceedings of ICMLA (pp. 364\u2013368).","DOI":"10.1109\/ICMLA.2015.113"},{"key":"2186_CR54","unstructured":"Sinha, S., Garg, A., & Larochelle, H. (2020). Curriculum by smoothing. In Proceedings of NeurIPS (pp. 21653\u201321664)."},{"key":"2186_CR55","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.cviu.2021.103166","volume":"204","author":"P Soviany","year":"2021","unstructured":"Soviany, P., Ionescu, R. T., Rota, P., & Sebe, N. (2021). Curriculum self-paced learning for cross-domain object detection. Computer Vision and Image Understanding., 204, 103\u2013166.","journal-title":"Computer Vision and Image Understanding."},{"issue":"6","key":"2186_CR56","doi-asserted-by":"publisher","first-page":"1526","DOI":"10.1007\/s11263-022-01611-x","volume":"130","author":"P Soviany","year":"2022","unstructured":"Soviany, P., Ionescu, R. T., Rota, P., & Sebe, N. (2022). Curriculum learning: A survey. International Journal of Computer Vision, 130(6), 1526\u20131565.","journal-title":"International Journal of Computer Vision"},{"key":"2186_CR57","unstructured":"Spitkovsky, V.I., Alshawi, H., & Jurafsky, D. (2009). Baby Steps: How \u201cLess is More\u201d in unsupervised dependency parsing. In Proceedings of NIPS."},{"key":"2186_CR58","doi-asserted-by":"crossref","unstructured":"Tay, Y., Wang, S., Luu, A.T., Fu, J., Phan, M.C., Yuan, X. et\u00a0al. (2019). Simple and effective curriculum pointer-generator networks for reading comprehension over long narratives. In Proceedings of ACL (pp. 4922\u20134931).","DOI":"10.18653\/v1\/P19-1486"},{"key":"2186_CR59","first-page":"3266","volume":"32","author":"A Wang","year":"2019","unstructured":"Wang, A., Pruksachatkun, Y., Nangia, N., Singh, A., Michael, J., Hill, F., et al. (2019). SuperGLUE: A stickier benchmark for general-purpose language understanding systems. Proceedings of NeurIPS, 32, 3266\u20133280.","journal-title":"Proceedings of NeurIPS"},{"key":"2186_CR60","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. R. (2019). GLUE: A multi-task benchmark and analysis platform for natural language understanding. In Proceedings of ICLR.","DOI":"10.18653\/v1\/W18-5446"},{"key":"2186_CR61","doi-asserted-by":"crossref","unstructured":"Wang, C. Y., Liao, H. Y. M., Wu, Y. H., Chen, P. Y., Hsieh, J. W., & Yeh, I. H. (2020). CSPNet: A new backbone that can enhance learning capability of CNN. In Proceedings of CVPRW (pp. 390\u2013391).","DOI":"10.1109\/CVPRW50498.2020.00203"},{"issue":"9","key":"2186_CR62","doi-asserted-by":"crossref","first-page":"4555","DOI":"10.1109\/TPAMI.2021.3072422","volume":"44","author":"X Wang","year":"2022","unstructured":"Wang, X., Chen, Y., & Zhu, W. (2022). A survey on curriculum learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(9), 4555\u20134576.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2186_CR63","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yue, Y., Lu, R., Liu, T., Zhong, Z., Song, S., et\u00a0al. (2023). EfficientTrain: Exploring generalized curriculum learning for training visual backbones. In Proceedings of ICCV (pp. 5852\u20135864).","DOI":"10.1109\/ICCV51070.2023.00538"},{"key":"2186_CR64","doi-asserted-by":"crossref","unstructured":"Wei, J., Suriawinata, A., Ren, B., Liu, X., Lisovsky, M., Vaickus, L, et\u00a0al. (2021). Learn like a pathologist: Curriculum learning by annotator agreement for histopathology image classification. In Proceedings of WACV (pp. 2472\u20132482).","DOI":"10.1109\/WACV48630.2021.00252"},{"key":"2186_CR65","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., et\u00a0al. (2021). CvT: Introducing convolutions to vision transformers. In Proceedings of ICCV (pp. 22\u201331).","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"2186_CR66","unstructured":"Wu, L., Tian, F., Xia, Y., Fan, Y., Qin, T., Jian-Huang, L., et al. (2018). Learning to teach with dynamic loss functions. In: Proceedings of NeurIPS (Vol. 31, pp. 6467\u20136478)."},{"key":"2186_CR67","unstructured":"You, Y., Gitman, I., & Ginsburg, B. (2017). Large batch training of convolutional networks. arXiv preprint arXiv:1708.03888."},{"key":"2186_CR68","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., & Komodakis, N. (2016). Wide residual networks. arXiv preprint arXiv:1605.07146.","DOI":"10.5244\/C.30.87"},{"issue":"10","key":"2186_CR69","doi-asserted-by":"publisher","first-page":"2171","DOI":"10.3390\/app9102171","volume":"9","author":"M Zhang","year":"2019","unstructured":"Zhang, M., Yu, Z., Wang, H., Qin, H., Zhao, W., & Liu, Y. (2019). Automatic digital modulation classification based on curriculum learning. Applied Sciences, 9(10), 2171.","journal-title":"Applied Sciences"},{"key":"2186_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, W., Wei, W., Wang, W., Jin, L., & Cao, Z. (2021). Reducing BERT computation by padding removal and curriculum learning. In Proceedings of ISPASS (pp. 90\u201392).","DOI":"10.1109\/ISPASS51385.2021.00025"},{"key":"2186_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Song, Y., & Qi, H. (2017). Age progression\/regression by conditional adversarial autoencoder. In Proceedings of CVPR (pp. 5810\u20135818).","DOI":"10.1109\/CVPR.2017.463"},{"key":"2186_CR72","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1016\/j.patcog.2017.10.005","volume":"76","author":"S Zhou","year":"2018","unstructured":"Zhou, S., Wang, J., Meng, D., Xin, X., Li, Y., Gong, Y., et al. (2018). Deep self-paced learning for person re-identification. Pattern Recognition, 76, 739\u2013751.","journal-title":"Pattern Recognition"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02186-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02186-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02186-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T06:12:37Z","timestamp":1736230357000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02186-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,27]]},"references-count":72,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["2186"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02186-5","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,27]]},"assertion":[{"value":"20 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}