{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T06:00:56Z","timestamp":1744783256599,"version":"3.37.3"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,5,13]],"date-time":"2022-05-13T00:00:00Z","timestamp":1652400000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,13]],"date-time":"2022-05-13T00:00:00Z","timestamp":1652400000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"crossref","award":["No. 2019YFB2102100"],"award-info":[{"award-number":["No. 2019YFB2102100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The Science and Technology Development Fund of Macau SAR","award":["File no. 0015\/2019\/AKP"],"award-info":[{"award-number":["File no. 0015\/2019\/AKP"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1007\/s11063-022-10830-9","type":"journal-article","created":{"date-parts":[[2022,5,13]],"date-time":"2022-05-13T21:02:37Z","timestamp":1652475757000},"page":"4735-4749","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["COLAM: Co-Learning of Deep Neural Networks and Soft Labels via Alternating Minimization"],"prefix":"10.1007","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8073-7552","authenticated-orcid":false,"given":"Xingjian","family":"Li","sequence":"first","affiliation":[]},{"given":"Haoyi","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Haozhe","family":"An","sequence":"additional","affiliation":[]},{"given":"Chengzhong","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Dejing","family":"Dou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,5,13]]},"reference":[{"key":"10830_CR1","unstructured":"Bagherinezhad H, Horton M, Rastegari M, Farhadi A (2018) Label refinery: improving imagenet classification through label progression. arXiv:1805.02641"},{"key":"10830_CR2","doi-asserted-by":"crossref","unstructured":"Chorowski J, Jaitly N (2016) Towards better decoding and language model integration in sequence to sequence models. In: INTERSPEECH","DOI":"10.21437\/Interspeech.2017-343"},{"key":"10830_CR3","doi-asserted-by":"crossref","unstructured":"Cimpoi M, Maji S, Vedaldi A (2015) Deep filter banks for texture recognition and segmentation. CVPR, pp 3828\u20133836","DOI":"10.1109\/CVPR.2015.7299007"},{"key":"10830_CR4","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. CVPR, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10830_CR5","doi-asserted-by":"crossref","unstructured":"Graves A, Jaitly N (2014) Towards end-to-end speech recognition with recurrent neural networks. In: ICML","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"10830_CR6","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. CVPR, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"10830_CR7","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. arXiv:1603.05027","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"10830_CR8","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv:1503.02531"},{"key":"10830_CR9","unstructured":"Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov R (2012) Improving neural networks by preventing co-adaptation of feature detectors. arXiv:1207.0580"},{"key":"10830_CR10","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Weinberger KQ (2016) Densely connected convolutional networks. CVPR, pp 2261\u20132269","DOI":"10.1109\/CVPR.2017.243"},{"key":"10830_CR11","unstructured":"Huang Y, Cheng Y, Chen D, Lee H, Ngiam J, Le QV, Chen Z (2018) Gpipe: Efficient training of giant neural networks using pipeline parallelism. arXiv:1811.06965"},{"key":"10830_CR12","unstructured":"J\u00f3zefowicz R, Vinyals O, Schuster M, Shazeer N, Wu Y (2016) Exploring the limits of language modeling. arXiv:1602.02410"},{"key":"10830_CR13","unstructured":"Krizhevsky A (2009) Learning multiple layers of features from tiny images"},{"key":"10830_CR14","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: NIPS"},{"key":"10830_CR15","unstructured":"Lopez-Paz D, Bottou L, Sch\u00f6lkopf B, Vapnik V (2016) Unifying distillation and privileged information. Int Conf Learn Represent (ICLR)"},{"key":"10830_CR16","unstructured":"Maji S, Rahtu E, Kannala J, Blaschko MB, Vedaldi A (2013) Fine-grained visual classification of aircraft. arXiv:1306.5151"},{"key":"10830_CR17","unstructured":"M\u00fcller R, Kornblith S, Hinton GE (2019) When does label smoothing help? CoRR arXiv:1906.02629"},{"key":"10830_CR18","doi-asserted-by":"crossref","unstructured":"Nilsback ME, Zisserman A (2008) Automated flower classification over a large number of classes. ICVGIP, pp 722\u2013729","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"10830_CR19","unstructured":"Pereyra G, Tucker G, Chorowski J, Kaiser L, Hinton GE (2017) Regularizing neural networks by penalizing confident output distributions. arXiv:1701.06548"},{"key":"10830_CR20","doi-asserted-by":"crossref","unstructured":"Real E, Aggarwal A, Huang Y, Le QV (2018) Regularized evolution for image classifier architecture search. In: AAAI","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"10830_CR21","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. CoRR arXiv:1409.1556"},{"key":"10830_CR22","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2014) Going deeper with convolutions. CVPR","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10830_CR23","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: CVPR, pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"10830_CR24","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: NIPS"},{"key":"10830_CR25","unstructured":"Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The caltech-UCSD birds-200-2011 dataset. Tech. Rep. CNS-TR-2011-001, California Institute of Technology"},{"key":"10830_CR26","doi-asserted-by":"crossref","unstructured":"Xie L, Wang J, Wei Z, Wang M, Tian Q (2016) Disturblabel: regularizing cnn on the loss layer. CVPR, pp 4753\u20134762","DOI":"10.1109\/CVPR.2016.514"},{"key":"10830_CR27","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick RB, Doll\u00e1r P, Tu Z, He K (2016) Aggregated residual transformations for deep neural networks. CVPR, pp 5987\u20135995","DOI":"10.1109\/CVPR.2017.634"},{"key":"10830_CR28","doi-asserted-by":"crossref","unstructured":"Yun S, Park J, Lee K, Shin J (2020) Regularizing class-wise predictions via self-knowledge distillation. In: The IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.01389"},{"key":"10830_CR29","doi-asserted-by":"crossref","unstructured":"Zagoruyko S, Komodakis N (2016) Wide residual networks. arXiv:1605.07146","DOI":"10.5244\/C.30.87"},{"key":"10830_CR30","unstructured":"Zeiler MD, Fergus R (2013) Stochastic pooling for regularization of deep convolutional neural networks. CoRR arXiv:1301.3557"},{"key":"10830_CR31","unstructured":"Zhang C, Bengio S, Hardt M, Recht B, Vinyals O (2016) Understanding deep learning requires rethinking generalization. arXiv:1611.03530"},{"key":"10830_CR32","unstructured":"Zhang G, Wang C, Xu B, Grosse RB (2018) Three mechanisms of weight decay regularization. arXiv:1810.12281"},{"key":"10830_CR33","doi-asserted-by":"crossref","unstructured":"Zoph B, Vasudevan V, Shlens J, Le QV (2017) Learning transferable architectures for scalable image recognition. CVPR, pp 8697\u20138710","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10830-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-022-10830-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10830-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,30]],"date-time":"2022-10-30T19:11:00Z","timestamp":1667157060000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-022-10830-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,13]]},"references-count":33,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["10830"],"URL":"https:\/\/doi.org\/10.1007\/s11063-022-10830-9","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2022,5,13]]},"assertion":[{"value":"5 April 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}