{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T16:11:37Z","timestamp":1762272697364,"version":"build-2065373602"},"reference-count":32,"publisher":"Institution of Engineering and Technology (IET)","issue":"3","license":[{"start":{"date-parts":[[2021,3,16]],"date-time":"2021-03-16T00:00:00Z","timestamp":1615852800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Computer Vision"],"published-print":{"date-parts":[[2021,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Image classification is one of the mainstream tasks of computer vision. However, the most existing methods use labels of the same granularity level for training. This leads to ignoring the hierarchy that may help to differentiate different visual objects better. Embedding hierarchical information into the convolutional neural networks (CNNs) can effectively regulate the semantic space and thus reduce the ambiguity of prediction. To this end, a multi\u2010task learning framework, named as Hierarchical Bilinear Convolutional Neural Network (HB\u2010CNN), is developed by seamlessly integrating CNNs with multi\u2010task learning over the hierarchical visual concept structures. Specifically, the labels with a tree structure are used as the supervision to hierarchically train multiple branch networks. In this way, the model can not only learn additional information (e.g. context information) as the coarse\u2010level category features, but also focus the learned fine\u2010level category features on the object properties. To smoothly pass hierarchical conceptual information and encourage feature reuse, a connectivity pattern is proposed to connect features at different levels. Furthermore, a bilinear module is embedded to generalise various orderless texture feature descriptors so that our model can capture more discriminative features. The proposed method is extensively evaluated on the CIFAR\u201010, CIFAR\u2010100, and \u2018Orchid\u2019 Plant image sets. The experimental results show the effectiveness and superiority of our method.<\/jats:p>","DOI":"10.1049\/cvi2.12023","type":"journal-article","created":{"date-parts":[[2021,3,17]],"date-time":"2021-03-17T02:11:40Z","timestamp":1615947100000},"page":"197-207","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Hierarchical bilinear convolutional neural network for image classification"],"prefix":"10.1049","volume":"15","author":[{"given":"Xiang","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information and Technology Northwest University  Shaanxi 710127 China"}]},{"given":"Lei","family":"Tang","sequence":"additional","affiliation":[{"name":"Center of Innovations Xi'an Microelectron Technology Institute  Shaanxi China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-5739","authenticated-orcid":false,"given":"Hangzai","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Information and Technology Northwest University  Shaanxi 710127 China"}]},{"given":"Sheng","family":"Zhong","sequence":"additional","affiliation":[{"name":"Center of Innovations Xi'an Microelectron Technology Institute  Shaanxi China"}]},{"given":"Ziyu","family":"Guan","sequence":"additional","affiliation":[{"name":"School of Information and Technology Northwest University  Shaanxi 710127 China"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Communications and Information Engineering Xi'an University of Posts and Telecommunications  Shaanxi 710061 China"}]},{"given":"Chao","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information and Technology Northwest University  Shaanxi 710127 China"}]},{"given":"Jinye","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Information and Technology Northwest University  Shaanxi 710127 China"}]},{"given":"Jianping","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Computer Science UNC  Charlotte NC 28223 USA"}]}],"member":"265","published-online":{"date-parts":[[2021,3,16]]},"reference":[{"key":"e_1_2_7_2_1","unstructured":"Krizhevsky A. Sutskever I. Hinton G.E.:Imagenet classification with deep convolutional neural networks. In:Proc. Advances in Neural Information Processing Systems Lake Tahoe NV USA pp.1097\u20131105(2012)"},{"volume-title":"Very deep convolutional networks for large\u2010scale image recognition","year":"2014","author":"Simonyan K.","key":"e_1_2_7_3_1"},{"key":"e_1_2_7_4_1","doi-asserted-by":"crossref","unstructured":"Szegedy C. et\u00a0al:Going deeper with convolutions. In:Proc. IEEE Conf. Computer Vision and Pattern Recognition Boston MA pp.1\u20139(2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_7_5_1","doi-asserted-by":"crossref","unstructured":"HeZhang K.X. Ren S. Sun J.:Deep residual learning for image recognition. In:Proc. IEEE Conf. Computer Vision and Pattern Recognition Las Vegas NV USA pp.770\u2013778(2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_7_6_1","doi-asserted-by":"crossref","unstructured":"Ding X. et\u00a0al.:Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks. In:Proc. IEEE Int. Conf. Computer Vision Seoul Korea pp.1911\u20131920(2019)","DOI":"10.1109\/ICCV.2019.00200"},{"key":"e_1_2_7_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0885-2014(98)90005-3"},{"key":"e_1_2_7_8_1","doi-asserted-by":"crossref","unstructured":"Lin T.Y. RoyChowdhury A. Maji S.:Bilinear cnn models for fine\u2010grained visual recognition. In:Proc. IEEE Int. Conf. Computer Vision Santiago Chile pp.1449\u20131457(2015)","DOI":"10.1109\/ICCV.2015.170"},{"volume-title":"B\u2010CNN: Branch convolutional neural network for hierarchical classification","year":"2017","author":"Zhu X.","key":"e_1_2_7_9_1"},{"volume-title":"Bird species categorization using pose normalized deep convolutional nets","year":"2014","author":"Branson S.","key":"e_1_2_7_10_1"},{"key":"e_1_2_7_11_1","doi-asserted-by":"crossref","unstructured":"Wang Y. Morariu V.I. Davis L.S.:Learning a discriminative filter bank within a CNN for fine\u2010grained recognition. In:Proc. IEEE Conf. Computer Vision and Pattern Recognition Salt Lake City UT USA pp.4148\u20134157(2018)","DOI":"10.1109\/CVPR.2018.00436"},{"key":"e_1_2_7_12_1","doi-asserted-by":"crossref","unstructured":"Zheng H. et\u00a0al.:Learning multi\u2010attention convolutional neural network for fine\u2010grained image recognition. In:Proc. IEEE Int. Conf. Computer Vision Venice Italy pp.5209\u20135217(2017)","DOI":"10.1109\/ICCV.2017.557"},{"key":"e_1_2_7_13_1","doi-asserted-by":"crossref","unstructured":"Liu X. et al.:Localising by describing: attribute\u2010guided attention localization for fine\u2010grained recognition. In:Proc. AAAI San Francisco CA USA(2017)","DOI":"10.1609\/aaai.v31i1.11202"},{"key":"e_1_2_7_14_1","unstructured":"Srivastava N. Salakhutdinov R.R.:Discriminative transfer learning with tree\u2010based priors. In:Proc. Advances in Neural Information Processing Systems lake Tahoe NV USA pp.2094\u20132102(2013)"},{"key":"e_1_2_7_15_1","doi-asserted-by":"crossref","unstructured":"Yan Z. et\u00a0al.:HD\u2010CNN: hierarchical deep convolutional neural networks for large scale visual recognition. In:Proc. IEEE Int. Conf. Computer Vision Santiago Chile pp.2740\u20132748(2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"e_1_2_7_16_1","doi-asserted-by":"crossref","unstructured":"Liu Y. et al.:Visual tree convolutional neural network in image classification. In:2018 24th International Conference on Pattern Recognition (ICPR) Beijing China pp.758\u2013763(2018)","DOI":"10.1109\/ICPR.2018.8546126"},{"volume-title":"Multi\u2010scale dense networks for resource efficient image classification","year":"2017","author":"Huang G.","key":"e_1_2_7_17_1"},{"key":"e_1_2_7_18_1","doi-asserted-by":"crossref","unstructured":"Zweig A. Weinshall D.:Exploiting object hierarchy: Combining models from different category levels. In:2007 IEEE 11th International Conference on Computer Vision Rio de Janeiro Brazil pp.1\u20138(2007)","DOI":"10.1109\/ICCV.2007.4409064"},{"key":"e_1_2_7_19_1","unstructured":"Jia Y. et al.:Visual concept learning: Combining machine vision and bayesian generalisation on concept hierarchies. In:Proc. Advances in Neural Information Processing Systems Lake Tahoe NV USA pp.1842\u20131850(2013)"},{"key":"e_1_2_7_20_1","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1500346"},{"key":"e_1_2_7_21_1","doi-asserted-by":"crossref","unstructured":"Deng J. et\u00a0al.:Large\u2010scale object classification using label relation graphs. In:European Conf. on Computer Vision Zurich Switzerland Zurich Switzerland pp.48\u201364(2014)","DOI":"10.1007\/978-3-319-10590-1_4"},{"key":"e_1_2_7_22_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2017.0636"},{"key":"e_1_2_7_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.09.022"},{"key":"e_1_2_7_24_1","doi-asserted-by":"crossref","unstructured":"Dhall A. et al.:Hierarchical image classification using Entailment Cone embeddings. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops pp.836\u2013837(2020)","DOI":"10.1109\/CVPRW50498.2020.00426"},{"key":"e_1_2_7_25_1","doi-asserted-by":"crossref","unstructured":"Chen Ti. et al.:Fine\u2010grained representation learning and recognition by exploiting hierarchical semantic embedding. In:Proceedings of the 26th ACM international conference on Multimedia pp.2023\u20132031(2018).","DOI":"10.1145\/3240508.3240523"},{"key":"e_1_2_7_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2615423"},{"key":"e_1_2_7_27_1","first-page":"3856","article-title":"Dynamic routing between capsules","author":"Sabour S.","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_2_7_28_1","doi-asserted-by":"crossref","unstructured":"Huang G. et al.:Densely connected convolutional networks. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pp.4700\u20134708(2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_7_29_1","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky A.","year":"2009","journal-title":"Tech Report"},{"key":"e_1_2_7_30_1","doi-asserted-by":"crossref","unstructured":"He K et\u00a0al.:Deep residual learning for image recognition. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Las Vegas NV USA. pp.770\u2013778(2016).https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_7_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.09.010"},{"volume-title":"Highway networks","year":"2015","author":"Srivastava R.","key":"e_1_2_7_32_1"},{"key":"e_1_2_7_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.10.007"}],"container-title":["IET Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cvi2.12023","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cvi2.12023","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cvi2.12023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T10:51:08Z","timestamp":1761648668000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cvi2.12023"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,16]]},"references-count":32,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,4]]}},"alternative-id":["10.1049\/cvi2.12023"],"URL":"https:\/\/doi.org\/10.1049\/cvi2.12023","archive":["Portico"],"relation":{},"ISSN":["1751-9632","1751-9640"],"issn-type":[{"type":"print","value":"1751-9632"},{"type":"electronic","value":"1751-9640"}],"subject":[],"published":{"date-parts":[[2021,3,16]]},"assertion":[{"value":"2020-06-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-10-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}