Hierarchical bilinear convolutional neural network for image classification

Xiang Zhang, Lei Tang, Hangzai Luo, Sheng Zhong, Ziyu Guan, Long Chen, Chao Zhao, Jinye Peng, Jianping Fan
<span title="2021-03-16">2021</span> <i title="Institution of Engineering and Technology (IET)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/j7d2hucrlnfzzecpjzw46furp4" style="color: black;">IET Computer Vision</a> </i> &nbsp;
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-task learning framework, named as
more &raquo; ... Bilinear Convolutional Neural Network (HB-CNN), is developed by seamlessly integrating CNNs with multitask 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-level category features, but also focus the learned fine-level 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-10, CIFAR-100, and 'Orchid' Plant image sets. The experimental results show the effectiveness and superiority of our method. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. Orchid Brasiliorchis Brasiliorchis chrysantha, Brasiliorchis gracilis, Brasiliorchis marginata, Brasiliorchis phoenicanthera, Brasiliorchis picta, Brasiliorchis porphyrostele, Brasiliorchis schunkeana, Brasiliorchis ubatubana Orchid Brassavola Brassavola acaulis, Brassavola ceboletta, Brassavola cucullata, Brassavola flagellaris, Brassavola nodosa, Brassavola perrinii, Brassavola subulifolia, Brassavola tuberculata Orchid Brassia Brassia arachnoidea, Brassia arcuigera, Brassia aurantiaca, Brassia caudata, Brassia chloroleuca, Brassia keiliana, Brassia maculata, Brassia verrucoda Orchid Calochilus
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1049/cvi2.12023">doi:10.1049/cvi2.12023</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/apr3ebtwdreohivpdol6um72ai">fatcat:apr3ebtwdreohivpdol6um72ai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210715064757/https://ietresearch.onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cvi2.12023" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/36/8a/368a97dc9bcce8ec7ed7b56491bf1163d426b356.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1049/cvi2.12023"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>