Abstract
The increasing complexity of convolutional neural networks (CNNs) has greatly improved the accuracy of image classification. However, there are unbalanced visual similarities between image categories, which results in different difficulties in classification. The existing solutions construct hierarchical structures according to image labels and use hierarchical information of categories to improve the performance of the network by constructing tree classifiers, but there is a problem of error transmission. In this paper, a multi-granularity decision fusion method based on category hierarchy is proposed. The two-level hierarchical structure of the image label is constructed according to the traditional algorithm, and the accuracy of image classification is improved through the decision fusion method of coarse and fine granularity, which effectively avoids the inter-level transmission of error. Real public data sets are used for verification. Experimental results show that, compared with the original convolutional neural network, the proposed method achieves higher classification results on CIFAR-10, CIFAR-100, and SVHM data sets.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Huang, G., Liu, Z., Van Der Maaten, L., et al.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708. IEEE, Honolulu, HI, USA (2017)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141. IEEE, Salt Lake City, UT, USA (2018)
Mi, J.-X., Feng, J.: Sharednet: a novel efficient convolutional architecture based on group sharing convolution. In: Huang, D.-S., Bevilacqua, V., Hussain, A. (eds.) Intelligent Computing Theories and Application. LNCS, vol. 12463, pp. 128–139. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60799-9_11
He, Z.: Deep learning in image classification: a survey report. In: 2nd International Conference on Information Technology and Computer Application, pp. 174–177. IEEE, Guangzhou, China (2020)
He, G., Ji, J., Zhang, H., et al.: Feature selection-based hierarchical deep network for image classification. IEEE Access 8, 15436–15447 (2020)
Zhao, T., Zhang, B., He, M., et al.: Embedding visual hierarchy with deep networks for large-scale visual recognition. IEEE Trans. Image Process. 27(10), 4740–4755 (2018)
Zheng, Y., Fan, J., Zhang, J., et al.: Discriminative fast hierarchical learning for multiclass image classification. IEEE Trans. Neural Netw. Learn. Syst. 31(8), 2779–2790 (2019)
Guo, S., Zhao, H.: Hierarchical classification with multi-path selection based on granular computing. Artif. Intell. Rev. 54(3), 2067–2089 (2020). https://doi.org/10.1007/s10462-020-09899-2
Saha, S., Varma, G., Jawahar, C.V.: Class2str: end to end latent hierarchy learning. In: 24th International Conference on Pattern Recognition, pp. 1000–1005. IEEE, Beijing, China (2018)
Wu, Z., Nagarajan, T., Kumar, A., et al.: Blockdrop: dynamic inference paths in residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8817–8826. IEEE, Salt Lake City, UT, USA (2018)
Veit, A., Belongie, S.: Convolutional networks with adaptive inference graphs. Int. J. Comput. Vision 128(3), 730–741 (2019). https://doi.org/10.1007/s11263-019-01190-4
Shen, J., Wang, Y., Xu, P., et al.: Fractional skipping: towards finer-grained dynamic CNN inference. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 5700–5708. AAAI, New York, USA (2020)
Yan, Z., Zhang, H., Piramuthu, R., et al.: HD-CNN: hierarchical deep convolutional neural networks for large scale visual recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2740–2748. IEEE, Boston, USA (2015)
Bilal, A., Jourabloo, A., Ye, M., et al.: Do convolutional neural networks learn class hierarchy? IEEE Trans. Visual Comput. Graph. 24(1), 152–162 (2017)
Wehrmann J., Cerri R., Barros R.: Hierarchical multi-label classification networks. In: International Conference on Machine Learning, pp. 5225–5234. PMLR, Stockholm, Sweden (2018)
Panchenko, I., Khan, A.: On expert-defined versus learned hierarchies for image classification. In: van der Aalst, W.M.P., et al. (eds.) Analysis of Images, Social Networks and Texts. LNCS, vol. 11832, pp. 345–356. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-37334-4_31
Roy, D., Panda, P., Roy, K.: Tree-CNN: a hierarchical deep convolutional neural network for incremental learning. Neural Netw. 121, 148–160 (2020)
Zhao, J., Peng, Y., He, X.: Attribute hierarchy based multi-task learning for fine-grained image classification. Neurocomputing 395, 150–159 (2020)
Zhang, H., Kuang, Z., Peng, X., et al.: Aggregating diverse deep attention networks for large-scale plant species identification. Neurocomputing 378, 283–294 (2020)
Romero, M., Finke, J., Rocha, C.: A top-down supervised learning approach to hierarchical multi-label classification in networks. Appl. Netw. Sci. 7(1), 1–17 (2022)
Liu, Y., Dou, Y., Jin, R., et al.: Hierarchical learning with backtracking algorithm based on the visual confusion label tree for large-scale image classification. Vis. Comput. 38(3), 897–917 (2022)
Zheng, Y., Fan, J., Zhang, J., et al.: Exploiting related and unrelated tasks for hierarchical metric learning and image classification. IEEE Trans. Image Process. 29, 883–896 (2019)
Chen, Z., Du, C., Huang, L., et al.: Improving image classification performance with automatically hierarchical label clustering. In: 24th International Conference on Pattern Recognition, pp. 1863–1868. IEEE, Beijing, China (2018)
Seo, Y., Shin, K.: Hierarchical convolutional neural networks for fashion image classification. Expert Syst. Appl. 116, 328–339 (2019)
Acknowledgments
This work was sponsored by Scientific and Technological Research Program of Chongqing Municipal Education Commission (Grant No. KJQN202100638).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Mi, JX., Huang, KY., Li, N. (2023). A Multi-granularity Decision Fusion Method Based on Category Hierarchy. In: Huang, DS., Premaratne, P., Jin, B., Qu, B., Jo, KH., Hussain, A. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2023. Lecture Notes in Computer Science, vol 14087. Springer, Singapore. https://doi.org/10.1007/978-981-99-4742-3_12
Download citation
DOI: https://doi.org/10.1007/978-981-99-4742-3_12
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4741-6
Online ISBN: 978-981-99-4742-3
eBook Packages: Computer ScienceComputer Science (R0)