Abstract
With the development of deep learning techniques, multi-label image classification tasks have achieved good performance. Recently, graph convolutional network has been proved to be an effective way to explore the labels dependencies. However, due to the complexity of label semantic relations, the static dependencies obtained by existing methods cannot consider the overall characteristics of an image and accurately locate the target region. Therefore, we propose the Multi-scale Global-local Semantic Graph Network (MGSGN) for multi-label image classification, which mainly includes three important parts. First, the multi-scale feature reconstruction aggregates complementary information at different levels in CNN through cross-layer attention, which can effectively identify target categories of different sizes. We then design a channel dual-branch cross-attention module to explore the correlation between global information and local features in multi-scale features, which using the way of adaptive cross-fusion to locate the target area more accurately. Moreover, we propose the multi-perspective weighted cosine measure in multi-perspective dynamic semantic representation module to construct content-based label dependencies for each image to dynamically construct a semantic relationship graph. Extensive experiments on the two public datasets have verified that the classification performance of our model is better than many state-of-the-art methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Boutell, M.R., Luo, J., Shen, X., Brown, C.M.: Learning multi-label scene classification. Pattern Recogn. 37(9), 1757–1771 (2004)
Chen, S.F., Chen, Y.C., Yeh, C.K., Wang, Y.C.: Order-free RNN with visual attention for multi-label classification. In: Proceedings of the 32th AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Chen, S., Li, Z., Tang, Z.: Relation R-CNN: a graph based relation-aware network for object detection. IEEE Signal Process. Lett. 27, 1680–1684 (2020)
Chen, T., Lin, L., Chen, R., Hui, X., Wu, H.: Knowledge-guided multi-label few-shot learning for general image recognition. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1371–1384 (2020)
Chen, T., Wang, Z., Li, G., Lin, L.: Recurrent attentional reinforcement learning for multi-label image recognition. In: Proceedings of the 32th AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Chen, T., Xu, M., Hui, X., Wu, H., Lin, L.: Learning semantic-specific graph representation for multi-label image recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 522–531 (2019)
Chen, Y., Zou, C., Chen, J.: Label-aware graph representation learning for multi-label image classification. Neurocomputing 492, 50–61 (2022)
Chen, Z.M., Wei, X.S., Wang, P., Guo, Y.: Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5177–5186 (2019)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111, 98–136 (2015)
Gao, B.B., Zhou, H.Y.: Learning to discover multi-class attentional regions for multi-label image recognition. IEEE Trans. Image Process. 30, 5920–5932 (2021)
Gao, P., et al.: Dynamic fusion with intra-and inter-modality attention flow for visual question answering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6639–6648 (2019)
Ge, Z., Mahapatra, D., Sedai, S., Garnavi, R., Chakravorty, R.: Chest X-rays classification: a multi-label and fine-grained problem. arXiv preprint arXiv:1807.07247 (2018)
Guo, H., Zheng, K., Fan, X., Yu, H., Wang, S.: Visual attention consistency under image transforms for multi-label image classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 729–739 (2019)
Hassanin, M., Radwan, I., Khan, S., Tahtali, M.: Learning discriminative representations for multi-label image recognition. J. Vis. Commun. Image Represent. 83, 103448 (2022)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hu, H., Zhou, G.T., Deng, Z., Liao, Z., Mori, G.: Learning structured inference neural networks with label relations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2960–2968 (2016)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Lanchantin, J., Wang, T., Ordonez, V., Qi, Y.: General multi-label image classification with transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16478–16488 (2021)
Li, Q., Peng, X., Qiao, Y., Peng, Q.: Learning category correlations for multi-label image recognition with graph networks. arXiv preprint arXiv:1909.13005 (2019)
Li, X., Zhao, F., Guo, Y.: Multi-label image classification with a probabilistic label enhancement model. In: Proceedings of the 30th Conference on Uncertainty in Artificial Intelligence, vol. 1, pp. 1–10 (2014)
Li, Y., Huang, C., Loy, C.C., Tang, X.: Human attribute recognition by deep hierarchical contexts. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 684–700. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_41
Li, Z., Lin, L., Zhang, C., Ma, H., Zhao, W., Shi, Z.: A semi-supervised learning approach based on adaptive weighted fusion for automatic image annotation. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 17(1), 1–23 (2021)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Maas, A.L., Hannun, A.Y., Ng, A.Y., et al.: Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the 30th International Conference on Machine Learning, Atlanta, Georgia, USA, vol. 30, p. 3 (2013)
Paszke, A., et al.: Automatic differentiation in pytorch (2017)
Wang, J., Yang, Y., Mao, J., Huang, Z., Huang, C., Xu, W.: CNN-RNN: a unified framework for multi-label image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2285–2294 (2016)
Wang, Y., et al.: Multi-label classification with label graph superimposing. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence, vol. 34, pp. 12265–12272 (2020)
Wang, Z., Fang, Z., Li, D., Yang, H., Du, W.: Semantic supplementary network with prior information for multi-label image classification. IEEE Trans. Circuits Syst. Video Technol. 32(4), 1848–1859 (2021)
Wang, Z., Chen, T., Li, G., Xu, R., Lin, L.: Multi-label image recognition by recurrently discovering attentional regions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 464–472 (2017)
Xian, T., Li, Z., Tang, Z., Ma, H.: Adaptive path selection for dynamic image captioning. IEEE Trans. Circuits Syst. Video Technol. 32(9), 5762–5775 (2022)
Ye, J., He, J., Peng, X., Wu, W., Qiao, Yu.: Attention-driven dynamic graph convolutional network for multi-label image recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 649–665. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58589-1_39
Zhao, J., Yan, K., Zhao, Y., Guo, X., Huang, F., Li, J.: Transformer-based dual relation graph for multi-label image recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 163–172 (2021)
Zhao, Q., Wang, X., Lyu, S., Liu, B., Yang, Y.: A feature consistency driven attention erasing network for fine-grained image retrieval. Pattern Recogn. 128, 108618 (2022)
Zhou, F., Huang, S., Liu, B., Yang, D.: Multi-label image classification via category prototype compositional learning. IEEE Trans. Circuits Syst. Video Technol. 32(7), 4513–4525 (2021)
Zhou, T., Li, Z., Zhang, C., Ma, H.: Classify multi-label images via improved CNN model with adversarial network. Multimedia Tools Appl. 79, 6871–6890 (2020)
Zhou, W., Dou, P., Su, T., Hu, H., Zheng, Z.: Feature learning network with transformer for multi-label image classification. Pattern Recogn. 136, 109203 (2023)
Zhou, W., Hou, Y., Chen, D., Hu, H., Su, T.: Attention-augmented memory network for image multi-label classification. ACM Trans. Multimedia Comput. Commun. Appl. 19(3), 1–24 (2022)
Zhou, W., Xia, Z., Dou, P., Su, T., Hu, H.: Double attention based on graph attention network for image multi-label classification. ACM Trans. Multimed. Comput. Commun. Appl. 19(1), 1–23 (2023)
Zhu, F., Li, H., Ouyang, W., Yu, N., Wang, X.: Learning spatial regularization with image-level supervisions for multi-label image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5513–5522 (2017)
Zhu, K., Wu, J.: Residual attention: a simple but effective method for multi-label recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 184–193 (2021)
Zhu, Q., Kuang, W., Li, Z.: Dual attention interactive fine-grained classification network based on data augmentation. J. Vis. Commun. Image Represent. 88, 103632 (2022)
Zhu, Q., Kuang, W., Zhixin, L.: Fusing bilinear multi-channel gated vector for fine-grained classification. Mach. Vis. Appl. 34(2), 26 (2023)
Acknowledgments
This work is supported by National Natural Science Foundation of China (Nos. 62276073, 61966004), Guangxi Natural Science Foundation (No. 2019GXNSFDA245018), Innovation Project of Guangxi Graduate Education (No. YCBZ2022060), Guangxi “Bagui Scholar” Teams for Innovation and Research Project, and Guangxi Collaborative Innovation Center of Multi-source Information Integration and Intelligent Processing.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Ethical Statement
We affirm that the ideas, concepts, and findings presented in this paper are the result of our own original work, conducted with honesty, rigor, and transparency. We have provided proper citations and references for all sources used, and have clearly acknowledged the contributions of others where applicable.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kuang, W., Zhu, Q., Li, Z. (2023). Multi-label Image Classification with Multi-scale Global-Local Semantic Graph Network. In: Koutra, D., Plant, C., Gomez Rodriguez, M., Baralis, E., Bonchi, F. (eds) Machine Learning and Knowledge Discovery in Databases: Research Track. ECML PKDD 2023. Lecture Notes in Computer Science(), vol 14171. Springer, Cham. https://doi.org/10.1007/978-3-031-43418-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-43418-1_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43417-4
Online ISBN: 978-3-031-43418-1
eBook Packages: Computer ScienceComputer Science (R0)