Abstract
Fine-grained image recognition is more difficult than conventional image classification tasks. Previous advanced network models require a large number of complex structure design and preliminary training. In this paper, a novel attention mechanism: Global Spatial Coordinate Attention Module (GSCAM) is proposed. This structure inherits the advantages of widely used SE channel attention and CBAM spatial attention, uses two 1D features for spatial position coding, and parallels global attention convergence blocks to extract context features, which can obtain the spatial location information and global context feature information of the region of interest of the image, so as to accurately locate the distinguishable region in the image. We apply this module to the mainstream classification network (ResNet50, ResNeXt50) pre-trained by ImageNet. Under the condition that the original network increases a very small number of parameters and computational cost, the accuracy of fine-grained image recognition is close to the SOTA level in different benchmark datasets, and there is no need to design the network structure from scratch, which is simple and fast.
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
Similar content being viewed by others
References
Du, R., et al.: Fine-grained visual classification via progressive multi-granularity training of jigsaw patches. In: European Conference on Computer Vision, pp. 153–168: Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58565-5_10
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)
Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492–1500 (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 (2018)
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Xie, L., Tian, Q., Hong, R., Yan, S., Zhang, B.: Hierarchical part matching for fine-grained visual categorization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1641–1648 (2013)
Zheng, H., Fu, J., Mei, T., Luo, J.: Learning multi-attention convolutional neural network for fine-grained image recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5209–5217 (2017)
Chen, Y., Bai, Y., Zhang, W., Mei, T.: Destruction and construction learning for fine-grained image recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5157–5166 (2019)
Ding, Y., Zhou, Y., Zhu, Y., Ye, Q., Jiao, J.: Selective sparse sampling for fine-grained image recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6599–6608 (2019)
Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794–7803 (2018)
Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: Gcnet: non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, p. 0 (2019)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31, no. 1 (2017)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105–6114. PMLR (2019)
Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. arXiv preprint arXiv:2103.02907 (2021)
Zhao, M., Zhong, S., Fu, X., Tang, B., Pecht, M.: Deep residual shrinkage networks for fault diagnosis. IEEE Trans. Industr. Inf. 16(7), 4681–4690 (2019)
Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200–2011 dataset (2011)
Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554–561 (2013)
Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)
Lin, T.Y., RoyChowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1449–1457 (2015)
Dubey, A., Gupta, O., Guo, P., Raskar, R., Farrell, R., Naik, N.: Pairwise confusion for fine-grained visual classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 71–88. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01258-8_5
Wang, Y., Morariu, V.I., Davis, L.S.: Learning a discriminative filter bank within a CNN for fine-grained recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4148–4157 (2018)
Ji, R., et al.: Attention convolutional binary neural tree for fine-grained visual categorization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10468–10477 (2020)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Acknowledgment
This work was supported in part by the National Natural Science Foundation of China under Grant 62071384, Key Research and Development Project of Shaanxi Province under Grant 2020ZDLGY04–09.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Guo, H., Guo, Z., Pan, Z. (2021). GSCAM: Global Spatial Coordinate Attention Module for Fine-Grained Image Recognition. In: Peng, Y., Hu, SM., Gabbouj, M., Zhou, K., Elad, M., Xu, K. (eds) Image and Graphics. ICIG 2021. Lecture Notes in Computer Science(), vol 12888. Springer, Cham. https://doi.org/10.1007/978-3-030-87355-4_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-87355-4_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87354-7
Online ISBN: 978-3-030-87355-4
eBook Packages: Computer ScienceComputer Science (R0)