Abstract
Semantic segmentation, a fundamental job in computer vision, involves identifying and classifying items in an image. However, it is too costly to collect a sizable volume of annotated data for prediction tasks. Few-shot semantic segmentation approaches aim to learn from a short amount of labeled data and generalize to new classes in order to get over this constraint. Learning to distinguish objects from a small sample of labeled samples is the key challenge in this project. Thus, we propose a Channel and Spatial Attention Alignment Network (CSAANet) for better performance in few-shot semantic segmentation. Our approach uses the channel and spatial attention to obtain weighted classifiers for novel classes. The classes in the image may be precisely segregated using the weight classifiers. Additionally, we construct a semantically aligned auxiliary learning module to fully utilize the supporting image information and enhance the learned weights. Experimental findings on few-shot semantic segmentation datasets, PASCAL-5i and COCO-20i, demonstrate that our proposed method outperforms other methods.
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
Zha, H., Liu, R., Yang, X., Zhou, D., Zhang, Q., Wei, X.: ASFNet: adaptive multiscale segmentation fusion network for real-time semantic segmentation. Comput. Animat. Virtual Worlds 32(3–4), e2022 (2021)
Rao, X., Lu, T., Wang, Z., Zhang, Y.: Few-shot semantic segmentation via frequency guided neural network. IEEE Signal Process. Lett. 29, 1092–1096 (2022)
Chang, Z., Lu, Y., Wang, X., Ran, X.: MGNet: mutual-guidance network for few-shot semantic segmentation. Eng. Appl. Artif. Intell. 116, 105431 (2022)
Gong, C., Shi, K., Niu, Z.: Hierarchical text-label integrated attention network for document classification. In: Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference, pp. 254–260 (2019)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Oktay, O., Schlemper, J., Folgoc, L.L., et al.: Attention U-Net: Learning Where to Look for the Pancreas. arXiv preprint arXiv:1804.03999 (2018)
Fu, J., Liu, J., Tian, H., et al.: Dual attention network for scene segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3146–3154 (2019)
Gidaris, S, Komodakis, N.: Dynamic few-shot visual learning without forgetting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4367–4375 (2018)
Wang, K., Lie J., Zou, Y., Zhou, D., Feng, J.: PANet: few-shot image semantic segmentation with prototype alignment. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9197–9206 (2019)
Rakelly, K., Shelhamer, E., Darrell, T., Efros, A.A., Levine, S.: Few-shot segmentation propagation with guided networks. arXiv preprint arXiv:1806.07373 (2018)
Liu, W., Zhang, C., Lin, G., and Liu, F.: CRNet: cross-reference networks for few-shot segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4165–4173 (2020)
Siam, M., Oreshkin, B.N., Jagersand, M.: AMP: adaptive masked proxies for few-shot segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5249–5258 (2019)
Wang, Z., Liu, L., Li, F.: TAAN: task-aware attention network for few-shot classification. In: 2020 25th International Conference on Pattern Recognition (ICPR) (2021)
Liu, L., Cao, J., Liu, M., Guo, Y., Chen, Q., Tan, M.: Dynamic extension nets for few-shot semantic segmentation. In: Proceedings of the 28th ACM International Conference on Multimedia (2020)
Zhang, X., Wei, Y., Yang, Y., Huang, T.S.: SG-One: similarity guidance network for one-shot semantic segmentation. IEEE Trans. Cybern. 50, 3855–3865 (2020)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neutal Information Processing Systems, pp. 4077–4087 (2017)
Shaban, A., Bansal, S., Liu, Z., Essa, I., Boots, B.: One-shot learning for semantic segmentation. arXiv preprint arXiv:1709.03410 (2017)
Rakelly, K., Shelhamer, E., Darrell, T., Efros, A., Levine, S.: Conditional networks for few-shot semantic segmentation. In: International Conference on Learning Representations, Workshop Track Proceedings (2018)
Zhang, C., Lin. G., Liu, F., Yao, R, Shen, C.: CANet: class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5217–5226 (2019)
Zhang, C., Lin, G., Liu, F., Guo, J, Wu, Q., Yao, R.: Pyramid graph networks with connection attentions for region-based one-shot semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9587–9595 (2019)
Wu, Z., Shi, X, Lin, G., Cai, J.: Learning meta-class memory for few-shot semantic segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 571–526 (2021)
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
Wei, G., Qian, P. (2023). CSAANet: An Attention-Based Mechanism for Aligned Few-Shot Semantic Segmentation Network. 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 14090. Springer, Singapore. https://doi.org/10.1007/978-981-99-4761-4_64
Download citation
DOI: https://doi.org/10.1007/978-981-99-4761-4_64
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4760-7
Online ISBN: 978-981-99-4761-4
eBook Packages: Computer ScienceComputer Science (R0)