Abstract
Over the past few years, deep learning-based semantic segmentation methods reached state-of-the-art performance. The segmentation task is time-consuming and requires a lot of pixel-level annotated data, which restricts the segmentation application. Benefiting from the general segmentation task, few-shot semantic segmentation also developed significantly. In this study, we propose a real-time training method based on feature transformation and a multi-stage classifier. The generalization ability of the model is enhanced through the strategy of real-time training. Aiming at the inconsistency of the feature domain of the support set and query set, we propose a feature transformation module, which uses the memory mechanism to map the query set features to the feature domain of the support set. Then, the query set features can better adapt to the classifier. The multi-stage classifier is used to retain the hierarchical information of different scales, and the attention mechanism is introduced to further explore information in different sizes and channels to prevent the abuse of advanced features effectively. We conducted experiments on the COCO-20i dataset, and our model can obtain good performance, i.e., 32.7% and 41.7% mIoU scores for 1-shot and 5-shot settings, respectively.
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
Dong, N., Xing, E.P.: Few-shot semantic segmentation with prototype learning. In: BMVC (2018)
Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010). https://doi.org/10.1007/s11263-009-0275-4
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, pp. 1126–1135 (2017)
Gairola, S., Hemani, M., Chopra, A., Krishnamurthy, B.: SimPropNet: improved similarity propagation for few-shot image segmentation. In: IJCAI, pp. 573–579 (2021)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Li, X., Wei, T., Chen, Y.P., Tai, Y.W., Tang, C.K.: FSS-1000: a 1000-class dataset for few-shot segmentation. In: CVPR, pp. 2869–2878 (2020)
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
Liu, W., Zhang, C., Lin, G., Liu, F.: CRNet: cross-reference networks for few-shot segmentation. In: CVPR, pp. 4165–4173 (2020)
Liu, Y., Zhang, X., Zhang, S., He, X.: Part-aware prototype network for few-shot semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 142–158. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_9
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440 (2015)
Nguyen, K., Todorovic, S.: Feature weighting and boosting for few-shot segmentation. In: ICCV, pp. 622–631 (2019)
Rakelly, K., Shelhamer, E., Darrell, T., Efros, A., Levine, S.: Conditional networks for few-shot semantic segmentation. In: ICLR (2018)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Shaban, A., Bansal, S., Liu, Z., Essa, I., Boots, B.: One-shot learning for semantic segmentation. In: BMVC (2017)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: NeurIPS (2017)
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: CVPR, pp. 1199–1208 (2018)
Tian, Z., Zhao, H., Shu, M., Yang, Z., Li, R., Jia, J.: Prior guided feature enrichment network for few-shot segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 44(2), 1050–1065 (2020)
Wang, H., Zhang, X., Hu, Y., Yang, Y., Cao, X., Zhen, X.: Few-shot semantic segmentation with democratic attention networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 730–746. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58601-0_43
Wang, K., Liew, J.H., Zou, Y., Zhou, D., Feng, J.: PANet: few-shot image semantic segmentation with prototype alignment. In: ICCV, pp. 9197–9206 (2019)
Yang, B., Liu, C., Li, B., Jiao, J., Ye, Q.: Prototype mixture models for few-shot semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 763–778. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58598-3_45
Ye, H.J., Hu, H., Zhan, D.C., Sha, F.: Few-shot learning via embedding adaptation with set-to-set functions. In: CVPR, pp. 8808–8817 (2020)
Zhang, C., Lin, G., Liu, F., Yao, R., Shen, C.: CANet: class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. In: CVPR, pp. 5217–5226 (2019)
Zhang, X., Wei, Y., Yang, Y., Huang, T.S.: SG-One: similarity guidance network for one-shot semantic segmentation. IEEE Trans. Cybern. 50(9), 3855–3865 (2020)
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
Gu, Z., Luo, Z., Li, S. (2023). A Classifier-Based Two-Stage Training Model for Few-Shot Segmentation. In: Sun, Y., et al. Computer Supported Cooperative Work and Social Computing. ChineseCSCW 2022. Communications in Computer and Information Science, vol 1682. Springer, Singapore. https://doi.org/10.1007/978-981-99-2385-4_17
Download citation
DOI: https://doi.org/10.1007/978-981-99-2385-4_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-2384-7
Online ISBN: 978-981-99-2385-4
eBook Packages: Computer ScienceComputer Science (R0)
