Abstract
When image-level labels are used for weakly-supervised semantic segmentation, there is a problem of missing target position and shape. Using classification networks to generate class activation maps has become a common method. Since the location map generated by Class Activation Mapping (CAM) tends to focus only on a small part of the significant area of the target, the generated class activation map is sparse and rough. To solve this common problem, an improved method based on CAM is proposed, which suppresses the classifier’s attention to salient regions, guides and spreads to adjacent non-salient regions, and generates denser segmentation labels. The generated segmentation label is enhanced by an improved VGG-16 network, and the high-quality pseudo-segment label will be used as the supervision information to supervise the training of the segmentation network. The comparison of the results on the PASCAL VOC 2012 proves the effectiveness of the method and excellent segmentation performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bertasius, G., Torresani, L., Yu, S.X., et al.: Convolutional random walk networks for semantic image segmentation. In: IEEE Conference on Computer Vision & Pattern Recognition. IEEE Computer Society (2016)
Chen, L.C., Papandreou, G., Kokkinos, I., et al.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. Comput. Sci. 4, 357–361 (2014)
Chen, L.C., Papandreou, G., Kokkinos, I., et al.: DeepLab: semantic image segmentation with deep convolutional nets, Atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2018)
Lin, G., Shen, C., Hengel, A., et al.: Efficient piecewise training of deep structured models for semantic segmentation. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2016)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640–651 (2015)
Noh, H., Hong, S., Han, B., et al.: Learning deconvolution network for semantic segmentation, pp. 1520–1528 (2015)
Qi, G.-J.: Hierarchically gated deep networks for semantic segmentation. Comput. Vis. Pattern Recogn., 2267–2275 (2016)
Zheng, S., Jayasumana, S., Romera-Paredes, B., et al.: Conditional random fields as recurrent neural networks. IEEE (2015)
Papandreou, G., Chen, L.C., Murphy, K.P., et al.: Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation. In: IEEE International Conference on Computer Vision. IEEE (2016)
Dai, J., He, K., Sun, J.: BoxSup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1635–1643 (2015)
Khoreva, A., Benenson, R., Hosang, J., et al.: Simple does it: weakly supervised instance and semantic segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Di, L., Dai, J., Jia, J., et al.: ScribbleSup: scribble-supervised convolutional networks for semantic segmentation. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2016)
Vernaza, P., Chandraker, M.: Learning random-walk label propagation for weakly-supervised semantic segmentation. In: IEEE Conference on Computer Vision & Pattern Recognition, pp. 2953–2961. IEEE Computer Society (2017)
Bearman, A., Russakovsky, O., Ferrari, V., et al.: What's the point: semantic segmentation with point supervision. In: European Conference on Computer Vision (2016)
Pathak, D., Shelhamer, E., Long, J., et al.: Fully convolutional multi-class multiple instance learning. Comput. Sci. (2014)
Hong, S., Yeo, D., Kwak, S., et al.: Weakly supervised semantic segmentation using web-crawled videos. IEEE Computer Society (2017)
Kolesnikov, A., Lampert, C.: Seed, expand and constrain: three principles for weakly-supervised image segmentation. In: Leibe, Bastian, Matas, Jiri, Sebe, Nicu, Welling, Max (eds.) ECCV 2016. LNCS, vol. 9908, pp. 695–711. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_42
Kwak, S., Hong, S., Han, B.: Weakly supervised semantic segmentation using superpixel pooling network. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI 2017), pp. 4111–4117. AAAI Press (2017)
Pathak, D., Krhenbühl, P., Darrell, T.: Constrained convolutional neural networks for weakly supervised segmentation. IEEE (2015)
Wei, Y., et al.: Object region mining with adversarial erasing: a simple classification to semantic segmentation approach. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2017)
Jia, D., Wei, D., Socher, R., et al.: ImageNet: a large-scale hierarchical image database. In: Proceedingsof IEEE Computer Vision & Pattern Recognition, pp. 248–255 (2009)
Zhou, B., Khosla, A., Lapedriza, A., et al.: Learning deep features for discriminative localization. IEEE Computer Society (2016)
Wei, Y., Liang, X., Chen, Y., et al.: STC: a simple to complex framework for weakly-supervised semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2314–2320 (2017)
Ahn, J., Kwak, S.: Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2018)
Huang, Z., Wang, X., Wang, J., Liu, W., Wang, J.: Weakly-supervised semantic segmentation network with deep seeded region growing. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7014–7023 (2018)
Jiang, P., Hou, Q., Cao, Y., Cheng, M., Wei, Y., Xiong, H.: Integral object mining via online attention accumulation. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 2070–2079 (2019)
Zhang, X., Wei, Y., Feng, J., et al.: Adversarial Complementary Learning for Weakly Supervised Object Localization. IEEE (2018)
Everingham, M., Eslami, S., Gool, L.V., et al.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111(1), 98–136 (2015)
Paszke A , Gross S , Chintala S , et al.: Automatic differentiation in PyTorch (2017)
Lin, Tsung-Yi., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.: 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
Wang, X., You, S., Li, X., et al.: Weakly-supervised semantic segmentation by iteratively mining common object features. IEEE (2018)
Chaudhry, A., Dokania, P., Torr, P.: Discovering class-specific pixels for weakly-supervised semantic segmentation. In: BMVC (2017)
Fan, J., Zhang, Z., Song, C., Tan, T.: Learning integral objects with intra-class discrimina-tor for weakly-supervised semantic segmentation. In: CVPR, pp. 4283–4292 (2020)
Wei, Y., Xiao, H., Shi, H., et al.: Revisiting dilated convolution: a simple approach for weakly- and semi- supervised semantic segmentation. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE (2018)
Lee, J., Kim, E., Lee, S., et al.: FickleNet: weakly and semi-supervised semantic image segmentation using stochastic inference. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2019)
Sun, G., Wang, W., Dai, J., et al.: Mining cross-image semantics for weakly supervised semantic segmentation (2020)
Shimoda, W., Yanai, K.: Distinct class-specific saliency maps for weakly supervised semantic segmentation. In: Leibe, Bastian, Matas, Jiri, Sebe, Nicu, Welling, Max (eds.) ECCV 2016. LNCS, vol. 9908, pp. 218–234. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_14
Zhang, D., Zhang, H., Tang, J., et al.: Causal intervention for weakly-supervised semantic segmentation (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yan, X., Gao, Y., Wang, G. (2022). Weakly-Supervised Semantic Segmentation Based on Improved CAM. In: Xie, Q., Zhao, L., Li, K., Yadav, A., Wang, L. (eds) Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery. ICNC-FSKD 2021. Lecture Notes on Data Engineering and Communications Technologies, vol 89. Springer, Cham. https://doi.org/10.1007/978-3-030-89698-0_60
Download citation
DOI: https://doi.org/10.1007/978-3-030-89698-0_60
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89697-3
Online ISBN: 978-3-030-89698-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)