Abstract
The domain adaptation of an instance segmentation model has gained much attention. However, manual annotation is tedious and self-training contains too much pseudolabel noise. Inspired by weakly supervised methods, we propose a method to handle these challenges by limited verification signals and label propagation. Semantic trees are constructed to explore the relation between samples by using a clustering method; Then, reliable pseudolabels are verified and propagated to unreliable labels, which improves instance segmentation model by employing the updated samples. Experiments on public datasets demonstrate that the proposed approach is competitive with state-of-the-art approaches.
J. Sun and Y. Tian— Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ali, R., et al.: Optic disk and cup segmentation through fuzzy broad learning system for glaucoma screening. IEEE Trans. Industr. Inf. 17(4), 2476–2487 (2020)
Cheng, B., Misra, I., Schwing, A.G., Kirillov, A.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE/CVF in Proceedings on Computer Vision and Pattern Recognition, pp. 1290–1299 (2022)
Dogan, A., Birant, D.: K-centroid link: a novel hierarchical clustering linkage method. Appl. Intell. 52(5), 5537–5560 (2021). https://doi.org/10.1007/s10489-021-02624-8
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)
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International in Proceedings on Machine Learning, pp. 1180–1189 (2015)
Hanselmann, N., Schneider, N., Ortelt, B., Geiger, A.: Learning cascaded detection tasks with weakly-supervised domain adaptation. In: IEEE Intelligent Vehicles Symposium, pp. 532–539 (2021)
Hsu, J., Chiu, W., Yeung, S.: DARCNN: domain adaptive region-based convolutional neural network for unsupervised instance segmentation in biomedical images. In: Proceedings of the IEEE/CVF in Proceedings on Computer Vision and Pattern Recognition, pp. 1003–1012 (2021)
Jia, Z., Li, Y., Tan, Z., Wang, W., Wang, Z., Yin, G.: Domain-invariant feature extraction and fusion for cross-domain person re-identification. Vis. Comput. 39(3), 1205–1216 (2023)
Kong, X., Xia, S., Liu, N., Wei, M.: GADA-SegNet: gated attentive domain adaptation network for semantic segmentation of lidar point clouds. Vis. Comput., 1–11 (2023). https://doi.org/10.1007/s00371-023-02799-w
Li, C., et al.: Domain adaptive nuclei instance segmentation and classification via category-aware feature alignment and pseudo-labelling. In: Proceedings of the Medical Image Computing and Computer Assisted Intervention, pp. 715–724 (2022)
Li, C., et al.: Spatial attention pyramid network for unsupervised domain adaptation. In: Proceedings of the European in Proceedings on Computer Vision, pp. 481–497 (2020)
Li, T., Rezaeipanah, A., El Din, E.M.T.: An ensemble agglomerative hierarchical clustering algorithm based on clusters clustering technique and the novel similarity measurement. J. King Saud Univ.-Comput. Inf. Sci. 34(6), 3828–3842 (2022)
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, D., Zhang, D., Song, Y.: Unsupervised instance segmentation in microscopy images via panoptic domain adaptation and task re-weighting. In: Proceedings of the IEEE/CVF in Proceedings on Computer Vision and Pattern Recognition, pp. 4243–4252 (2020)
Liu, D., et al.: PDAM: a panoptic-level feature alignment framework for unsupervised domain adaptive instance segmentation in microscopy images. IEEE Trans. Med. Imaging 40(1), 154–165 (2020)
Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y.: Swin transformer v2: scaling up capacity and resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12009–12019 (2022)
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10012–10022 (2021)
Ljosa, V., Sokolnicki, K.L., Carpenter, A.E.: Annotated high-throughput microscopy image sets for validation. Nat. Methods 9(7), 637–637 (2012)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International in Proceedings on Learning Representations, pp. 1526–1537 (2019)
Naylor, P., Laé, M., Reyal, F., Walter, T.: Segmentation of nuclei in histopathology images by deep regression of the distance map. IEEE Trans. Med. Imaging 38(2), 448–459 (2018)
Sharma, Y., Syed, S., Brown, D.E.: MaNi: Maximizing mutual information for nuclei cross-domain unsupervised segmentation. In: Proceedings of the Medical Image Computing and Computer Assisted Intervention, pp. 345–355 (2022). https://doi.org/10.1007/978-3-031-16434-7_34
Shen, Y.: Domain-invariant interpretable fundus image quality assessment. Med. Image Anal. 61, 101654 (2020)
Srivastav, V., Gangi, A., Padoy, N.: Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room. Med. Image Anal. 80, 102525 (2022)
Tian, Y., et al.: Global context assisted structure-aware vehicle retrieval. IEEE Trans. Intell. Transp. Syst. 21(10), 1–10 (2021)
Tian, Y., Cheng, G., Gelernter, J., Yu, S., Song, C., Yang, B.: Joint temporal context exploitation and active learning for video segmentation. Pattern Recogn. 100, 107158 (2020)
Tian, Y., Gelernter, J., Wang, X., Li, J., Yu, Y.: Traffic sign detection using a multi-scale recurrent attention network. IEEE Trans. Intell. Transp. Syst. 20(12), 4466–4475 (2019)
Tian, Y., Wang, X., Wu, J., Wang, R.: Multi-scale hierarchical residual network for dense captioning. J. Artif. Intell. Res. 64, 181–196 (2019)
Tian, Y., et al.: 3D tooth instance segmentation learning objectness and affinity in point cloud. ACM Trans. Multimed. Comput. Commun. Appl. 18, 202–211 (2022)
Tian, Y., Zhang, Y., Zhou, D., Cheng, G., Chen, W.G., Wang, R.: Triple attention network for video segmentation. Neurocomputing 417, 202–211 (2020)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE in Proceedings on Computer Vision and Pattern Recognition, pp. 7167–7176 (2017)
Varshney, A.K., Muhuri, P.K.: PIFHC: the probabilistic intuitionistic fuzzy hierarchical clustering algorithm. Appl. Soft Comput. 120, 108584 (2022)
Yang, J., Li, C., Zhang, P., Dai, X., Xiao, B.: Focal self-attention for local-global interactions in vision transformers. arXiv preprint arXiv:2107.00641 (2021)
Yang, S., Zhang, J., Huang, J., Lovell, B.C., Han, X.: Minimizing labeling cost for nuclei instance segmentation and classification with cross-domain images and weak labels. In: Proceedings of the AAAI in Proceedings on Artificial Intelligence, pp. 697–705 (2021)
Zhou, D., Tian, Y., Chen, W.G.: Self-supervised saliency estimation for pixel embedding in road detection. IEEE Signal Process. Lett. 28, 1325–1329 (2021)
Zhu, Y., et al.: Improving semantic segmentation via video propagation and label relaxation. In: Proceedings of the IEEE/CVF in Proceedings on Computer Vision and Pattern Recognition, pp. 8856–8865 (2019)
Acknowledgments
This work was supported by the National Natural Science Foundation of China (61976188, 61972351, 62111530300). The authors declare no conflicts of interest.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sun, J. et al. (2024). Weakly Supervised Method for Domain Adaptation in Instance Segmentation. In: Sheng, B., Bi, L., Kim, J., Magnenat-Thalmann, N., Thalmann, D. (eds) Advances in Computer Graphics. CGI 2023. Lecture Notes in Computer Science, vol 14495. Springer, Cham. https://doi.org/10.1007/978-3-031-50069-5_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-50069-5_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50068-8
Online ISBN: 978-3-031-50069-5
eBook Packages: Computer ScienceComputer Science (R0)