Abstract
Class-Incremental Learning is a challenging problem in machine learning that aims to extend previously trained neural networks with new classes. This is especially useful if the system is able to classify new objects despite the original training data being unavailable. Although the semantic segmentation problem has received less attention than classification, it poses distinct problems and challenges, since previous and future target classes can be unlabeled in the images of a single increment. In this case, the background, past and future classes are correlated and there exists a background-shift.
In this paper, we address the problem of how to model unlabeled classes while avoiding spurious feature clustering of future uncorrelated classes. We propose to use Evidential Deep Learning to model the evidence of the classes as a Dirichlet distribution. Our method factorizes the problem into a separate foreground class probability, calculated by the expected value of the Dirichlet distribution, and an unknown class (background) probability corresponding to the uncertainty of the estimate. In our novel formulation, the background probability is implicitly modeled, avoiding the feature space clustering that comes from forcing the model to output a high background score for pixels that are not labeled as objects. Experiments on the incremental Pascal VOC and ADE20k benchmarks show that our method is superior to the state of the art, especially when repeatedly learning new classes with increasing number of increments.
Supported by Sweden’s Innovation Agency (Vinnova).
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
Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., Tuytelaars, T.: Memory aware synapses: learning what (not) to Forget. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 144–161. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_9
Castro, F.M., Marín-Jiménez, M.J., Guil, N., Schmid, C., Alahari, K.: End-to-end incremental learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 241–257. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01258-8_15
Cermelli, F., Mancini, M., Bulo, S.R., Ricci, E., Caputo, B.: Modeling the background for incremental learning in semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (June 2020)
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2017)
Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)
Choi, Y., El-Khamy, M., Lee, J.: Dual-teacher class-incremental learning with data-free generative replay. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3543–3552 (2021)
Douillard, A., Chen, Y., Dapogny, A., Cord, M.: Plop: Learning without forgetting for continual semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4040–4050 (2021)
Drummond, N., Shearer, R.: The open world assumption. In: eSI Workshop: The Closed World of Databases meets the Open World of the Semantic Web, vol. 15 (2006)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2012 (VOC 2012) Results. http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html
He, C., Wang, R., Chen, X.: A tale of two cils: The connections between class incremental learning and class imbalanced learning, and beyond. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3559–3569 (2021)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521–3526 (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 25, 1097–1105 (2012)
Lesort, T., Lomonaco, V., Stoian, A., Maltoni, D., Filliat, D., Dıaz-Rodrıguez, N.: Continual learning for robotics, pp. 1–34. arXiv preprint arXiv:1907.00182 (2019)
Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935–2947 (2017)
Liu, X., et al.: Generative feature replay for class-incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 226–227 (2020)
Liu, X., Yang, H., Ravichandran, A., Bhotika, R., Soatto, S.: Continual universal object detection. arXiv preprint arXiv:2002.05347 (2020)
Liu, Y., Su, Y., Liu, A.A., Schiele, B., Sun, Q.: Mnemonics training: Multi-class incremental learning without forgetting. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12245–12254 (2020)
Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)
Maracani, A., Michieli, U., Toldo, M., Zanuttigh, P.: Recall: Replay-based continual learning in semantic segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 7026–7035 (October 2021)
Mi, F., Kong, L., Lin, T., Yu, K., Faltings, B.: Generalized class incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (June 2020)
Michieli, U., Zanuttigh, P.: Incremental learning techniques for semantic segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (2019)
Michieli, U., Zanuttigh, P.: Continual semantic segmentation via repulsion-attraction of sparse and disentangled latent representations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1114–1124 (June 2021)
Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: icarl: Incremental classifier and representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2001–2010 (2017)
Şensoy, M., Kaplan, L., Kandemir, M.: Evidential deep learning to quantify classification uncertainty. In: Advances in Neural Information Processing Systems (2018)
Tao, X., Chang, X., Hong, X., Wei, X., Gong, Y.: Topology-preserving class-incremental learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 254–270. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58529-7_16
Tao, X., Hong, X., Chang, X., Dong, S., Wei, X., Gong, Y.: Few-shot class-incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12183–12192 (2020)
Wentao Bao, Q.Y., Kong, Y.: Evidential deep learning for open set action recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2021)
Wu, Y., et al.: Incremental classifier learning with generative adversarial networks. arXiv preprint arXiv:1802.00853 (2018)
Xiang, Y., Fu, Y., Ji, P., Huang, H.: Incremental learning using conditional adversarial networks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6619–6628 (2019)
Yu, L., et al.: Semantic drift compensation for class-incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (June 2020)
Zhang, B.F., Su, J.S., Xu, X.: A class-incremental learning method for multi-class support vector machines in text classification. In: 2006 International Conference on Machine Learning and Cybernetics, pp. 2581–2585. IEEE (2006)
Zhang, H., Zhu, M., Zhang, J., Zhuo, L.: Long-term visual object tracking via continual learning. IEEE Access 7, 182548–182558 (2019). https://doi.org/10.1109/ACCESS.2019.2960321
Zhang, J., et al.: Class-incremental learning via deep model consolidation. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (March 2020)
Zhao, B., Xiao, X., Gan, G., Zhang, B., Xia, S.T.: Maintaining discrimination and fairness in class incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (June 2020)
Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881–6890 (2021)
Zhou, B., et al.: Semantic understanding of scenes through the ade20k dataset. Int. J. Comput. Vision 127(3), 302–321 (2019)
Zoph, B., et al.: Rethinking pre-training and self-training. Adv. Neural. Inf. Process. Syst. 33, 3833–3845 (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 Switzerland AG
About this paper
Cite this paper
Holmquist, K., Klasén, L., Felsberg, M. (2023). Evidential Deep Learning for Class-Incremental Semantic Segmentation. In: Gade, R., Felsberg, M., Kämäräinen, JK. (eds) Image Analysis. SCIA 2023. Lecture Notes in Computer Science, vol 13886. Springer, Cham. https://doi.org/10.1007/978-3-031-31438-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-31438-4_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31437-7
Online ISBN: 978-3-031-31438-4
eBook Packages: Computer ScienceComputer Science (R0)
