Abstract
Continual semantic segmentation (CSS) aims to continuously learn a semantic segmentation model that incorporates new categories while avoiding forgetting the previously seen categories. However, CSS faces a significant challenge known as weight shift, which leads to the network mistakenly predicting masks belonging to new categories instead of their actual categories. To mitigate this phenomenon, we propose a novel module named mask matching module, which transfers pixel-level prediction task into a mask-level feature matching task by computing the similarity between mask features and prototypes. Further, we introduce a new paradigm and a network called Learn-to-Match (L2M) Net, which alleviates weight shift and gains remarkable improvements on long settings by leveraging mask-level feature matching. Our method can be easily integrated into various network architectures without extra memory and data cost. Experiments conducted on the Pascal-VOC 2012 and ADE20K datasets demonstrate that, particularly on long settings where CSS encounters more challenging settings, our method achieves a remarkable \(10.6\%\) improvement in terms of all mean Intersection over Union (mIoU) and establishes a new state-of-the-art performance in the demanding CSS settings.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bulo, S.R., Porzi, L., Kontschieder, P.: In-place activated batchnorm for memory-optimized training of DNNs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5639–5647 (2018)
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, pp. 9233–9242 (2020)
Cha, S., Yoo, Y., Moon, T., et al.: SSUL: semantic segmentation with unknown label for exemplar-based class-incremental learning. Adv. Neural. Inf. Process. Syst. 34, 10919–10930 (2021)
Chaudhry, A., et al.: Continual learning with tiny episodic memories (2019)
Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)
Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Adv. Neural. Inf. Process. Syst. 34, 17864–17875 (2021)
De Lange, M., et al.: A continual learning survey: defying forgetting in classification tasks. IEEE Trans. Pattern Anal. Mach. Intell. 44(7), 3366–3385 (2021)
De Lange, M., Tuytelaars, T.: Continual prototype evolution: learning online from non-stationary data streams. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8250–8259 (2021)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Ding, H., Jiang, X., Shuai, B., Liu, A.Q., Wang, G.: Semantic segmentation with context encoding and multi-path decoding. IEEE Trans. Image Process. 29, 3520–3533 (2020)
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)
Douillard, A., Chen, Y., Dapogny, A., Cord, M.: Tackling catastrophic forgetting and background shift in continual semantic segmentation. arXiv preprint arXiv:2106.15287 (2021)
Douillard, A., Cord, M., Ollion, C., Robert, T., Valle, E.: PODNet: pooled outputs distillation for small-tasks incremental learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XX. LNCS, vol. 12365, pp. 86–102. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58565-5_6
Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88, 303–338 (2010)
French, R.M.: Catastrophic forgetting in connectionist networks. Trends Cogn. Sci. 3(4), 128–135 (1999)
Fu, J., 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)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hsu, Y.C., Liu, Y.C., Ramasamy, A., Kira, Z.: Re-evaluating continual learning scenarios: a categorization and case for strong baselines. arXiv preprint arXiv:1810.12488 (2018)
Huang, Z., et al.: Half-real half-fake distillation for class-incremental semantic segmentation. arXiv preprint arXiv:2104.00875 (2021)
Isele, D., Cosgun, A.: Selective experience replay for lifelong learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Jung, H., Ju, J., Jung, M., Kim, J.: Less-forgetting learning in deep neural networks. arXiv preprint arXiv:1607.00122 (2016)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Nat. Acad. Sci. 114(13), 3521–3526 (2017)
Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935–2947 (2017)
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, pp. 7026–7035 (2021)
Michieli, U., Zanuttigh, P.: Incremental learning techniques for semantic segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, pp. 0–0 (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, pp. 1114–1124 (2021)
Phan, M.H., Phung, S.L., Tran-Thanh, L., Bouzerdoum, A., et al.: Class similarity weighted knowledge distillation for continual semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16866–16875 (2022)
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)
Rolnick, D., Ahuja, A., Schwarz, J., Lillicrap, T., Wayne, G.: Experience replay for continual learning. Adv. Neural Inf. Process. Syst. 32 (2019)
Singh, P., Mazumder, P., Rai, P., Namboodiri, V.P.: Rectification-based knowledge retention for continual learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 15282–15291 (2021)
Sun, K., et al.: High-resolution representations for labeling pixels and regions. arXiv preprint arXiv:1904.04514 (2019)
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)
Thrun, S.: Lifelong learning algorithms. Learn. Learn 8, 181–209 (1998)
Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)
Van de Ven, G.M., Tolias, A.S.: Three scenarios for continual learning. arXiv preprint arXiv:1904.07734 (2019)
Wu, Y., et al.: Large scale incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 374–382 (2019)
Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Learning a discriminative feature network for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1857–1866 (2018)
Yu, L., Liu, X., Van de Weijer, J.: Self-training for class-incremental semantic segmentation. IEEE Trans. Neural Netw. Learning Syst. 34, 9116–9127 (2022)
Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part VI. LNCS, vol. 12351, pp. 173–190. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58539-6_11
Zenke, F., Poole, B., Ganguli, S.: Continual learning through synaptic intelligence. In: International Conference on Machine Learning, pp. 3987–3995. PMLR (2017)
Zhang, C.B., Xiao, J.W., Liu, X., Chen, Y.C., Cheng, M.M.: Representation compensation networks for continual semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7053–7064 (2022)
Zhang, C., Song, N., Lin, G., Zheng, Y., Pan, P., Xu, Y.: Few-shot incremental learning with continually evolved classifiers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12455–12464 (2021)
Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633–641 (2017)
Acknowledgement
The paper is supported in part by the National Natural Science Foundation of China (62006036), and Fundamental Research Funds for Central Universities (DUT22LAB124, DUT22QN228).
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 Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, W., Li, B., Wang, Y. (2024). L2MNet: Enhancing Continual Semantic Segmentation with Mask Matching. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14434. Springer, Singapore. https://doi.org/10.1007/978-981-99-8549-4_11
Download citation
DOI: https://doi.org/10.1007/978-981-99-8549-4_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8548-7
Online ISBN: 978-981-99-8549-4
eBook Packages: Computer ScienceComputer Science (R0)