{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:47:13Z","timestamp":1774716433536,"version":"3.50.1"},"reference-count":29,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004480","name":"Natural Science Foundation of Shanxi Province","doi-asserted-by":"publisher","award":["202203021212138"],"award-info":[{"award-number":["202203021212138"]}],"id":[{"id":"10.13039\/501100004480","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272426"],"award-info":[{"award-number":["62272426"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation of Shanxi Key Laboratory of Machine Vision and Virtual Reality","award":["447-110103"],"award-info":[{"award-number":["447-110103"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Although current 3D semantic segmentation methods have achieved significant success, they suffer from catastrophic forgetting when confronted with dynamic, open environments. To address this issue, class incremental learning is introduced to update models while maintaining a balance between plasticity and stability. In this work, we propose CosPrompt, a rehearsal-free approach for class incremental semantic segmentation. Specifically, we freeze the prompts for existing classes and incrementally expand and fine-tune the prompts for new classes, thereby generating discriminative and customized features. We employ clamping operations to regulate backward propagation, ensuring smooth training. Furthermore, we utilize the learning without forgetting loss and pseudo-label generation to further mitigate catastrophic forgetting. We conduct comparative and ablation experiments on the S3DIS dataset and ScanNet v2 dataset, demonstrating the effectiveness and feasibility of our method.<\/jats:p>","DOI":"10.3390\/a18100648","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:29:38Z","timestamp":1760599778000},"page":"648","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Cosine Prompt-Based Class Incremental Semantic Segmentation for Point Clouds"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1559-6022","authenticated-orcid":false,"given":"Lei","family":"Guo","sequence":"first","affiliation":[{"name":"Shanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, China"},{"name":"School of Computer Science and Technology, North University of China, Taiyuan 030051, China"}]},{"given":"Hongye","family":"Li","sequence":"additional","affiliation":[{"name":"Luzhou North Chemical Industries Co., Ltd., Luzhou 646003, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0165-4212","authenticated-orcid":false,"given":"Min","family":"Pang","sequence":"additional","affiliation":[{"name":"Shanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, China"},{"name":"School of Computer Science and Technology, North University of China, Taiyuan 030051, China"}]},{"given":"Kaowei","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, China"},{"name":"School of Computer Science and Technology, North University of China, Taiyuan 030051, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2320-042X","authenticated-orcid":false,"given":"Xie","family":"Han","sequence":"additional","affiliation":[{"name":"Shanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, China"},{"name":"School of Computer Science and Technology, North University of China, Taiyuan 030051, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3596-6457","authenticated-orcid":false,"given":"Fengguang","family":"Xiong","sequence":"additional","affiliation":[{"name":"Shanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, China"},{"name":"School of Computer Science and Technology, North University of China, Taiyuan 030051, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/s00138-024-01543-1","article-title":"A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation","volume":"35","author":"Sarker","year":"2024","journal-title":"Mach. Vis. Appl."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"5362","DOI":"10.1109\/TPAMI.2024.3367329","article-title":"A comprehensive survey of continual learning: Theory, method and application","volume":"46","author":"Wang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"9851","DOI":"10.1109\/TPAMI.2024.3429383","article-title":"Class-incremental learning: A survey","volume":"46","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.A., Kolesnikov, A., Sperl, G., and Lampert, C.H. (2017, January 21\u201326). icarl: Incremental classifier and representation learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Douillard, A., Cord, M., Ollion, C., Robert, T., and Valle, E. (2020, January 23\u201328). Podnet: Pooled outputs distillation for small-tasks incremental learning. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58565-5_6"},{"key":"ref_6","unstructured":"Gao, R., and Liu, W. (2023, January 23\u201329). Ddgr: Continual learning with deep diffusion-based generative replay. Proceedings of the International Conference on Machine Learning, Honolulu, HI, USA."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","article-title":"Learning without forgetting","volume":"40","author":"Li","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_8","unstructured":"Lee, K., Lee, K., Shin, J., and Lee, H. (November, January 27). Overcoming catastrophic forgetting with unlabeled data in the wild. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_9","unstructured":"Gao, Z., Han, S., Zhang, X., Xu, K., Zhou, D., Mao, X., Dou, Y., and Wang, H. (March, January 25). Maintaining fairness in logit-based knowledge distillation for class-incremental learning. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_11","unstructured":"Benzing, F. (2022, January 28\u201330). Unifying importance based regularisation methods for continual learning. Proceedings of the International Conference on Artificial Intelligence and Statistics, Virtual."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yan, S., Xie, J., and He, X. (2021, January 20\u201325). Der: Dynamically expandable representation for class incremental learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Douillard, A., Ram\u00e9, A., Couairon, G., and Cord, M. (2022, January 18\u201324). Dytox: Transformers for continual learning with dynamic token expansion. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"ref_14","unstructured":"Wang, Z., Zhang, Z., Ebrahimi, S., Sun, R., Zhang, H., Lee, C.Y., Ren, X., Su, G., Perot, V., and Dy, J. (2020, January 23\u201328). Dualprompt: Complementary prompting for rehearsal-free continual learning. Proceedings of the European Conference on Computer Vision, Glasgow, UK."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Dong, J., Cong, Y., Sun, G., Ma, B., and Wang, L. (2021, January 2\u20139). I3dol: Incremental 3d object learning without catastrophic forgetting. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i7.16756"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"103621","DOI":"10.1016\/j.cviu.2023.103621","article-title":"Continual learning on 3d point clouds with random compressed rehearsal","volume":"228","author":"Zamorski","year":"2023","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"7486","DOI":"10.1109\/TIP.2021.3106799","article-title":"L3DOC: Lifelong 3D object classification","volume":"30","author":"Liu","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhong, L., and Zhuang, H. (March, January 26). ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning. Proceedings of the 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA.","DOI":"10.1109\/WACV61041.2025.00335"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Chowdhury, T., Cheraghian, A., Ramasinghe, S., Ahmadi, S., Saberi, M., and Rahman, S. (2022, January 23\u201327). Few-shot class-incremental learning for 3d point cloud objects. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-20044-1_12"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Yang, Y., Hayat, M., Jin, Z., Ren, C., and Lei, Y. (2023, January 17\u201324). Geometry and uncertainty-aware 3d point cloud class-incremental semantic segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.02084"},{"key":"ref_21","unstructured":"Boudjoghra, M.E.A., Lahoud, J., Cholakkal, H., Anwer, R.M., Khan, S., and Khan, F.S. (October, January 29). Continual Learning and Unknown Object Discovery in 3D Scenes via Self-distillation. Proceedings of the European Conference on Computer Vision, Milan, Italy."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"126399","DOI":"10.1016\/j.eswa.2025.126399","article-title":"Balanced residual distillation learning for 3D point cloud class-incremental semantic segmentation","volume":"269","author":"Su","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Cermelli, F., Mancini, M., Bulo, S.R., Ricci, E., and Caputo, B. (2020, January 13\u201319). Modeling the background for incremental learning in semantic segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00925"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Douillard, A., Chen, Y., Dapogny, A., and Cord, M. (2021, January 20\u201325). Plop: Learning without forgetting for continual semantic segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00403"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lin, Z., Wang, Z., and Zhang, Y. (2022, January 23\u201327). Continual semantic segmentation via structure preserving and projected feature alignment. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-19818-2_20"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhang, C.B., Xiao, J.W., Liu, X., Chen, Y.C., and Cheng, M.M. (2022, January 18\u201324). Representation compensation networks for continual semantic segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00692"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Xiao, J.W., Zhang, C.B., Feng, J., Liu, X., van de Weijer, J., and Cheng, M.M. (2023, January 17\u201324). Endpoints weight fusion for class incremental semantic segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00696"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Armeni, I., Sener, O., Zamir, A.R., Jiang, H., Brilakis, I., Fischer, M., and Savarese, S. (2016, January 27\u201330). 3d semantic parsing of large-scale indoor spaces. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., and Nie\u00dfner, M. (2017, January 21\u201326). ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.261"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/10\/648\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:37:42Z","timestamp":1760600262000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/10\/648"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,16]]},"references-count":29,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["a18100648"],"URL":"https:\/\/doi.org\/10.3390\/a18100648","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,16]]}}}