{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T12:16:10Z","timestamp":1783080970852,"version":"3.54.6"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100008048","name":"Nanjing University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008048","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372223"],"award-info":[{"award-number":["62372223"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20330"],"award-info":[{"award-number":["U24A20330"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113838","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T23:28:28Z","timestamp":1777073308000},"page":"113838","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["Diffusion models with spatial control and attention fusion for incremental few-shot semantic segmentation"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2568-4130","authenticated-orcid":false,"given":"Guangchen","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yirui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shivakumara","family":"Palaiahnakote","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shirong","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113838_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111542","article-title":"Efficient sampling-based Gaussian processes for few-shot semantic segmentation","volume":"164","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113838_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109993","article-title":"Learning foreground information bottleneck for few-shot semantic segmentation","volume":"146","author":"Hu","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113838_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109291","article-title":"Hybrid feature enhancement network for few-shot semantic segmentation","volume":"137","author":"Min","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113838_b4","doi-asserted-by":"crossref","first-page":"5630","DOI":"10.1109\/TMM.2023.3338088","article-title":"CFENet: Boosting few-shot semantic segmentation with complementary feature-enhanced network","volume":"26","author":"Wang","year":"2024","journal-title":"IEEE Trans. Multim."},{"key":"10.1016\/j.patcog.2026.113838_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109018","article-title":"Self-regularized prototypical network for few-shot semantic segmentation","volume":"133","author":"Ding","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113838_b6","first-page":"18","article-title":"CLOSER: towards better representation learning for few-shot class-incremental learning","volume":"vol. 15107","author":"Oh","year":"2024"},{"key":"10.1016\/j.patcog.2026.113838_b7","doi-asserted-by":"crossref","unstructured":"G. Shi, Y. Wu, J. Liu, S. Wan, W. Wang, T. Lu, Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation, in: Proceedings of the ACM International Conference on Multimedia, 2022, pp. 5547\u20135556.","DOI":"10.1145\/3503161.3548218"},{"key":"10.1016\/j.patcog.2026.113838_b8","doi-asserted-by":"crossref","unstructured":"R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, High-Resolution Image Synthesis with Latent Diffusion Models, in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2022, pp. 10674\u201310685.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.patcog.2026.113838_b9","doi-asserted-by":"crossref","unstructured":"J. Kim, H. Cho, J. Kim, Y.Y. Tiruneh, S. Baek, SDDGR: Stable Diffusion-Based Deep Generative Replay for Class Incremental Object Detection, in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2024, pp. 28772\u201328781.","DOI":"10.1109\/CVPR52733.2024.02718"},{"key":"10.1016\/j.patcog.2026.113838_b10","first-page":"142","article-title":"DiffClass: Diffusion-based class incremental learning","volume":"vol. 15145","author":"Meng","year":"2024"},{"key":"10.1016\/j.patcog.2026.113838_b11","series-title":"Diffusion model meets non-exemplar class-incremental learning and beyond","author":"Zhang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113838_b12","doi-asserted-by":"crossref","unstructured":"M. Le, T.V. Nguyen, T. Le, T. Do, M.N. Do, M. Tran, MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation, in: Proceedings of AAAI Conference on Artificial Intelligence, 2024, pp. 2874\u20132881.","DOI":"10.1609\/aaai.v38i3.28068"},{"key":"10.1016\/j.patcog.2026.113838_b13","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.1109\/TIP.2025.3551648","article-title":"Diffusion model is secretly a training-free open vocabulary semantic segmenter","volume":"34","author":"Wang","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113838_b14","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume":"vol. 70","author":"Finn","year":"2017"},{"key":"10.1016\/j.patcog.2026.113838_b15","unstructured":"S. Ravi, H. Larochelle, Optimization as a Model for Few-Shot Learning, in: Proceedings of the International Conference on Learning Representations, 2017."},{"key":"10.1016\/j.patcog.2026.113838_b16","doi-asserted-by":"crossref","unstructured":"K. Lee, S. Maji, A. Ravichandran, S. Soatto, Meta-Learning With Differentiable Convex Optimization, in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 10657\u201310665.","DOI":"10.1109\/CVPR.2019.01091"},{"key":"10.1016\/j.patcog.2026.113838_b17","unstructured":"W. Chen, Y. Liu, Z. Kira, Y.F. Wang, J. Huang, A Closer Look at Few-shot Classification, in: Proceedings of the International Conference on Learning Representations, 2019."},{"key":"10.1016\/j.patcog.2026.113838_b18","doi-asserted-by":"crossref","unstructured":"Y. Chen, J. Hsieh, X. Li, M. Chang, Pushing the Limit of Fine-Tuning for Few-Shot Learning: Where Feature Reusing Meets Cross-Scale Attention, in: Proceedings of AAAI Conference on Artificial Intelligence, 2024, pp. 11434\u201311442.","DOI":"10.1609\/aaai.v38i10.29024"},{"key":"10.1016\/j.patcog.2026.113838_b19","doi-asserted-by":"crossref","first-page":"6501","DOI":"10.1109\/TMM.2024.3352921","article-title":"Query-guided prototype evolution network for few-shot segmentation","volume":"26","author":"Cong","year":"2024","journal-title":"IEEE Trans. Multim."},{"key":"10.1016\/j.patcog.2026.113838_b20","doi-asserted-by":"crossref","first-page":"8874","DOI":"10.1109\/TMM.2024.3383276","article-title":"Dual-guided frequency prototype network for few-shot semantic segmentation","volume":"26","author":"Wen","year":"2024","journal-title":"IEEE Trans. Multim."},{"key":"10.1016\/j.patcog.2026.113838_b21","doi-asserted-by":"crossref","unstructured":"H. Liu, Y. Wang, X. Zhang, F. Zhang, W. Wang, F. Ma, H. Yu, Multi-Label Few-Shot Image Classification via Pairwise Feature Augmentation and Flexible Prompt Learning, in: Proceedings of AAAI Conference on Artificial Intelligence, 2025, pp. 5433\u20135441.","DOI":"10.1609\/aaai.v39i5.32578"},{"key":"10.1016\/j.patcog.2026.113838_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112441","article-title":"Buffer-free class-incremental learning with out-of-distribution detection","volume":"172","author":"Gupta","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113838_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110943","article-title":"Class incremental learning with self-supervised pre-training and prototype learning","volume":"157","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113838_b24","doi-asserted-by":"crossref","first-page":"8038","DOI":"10.1109\/TMM.2024.3374573","article-title":"Visual-textual attribute learning for class-incremental facial expression recognition","volume":"26","author":"Lv","year":"2024","journal-title":"IEEE Trans. Multim."},{"key":"10.1016\/j.patcog.2026.113838_b25","doi-asserted-by":"crossref","unstructured":"Z. Qiu, Y. Xu, F. Meng, H. Li, L. Xu, Q. Wu, Dual-Consistency Model Inversion for Non-Exemplar Class Incremental Learning, in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2024, pp. 24025\u201324035.","DOI":"10.1109\/CVPR52733.2024.02268"},{"key":"10.1016\/j.patcog.2026.113838_b26","doi-asserted-by":"crossref","unstructured":"A. Agarwal, B. Banerjee, F. Cuzzolin, S. Chaudhuri, Semantics-Driven Generative Replay for Few-Shot Class Incremental Learning, in: Proceedings of the ACM International Conference on Multimedia, 2022, pp. 5246\u20135254.","DOI":"10.1145\/3503161.3548160"},{"key":"10.1016\/j.patcog.2026.113838_b27","doi-asserted-by":"crossref","unstructured":"F. Cermelli, M. Mancini, S.R. Bul\u00f2, E. Ricci, B. Caputo, Modeling the Background for Incremental Learning in Semantic Segmentation, in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2020, pp. 9230\u20139239.","DOI":"10.1109\/CVPR42600.2020.00925"},{"key":"10.1016\/j.patcog.2026.113838_b28","doi-asserted-by":"crossref","unstructured":"C. Zhang, N. Song, G. Lin, Y. Zheng, P. Pan, Y. Xu, Few-Shot Incremental Learning With Continually Evolved Classifiers, in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2021, pp. 12455\u201312464.","DOI":"10.1109\/CVPR46437.2021.01227"},{"key":"10.1016\/j.patcog.2026.113838_b29","doi-asserted-by":"crossref","first-page":"5561","DOI":"10.1109\/TMM.2023.3336243","article-title":"Gradient-semantic compensation for incremental semantic segmentation","volume":"26","author":"Cong","year":"2024","journal-title":"IEEE Trans. Multim."},{"key":"10.1016\/j.patcog.2026.113838_b30","doi-asserted-by":"crossref","first-page":"3841","DOI":"10.1109\/TMM.2022.3167555","article-title":"Continual attentive fusion for incremental learning in semantic segmentation","volume":"25","author":"Yang","year":"2023","journal-title":"IEEE Trans. Multim."},{"key":"10.1016\/j.patcog.2026.113838_b31","doi-asserted-by":"crossref","unstructured":"D.A. Ganea, B. Boom, R. Poppe, Incremental Few-Shot Instance Segmentation, in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2021, pp. 1185\u20131194.","DOI":"10.1109\/CVPR46437.2021.00124"},{"key":"10.1016\/j.patcog.2026.113838_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2025.104317","article-title":"Incremental few-shot instance segmentation via feature enhancement and prototype calibration","volume":"253","author":"Gao","year":"2025","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.patcog.2026.113838_b33","unstructured":"L. Shan, W. Zhou, G. Zhao, Incremental Few Shot Semantic Segmentation via Class-agnostic Mask Proposal and Language-driven Classifier, in: Proceedings of ACM International Conference on Multimedia, 2023, pp. 8561\u20138570."},{"key":"10.1016\/j.patcog.2026.113838_b34","doi-asserted-by":"crossref","unstructured":"A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A.C. Berg, W. Lo, P. Doll\u00e1r, R.B. Girshick, Segment Anything, in: Proceedings of IEEE International Conference on Computer Vision, 2023, pp. 3992\u20134003.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.patcog.2026.113838_b35","unstructured":"A. Radford, J.W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, Learning Transferable Visual Models From Natural Language Supervision, in: Proceedings of International Conference on Machine Learning, 2021, pp. 8748\u20138763."},{"key":"10.1016\/j.patcog.2026.113838_b36","unstructured":"D.P. Kingma, M. Welling, Auto-Encoding Variational Bayes, in: Proceedings of International Conference on Learning Representations, 2014."},{"key":"10.1016\/j.patcog.2026.113838_b37","doi-asserted-by":"crossref","unstructured":"S. Xie, Z. Tu, Holistically-Nested Edge Detection, in: Proceedings of International Conference on Computer Vision, 2015, pp. 1395\u20131403.","DOI":"10.1109\/ICCV.2015.164"},{"key":"10.1016\/j.patcog.2026.113838_b38","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep Residual Learning for Image Recognition, in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778."},{"key":"10.1016\/j.patcog.2026.113838_b39","unstructured":"L. Zhang, A. Rao, M. Agrawala, Adding Conditional Control to Text-to-Image Diffusion Models, in: Proceedings of IEEE International Conference on Computer Vision, 2023, pp. 3836\u20133847."},{"key":"10.1016\/j.patcog.2026.113838_b40","unstructured":"A. Shaban, S. Bansal, Z. Liu, I. Essa, B. Boots, One-Shot Learning for Semantic Segmentation, in: Proceedings of British Machine Vision Conference, 2017."},{"issue":"2","key":"10.1016\/j.patcog.2026.113838_b41","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (VOC) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113838_b42","first-page":"297","article-title":"Simultaneous detection and segmentation","volume":"vol. 8695","author":"Hariharan","year":"2014"},{"key":"10.1016\/j.patcog.2026.113838_b43","doi-asserted-by":"crossref","unstructured":"T. Lin, M. Maire, S.J. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll\u00e1r, C.L. Zitnick, Microsoft COCO: Common Objects in Context, in: Proceedings of European Conference on Computer Vision, 2014, pp. 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"10.1016\/j.patcog.2026.113838_b44","doi-asserted-by":"crossref","unstructured":"F. Cermelli, M. Mancini, Y. Xian, Z. Akata, B. Caputo, Prototype-based Incremental Few-Shot Semantic Segmentation, in: Proceedings of British Machine Vision Conference, 2021, p. 155.","DOI":"10.5244\/C.35.139"},{"key":"10.1016\/j.patcog.2026.113838_b45","doi-asserted-by":"crossref","first-page":"9175","DOI":"10.1109\/TMM.2024.3387743","article-title":"Partial-tuning based mixed-modal prototypes for few-shot classification","volume":"26","author":"Su","year":"2024","journal-title":"IEEE Trans. Multim."},{"key":"10.1016\/j.patcog.2026.113838_b46","doi-asserted-by":"crossref","unstructured":"A. B\u00e4r, N. Houlsby, M. Dehghani, Frozen Feature Augmentation for Few-Shot Image Classification, in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2024, pp. 16046\u201316057.","DOI":"10.1109\/CVPR52733.2024.01519"},{"key":"10.1016\/j.patcog.2026.113838_b47","doi-asserted-by":"crossref","unstructured":"Z. Ma, Z. Chen, T. Zheng, X. Luo, Z. Jia, X. Xu, Few-Shot Fine-Grained Image Classification with Progressively Feature Refinement and Continuous Relationship Modeling, in: Proceedings of AAAI Conference on Artificial Intelligence, 2025, pp. 6036\u20136044.","DOI":"10.1609\/aaai.v39i6.32645"},{"key":"10.1016\/j.patcog.2026.113838_b48","doi-asserted-by":"crossref","unstructured":"J. He, Gradient Reweighting: Towards Imbalanced Class-Incremental Learning, in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2024, pp. 16668\u201316677.","DOI":"10.1109\/CVPR52733.2024.01577"},{"key":"10.1016\/j.patcog.2026.113838_b49","doi-asserted-by":"crossref","first-page":"4419","DOI":"10.1109\/TIP.2024.3434475","article-title":"Model attention expansion for few-shot class-incremental learning","volume":"33","author":"Wang","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113838_b50","first-page":"244","article-title":"Advancing incremental few-shot semantic segmentation via semantic-guided relation alignment and adaptation","volume":"vol. 14554","author":"Zhou","year":"2024"},{"key":"10.1016\/j.patcog.2026.113838_b51","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2025.104323","article-title":"Incremental few-shot instance segmentation without fine-tuning on novel classes","volume":"254","author":"Zhang","year":"2025","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.patcog.2026.113838_b52","unstructured":"Y. Wu, Y. Xia, H. Li, L. Yuan, J. Chen, J. Liu, T. Lu, S. Wan, Deconfound Semantic Shift and Incompleteness in Incremental Few-shot Semantic Segmentation, in: Proceedings of AAAI Conference on Artificial Intelligence, 2025, pp. 8478\u20138486."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008034?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008034?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T11:20:12Z","timestamp":1783077612000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326008034"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":52,"alternative-id":["S0031320326008034"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113838","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Diffusion models with spatial control and attention fusion for incremental few-shot semantic segmentation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113838","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113838"}}