{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:09:53Z","timestamp":1776888593730,"version":"3.51.2"},"reference-count":77,"publisher":"Association for Computing Machinery (ACM)","issue":"8","license":[{"start":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T00:00:00Z","timestamp":1718236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0119004"],"award-info":[{"award-number":["2022ZD0119004"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62272468, 62003256, 62027813, U1801265, 62293543, 62322605, 62036005, 62202015 and U21B2048"],"award-info":[{"award-number":["62272468, 62003256, 62027813, U1801265, 62293543, 62322605, 62036005, 62202015 and U21B2048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key-Area Research and Development Program of Shaanxi Province","award":["2023-ZDISF-41"],"award-info":[{"award-number":["2023-ZDISF-41"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2024,8,31]]},"abstract":"<jats:p>\n            Saliency prediction (SAP) plays a crucial role in simulating the visual perception function of human beings. In practical situations, humans can quickly grasp saliency extraction in new image domains. However, current SAP methods mainly concentrate on training models in single domains, which do not effectively handle diverse content and styles present in real-world images. As a result, it would be of great significance if SAP models could efficiently adjust to new image domains. To this end, this article aims to design SAP models that can imitate the incremental learning ability of human beings on multiple image domains and name domain-incremental saliency prediction (DISAP). To make a tradeoff between preventing the forgetting of historical domains and achieving high performance on new domains, we propose a progressively updated domain incremental encoder. This encoder consists of a domain-sharing branch and a domain-specific branch. The domain-sharing branch includes a feature selection mechanism to preserve crucial parameters after fine-tuning the model on each current domain. The remaining parameters are reserved to absorb knowledge from future domains. Furthermore, to capture the unique characteristics of each domain with relatively low computational overhead, we introduce a lightweight design to construct the domain-specific branch, enabling effective adaptation to new domains. Extensive experiments are conducted on multiple domain-incremental learning settings formed by four saliency prediction datasets, including Salicon, MIT1003, the art subset of CAT2000, and WebSal. The results demonstrate that our method outperforms existing methods significantly. The code is available at\u00a0\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/KaIi-github\/DIL4SAP\">https:\/\/github.com\/KaIi-github\/DIL4SAP<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3661312","type":"journal-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T10:59:48Z","timestamp":1713956388000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Progressive Adapting and Pruning: Domain-Incremental Learning for Saliency Prediction"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8140-6374","authenticated-orcid":false,"given":"Kaihui","family":"Yang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China and Nanchang University, Nanchang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5545-7217","authenticated-orcid":false,"given":"Junwei","family":"Han","sequence":"additional","affiliation":[{"name":"Nanchang University, Nanchang, China and Hefei Comprehensive National Science Center, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5205-6319","authenticated-orcid":false,"given":"Guangyu","family":"Guo","sequence":"additional","affiliation":[{"name":"Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8805-9792","authenticated-orcid":false,"given":"Chaowei","family":"Fang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1912-6135","authenticated-orcid":false,"given":"Yingzi","family":"Fan","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7546-9052","authenticated-orcid":false,"given":"Lechao","family":"Cheng","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8369-8886","authenticated-orcid":false,"given":"Dingwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Brain and Artificial Intelligence Lab, Northwestern Polytechnical University, Xi'an, China and Department of Clinical Immunology, Xijing Hospital, The Fourth Military Medical University, Xi'an, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,13]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00399"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.753"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00625"},{"key":"e_1_3_2_5_2","article-title":"Cat2000: A large scale fixation dataset for boosting saliency research","author":"Borji Ali","year":"2015","unstructured":"Ali Borji and Laurent Itti. 2015. Cat2000: A large scale fixation dataset for boosting saliency research. arXiv preprint arXiv:1505.03581 (2015).","journal-title":"arXiv preprint arXiv:1505.03581"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2210727"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900174"},{"issue":"7","key":"e_1_3_2_9_2","first-page":"3366","article-title":"A continual learning survey: Defying forgetting in classification tasks","volume":"44","author":"Lange Matthias De","year":"2021","unstructured":"Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Ale\u0161 Leonardis, Gregory Slabaugh, and Tinne Tuytelaars. 2021. A continual learning survey: Defying forgetting in classification tasks. IEEE Trans. Pattern Anal. Mach. Intell. 44, 7 (2021), 3366\u20133385.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00528"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3384-y"},{"key":"e_1_3_2_13_2","article-title":"PathNet: Evolution channels gradient descent in super neural networks","author":"Fernando Chrisantha","year":"2017","unstructured":"Chrisantha Fernando, Dylan Banarse, Charles Blundell, Yori Zwols, David Ha, Andrei A. Rusu, Alexander Pritzel, and Daan Wierstra. 2017. PathNet: Evolution channels gradient descent in super neural networks. arXiv preprint arXiv:1701.08734 (2017).","journal-title":"arXiv preprint arXiv:1701.08734"},{"key":"e_1_3_2_14_2","first-page":"761","volume-title":"IEEE Winter Conference on Applications of Computer Vision","author":"Garg Prachi","year":"2022","unstructured":"Prachi Garg, Rohit Saluja, Vineeth N. Balasubramanian, Chetan Arora, Anbumani Subramanian, and C. V. Jawahar. 2022. Multi-domain incremental learning for semantic segmentation. In IEEE Winter Conference on Applications of Computer Vision. 761\u2013771."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2949562"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2013.12.011"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3570507"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"e_1_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Lai Jiang Zhe Wang Mai Xu and Zulin Wang. 2019. Image saliency prediction in transformed domain: A deep complex neural network method. In Association for the Advancement of Artificial Intelligence Vol. 33. AAAI Press 8521\u20138528.","DOI":"10.1609\/aaai.v33i01.33018521"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298710"},{"key":"e_1_3_2_23_2","unstructured":"Tilke Judd Fr\u00e9do Durand and Antonio Torralba. 2012. A benchmark of computational models of saliency to predict human fixations. MIT Computer Science and Artificial Intelligence Laboratory Technical Report (2012)."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01869"},{"key":"e_1_3_2_26_2","article-title":"Adam: A method for stochastic optimization","author":"Kingma Diederik P.","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","unstructured":"James Kirkpatrick Razvan Pascanu Neil Rabinowitz Joel Veness Guillaume Desjardins Andrei A. Rusu Kieran Milan John Quan Tiago Ramalho Agnieszka Grabska-Barwinska Demis Hassabis Claudia Clopath Dharshan Kumaran and Raia Hadsell. 2017. Overcoming catastrophic forgetting in neural networks. In Proceedings of the National Academy of Sciences 114 13 (2017) 3521\u20133526.","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.05.004"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.513"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00363"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_20"},{"issue":"4","key":"e_1_3_2_34_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3576045","article-title":"Distilled meta-learning for multi-class incremental learning","volume":"19","author":"Liu Hao","year":"2023","unstructured":"Hao Liu, Zhaoyu Yan, Bing Liu, Jiaqi Zhao, Yong Zhou, and Abdulmotaleb El Saddik. 2023. Distilled meta-learning for multi-class incremental learning. ACM Trans. Multim. Comput., Commun. Applic. 19, 4 (2023), 1\u201316.","journal-title":"ACM Trans. Multim. Comput., Commun. Applic."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126916"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01226"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3215887"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_30"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_5"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"e_1_3_2_41_2","first-page":"3001","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition","author":"Mirza M. Jehanzeb","year":"2022","unstructured":"M. Jehanzeb Mirza, Marc Masana, Horst Possegger, and Horst Bischof. 2022. An efficient domain-incremental learning approach to drive in all weather conditions. In IEEE Conference on Computer Vision and Pattern Recognition. 3001\u20133011."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.01.014"},{"key":"e_1_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Nabil Ouerhani Roman Von Wartburg Heinz Hugli and Rene Muri. 2004. Empirical validation of the saliency-based model of visual attention. In Electron. Lett. Comput. Vis. Image Anal. 3 1 (2004) 13\u201324.","DOI":"10.5565\/rev\/elcvia.66"},{"key":"e_1_3_2_44_2","first-page":"4453","article-title":"Continual deep learning by functional regularisation of memorable past","volume":"33","author":"Pan Pingbo","year":"2020","unstructured":"Pingbo Pan, Siddharth Swaroop, Alexander Immer, Runa Eschenhagen, Richard Turner, and Mohammad Emtiyaz E. Khan. 2020. Continual deep learning by functional regularisation of memorable past. Annual Conf. Neural Inf. Process. Syst. 33 (2020), 4453\u20134464.","journal-title":"Annual Conf. Neural Inf. Process. Syst."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"e_1_3_2_46_2","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. Annual Conference on Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_47_2","article-title":"Continual normalization: Rethinking batch normalization for online continual learning","author":"Pham Quang","year":"2022","unstructured":"Quang Pham, Chenghao Liu, and Steven Hoi. 2022. Continual normalization: Rethinking batch normalization for online continual learning. arXiv preprint arXiv:2203.16102 (2022).","journal-title":"arXiv preprint arXiv:2203.16102"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2750080"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2005.08.011"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026543900054"},{"key":"e_1_3_2_52_2","first-page":"4548","volume-title":"International Conference on Machine Learning","author":"Serra Joan","year":"2018","unstructured":"Joan Serra, Didac Suris, Marius Miron, and Alexandros Karatzoglou. 2018. Overcoming catastrophic forgetting with hard attention to the task. In International Conference on Machine Learning. PMLR, 4548\u20134557."},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_3"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00568-3"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"issue":"9","key":"e_1_3_2_57_2","first-page":"4555","article-title":"A survey on curriculum learning","volume":"44","author":"Wang Xin","year":"2021","unstructured":"Xin Wang, Yudong Chen, and Wenwu Zhu. 2021. A survey on curriculum learning. IEEE Trans. Pattern Anal. Mach. Intell. 44, 9 (2021), 4555\u20134576.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"08","key":"e_1_3_2_58_2","article-title":"Spring research presentation: A theoretical foundation for inductive transfer","volume":"1","author":"West Jeremy","year":"2007","unstructured":"Jeremy West, Dan Ventura, and Sean Warnick. 2007. Spring research presentation: A theoretical foundation for inductive transfer. Brig. Young Univ., College Phys. Math. Sci. 1, 08 (2007).","journal-title":"Brig. Young Univ., College Phys. Math. Sci."},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3095064"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475443"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612207"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.12.006"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3573202"},{"key":"e_1_3_2_65_2","first-page":"3987","volume-title":"International Conference on Machine Learning","author":"Zenke Friedemann","year":"2017","unstructured":"Friedemann Zenke, Ben Poole, and Surya Ganguli. 2017. Continual learning through synaptic intelligence. In International Conference on Machine Learning. PMLR, 3987\u20133995."},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00692"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2495161"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2881114"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2900649"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1112-4"},{"key":"e_1_3_2_71_2","doi-asserted-by":"crossref","unstructured":"Dingwen Zhang Hao Li Wenyuan Zeng Chaowei Fang Lechao Cheng Ming-Ming Cheng and Junwei Han. 2023. Weakly supervised semantic segmentation via alternate self-dual teaching. IEEE Trans. Image Process. (2023) 1\u20131.","DOI":"10.1109\/TIP.2023.3343112"},{"key":"e_1_3_2_72_2","first-page":"484","volume-title":"IEEE Winter Conference on Applications of Computer Vision","author":"Zhang Yifeng","year":"2021","unstructured":"Yifeng Zhang, Ming Jiang, and Qi Zhao. 2021. Saliency prediction with external knowledge. In IEEE Winter Conference on Applications of Computer Vision. 484\u2013493."},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3072041"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_4"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082316"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3179021"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.107"},{"issue":"3","key":"e_1_3_2_78_2","first-page":"3738","article-title":"Salient object detection via integrity learning","volume":"45","author":"Zhuge Mingchen","year":"2022","unstructured":"Mingchen Zhuge, Deng-Ping Fan, Nian Liu, Dingwen Zhang, Dong Xu, and Ling Shao. 2022. Salient object detection via integrity learning. IEEE Trans. Pattern Anal. Mach. Intell. 45, 3 (2022), 3738\u20133752.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3661312","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3661312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:02Z","timestamp":1750291442000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3661312"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,13]]},"references-count":77,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8,31]]}},"alternative-id":["10.1145\/3661312"],"URL":"https:\/\/doi.org\/10.1145\/3661312","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,13]]},"assertion":[{"value":"2023-11-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-12","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}