{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:22:58Z","timestamp":1782404578045,"version":"3.54.5"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62566012"],"award-info":[{"award-number":["62566012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Science and Technology Projects of Guizhou Province","award":["QKHJCZK2023YB143"],"award-info":[{"award-number":["QKHJCZK2023YB143"]}]},{"name":"Natural Science Research Project of Education Department of Guizhou Province","award":["QJJ2023061 and QJJ2023012"],"award-info":[{"award-number":["QJJ2023061 and QJJ2023012"]}]},{"name":"Guizhou Province Postgraduate Education Teaching Reform Project","award":["2024YJSJGXM041"],"award-info":[{"award-number":["2024YJSJGXM041"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>Fine-tuning has emerged as a popular technique in the field of transfer learning, demonstrating remarkable achievements in various data-scarce tasks. The performance of fine-tuning in deep convolutional neural networks depends on the selection of which parameters to fine-tune and freeze. However, it is difficult to determine which parameters in the pre-trained model need to be fine-tuned for a new task. This article proposes a filter-level discrete optimization model to identify the filter subset for fine-tuning, a core step of filter selection coding optimization. Due to the huge search space of the filter fine-tuning problem, we propose a filter interactivity decomposition strategy to find a valid search subspace (a smaller search subspace containing the optimal solution) by dividing the entire filter fine-tuning problem into multiple suboptimization problems. Based on the decomposition strategy, we design a microscale-searching transfer optimization algorithm, which solves each subproblem by searching the valid search subspace instead of the original search space of the filter fine-tuning problem. To verify the validity of the proposed algorithm, extensive experiments are conducted on seven publicly available image classification datasets: Stanford Dogs, MIT Indoors, Caltech 256-30, Caltech 256-60, Aircraft, UCF-101, and Omniglot. Experimental results show that the proposed method significantly improves the fine-tuning accuracy while effectively reducing the filter fine-tuning problem scale. Moreover, the proposed algorithm outperforms the state-of-the-art fine-tuning methods on the fine-tuning problem for transfer learning.<\/jats:p>","DOI":"10.1145\/3787456","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T10:06:38Z","timestamp":1768817198000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Microscale-Searching Optimization for Transfer Learning-Based Filter Fine-Tuning"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7671-0278","authenticated-orcid":false,"given":"Le","family":"Feng","sequence":"first","affiliation":[{"name":"Guizhou Minzu University, Guiyang, China and Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1163-3298","authenticated-orcid":false,"given":"Fujian","family":"Feng","sequence":"additional","affiliation":[{"name":"Guizhou Minzu University, Guiyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3063-0869","authenticated-orcid":false,"given":"Li","family":"Xiao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6064-072X","authenticated-orcid":false,"given":"Mian","family":"Tan","sequence":"additional","affiliation":[{"name":"Guizhou Minzu University, Guiyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1617-4147","authenticated-orcid":false,"given":"Han","family":"Huang","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9197-8575","authenticated-orcid":false,"given":"Yinong","family":"Wang","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,2,19]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2025.3558861"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02712"},{"issue":"3","key":"e_1_3_1_5_2","first-page":"3239","article-title":"User-specific adaptive fine-tuning for cross-domain recommendations","volume":"35","author":"Chen Lei","year":"2023","unstructured":"Lei Chen, Fajie Yuan, Jiaxi Yang, Xiangnan He, Chengming Li, and Min Yang. 2023. User-specific adaptive fine-tuning for cross-domain recommendations. IEEE Transactions on Knowledge and Data Engineering 35, 3 (2023), 3239\u20133252.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_34"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CEC45853.2021.9504912"},{"key":"e_1_3_1_8_2","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:1701.08734. Retrieved from https:\/\/arxiv.org\/abs\/1701.08734"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.115"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_1_11_2","unstructured":"Gregory Griffin Alex Holub and Pietro Perona. 2007. Caltech-256 Object Category Dataset. California Institute of Technology."},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00494"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3166225"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2024.3365101"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2921547"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-64165-3"},{"key":"e_1_3_1_17_2","first-page":"3030","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Jang Yunhun","year":"2019","unstructured":"Yunhun Jang, Hankook Lee, Sung Ju Hwang, and Jinwoo Shin. 2019. Learning what and where to transfer. In Proceedings of the International Conference on Machine Learning. PMLR, 3030\u20133039."},{"key":"e_1_3_1_18_2","volume-title":"Proceedings of the CVPR Workshop on Fine-Grained Visual Categorization (FGVC)","volume":"2","author":"Khosla Aditya","year":"2011","unstructured":"Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao, and Fei-Fei Li. 2011. Novel dataset for fine-grained image categorization: Stanford dogs. In Proceedings of the CVPR Workshop on Fine-Grained Visual Categorization (FGVC), Vol. 2."},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3050"},{"key":"e_1_3_1_20_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Lee Yoonho","year":"2023","unstructured":"Yoonho Lee, Annie S. Chen, Fahim Tajwar, Ananya Kumar, Huaxiu Yao, Percy Liang, and Chelsea Finn. 2023. Surgical fine-tuning improves adaptation to distribution shifts. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_1_21_2","first-page":"97","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Long Mingsheng","year":"2015","unstructured":"Mingsheng Long, Yue Cao, Jianmin Wang, and Michael Jordan. 2015. Learning transferable features with deep adaptation networks. In Proceedings of the International Conference on Machine Learning. PMLR, 97\u2013105."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02168"},{"key":"e_1_3_1_23_2","unstructured":"Subhransu Maji Esa Rahtu Juho Kannala Matthew Blaschko and Andrea Vedaldi. 2013. Fine-grained visual classification of aircraft. arXiv:1306.5151. Retrieved from https:\/\/arxiv.org\/abs\/1306.5151"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.051"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CEC48606.2020.9185501"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.5555\/3600270.3602281"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3059669"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16358"},{"key":"e_1_3_1_31_2","unstructured":"Albert Susanto Herman Tjeng Wawan Cenggoro Suharjito and Bens Pardamean. 2020. Transfer-learning-aware neuro-evolution for diseases detection in chest X-ray images. arXiv:2004.07136. Retrieved from https:\/\/arxiv.org\/abs\/2004.07136"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3582297"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3034343"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889779"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02313"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3328060"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2025.3577813"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2021.3097937"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2025.112868"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.749"},{"key":"e_1_3_1_43_2","first-page":"2825","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Xuhong L. I.","year":"2018","unstructured":"L. I. Xuhong, Yves Grandvalet, and Franck Davoine. 2018. Explicit inductive bias for transfer learning with convolutional networks. In Proceedings of the International Conference on Machine Learning. PMLR, 2825\u20132834."},{"key":"e_1_3_1_44_2","first-page":"3320","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems","author":"Yosinski Jason","year":"2014","unstructured":"Jason Yosinski, Jeff Clune, Yoshua Bengio, and Hod Lipson. 2014. How transferable are features in deep neural networks? In Proceedings of the 27th International Conference on Neural Information Processing Systems, 3320\u20133328."},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110528"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3210927"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3237085"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3787456","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T12:33:29Z","timestamp":1772800409000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3787456"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,19]]},"references-count":47,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3787456"],"URL":"https:\/\/doi.org\/10.1145\/3787456","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,19]]},"assertion":[{"value":"2024-12-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}