{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T04:06:46Z","timestamp":1751947606764,"version":"3.41.2"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T00:00:00Z","timestamp":1748304000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T00:00:00Z","timestamp":1748304000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U21A20515","62365014"],"award-info":[{"award-number":["U21A20515","62365014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Open Project of Key Laboratory of Computing Power Network and Information Security","award":["2024PY021"],"award-info":[{"award-number":["2024PY021"]}]},{"name":"Beijing Natural Science Foundation","award":["L231013"],"award-info":[{"award-number":["L231013"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s00371-025-03973-y","type":"journal-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T10:42:45Z","timestamp":1748342565000},"page":"6745-6755","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PDFT: parameter-diminish fine-tuning for transformer-based models"],"prefix":"10.1007","volume":"41","author":[{"given":"Muyang","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Weiliang","family":"Meng","sequence":"additional","affiliation":[]},{"given":"Mingda","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Jiaming","family":"Gu","sequence":"additional","affiliation":[]},{"given":"Yihua","family":"Shao","sequence":"additional","affiliation":[]},{"given":"Changwei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Rongtao","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Zhihao","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,27]]},"reference":[{"key":"3973_CR1","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.: Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3973_CR2","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., et\u00a0al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"3973_CR3","unstructured":"Liu, Y., Zhang, K., Li, Y., Yan, Z., Gao, C., Chen, R., Yuan, Z., Huang, Y., Sun, H., Gao, J., et\u00a0al.: Sora: A review on background, technology, limitations, and opportunities of large vision models. arXiv preprint arXiv:2402.17177 (2024)"},{"key":"3973_CR4","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"3973_CR5","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3973_CR6","doi-asserted-by":"crossref","unstructured":"Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., Kalenichenko, D.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2704\u20132713 (2018)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"3973_CR7","unstructured":"Han, S., Pool, J., Tran, J., Dally, W..: Learning both weights and connections for efficient neural network. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"3973_CR8","unstructured":"Hinton, G., Vinyals, O., Dean, J..: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"3973_CR9","unstructured":"Ma, L., Han, J., Wang, Z., Zhang, D..: Cephgpt-4: an interactive multimodal cephalometric measurement and diagnostic system with visual large language model. arXiv preprint arXiv:2307.07518 (2023)"},{"key":"3973_CR10","unstructured":"Reid, M., Savinov, N., Teplyashin, D., Lepikhin, D., Lillicrap, T., et\u00a0al.: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)"},{"key":"3973_CR11","unstructured":"Xu, J., Zou, X., Huang, K., Chen, Y., Liu, B., Cheng, M., Shi, X., Huang, J.: Easyanimate: a high-performance long video generation method based on transformer architecture. arXiv preprint arXiv:2405.18991 (2024)"},{"key":"3973_CR12","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., et\u00a0al.: High-resolution image synthesis with latent diffusion models. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684\u201310695. IEEE, 6 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3973_CR13","unstructured":"Devlin, J., Chang, M.-W., Lee, K., et\u00a0al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (Dominik)"},{"key":"3973_CR14","unstructured":"Gu, Y., Dong, L., Wei, F., Huang, M.: Minillm: knowledge distillation of large language models. In The Twelfth International Conference on Learning Representations (2024)"},{"key":"3973_CR15","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, Y., Zheng, Z., Li, X., Cheng, M.-M., Hou, Q.: Crosskd: cross-head knowledge distillation for object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pages 16520\u201316530 (2024)","DOI":"10.1109\/CVPR52733.2024.01563"},{"key":"3973_CR16","doi-asserted-by":"crossref","unstructured":"Pham, C., Nguyen, V.-A., Le, T., Phung, D., Carneiro, G., Do, T.-T.: Frequency attention for knowledge distillation. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 2277\u20132286 (2024)","DOI":"10.1109\/WACV57701.2024.00227"},{"key":"3973_CR17","doi-asserted-by":"publisher","first-page":"110422","DOI":"10.1016\/j.patcog.2024.110422","volume":"151","author":"Z Li","year":"2024","unstructured":"Li, Z., Li, X., Yang, L., Song, R., Yang, J., Pan, Z.: Dual teachers for self-knowledge distillation. Pattern Recognit. 151, 110422 (2024)","journal-title":"Pattern Recognit."},{"key":"3973_CR18","doi-asserted-by":"crossref","unstructured":"Bang, G., Choi, K., Kim, J., Kum, D., Choi, J.\u00a0W.: Radardistill: boosting radar-based object detection performance via knowledge distillation from lidar features. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15491\u201315500 (2024)","DOI":"10.1109\/CVPR52733.2024.01467"},{"key":"3973_CR19","doi-asserted-by":"crossref","unstructured":"Xu, R., Wang, C., Sun, J., Xu, S., Meng, W., Zhang, X.: Self correspondence distillation for end-to-end weakly-supervised semantic segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3045\u20133053 (2023)","DOI":"10.1609\/aaai.v37i3.25408"},{"key":"3973_CR20","doi-asserted-by":"crossref","unstructured":"Lin, S., Xie, H., Wang, B., Yu, K., Chang, X., Liang, X., Wang, G.: Knowledge distillation via the target-aware transformer. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10915\u201310924 (2022)","DOI":"10.1109\/CVPR52688.2022.01064"},{"key":"3973_CR21","doi-asserted-by":"crossref","unstructured":"Ni, Y., Koniusz, P., Hartley, R., Nock, R.: Manifold learning benefits gans. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11265\u201311274 (2022)","DOI":"10.1109\/CVPR52688.2022.01098"},{"key":"3973_CR22","doi-asserted-by":"crossref","unstructured":"Ren, S., Gao, Z., Hua, T., Xue, Z., Tian, Y., He, S., Zhao, H.: Co-advise: cross inductive bias distillation. In Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp. 16773\u201316782 (2022)","DOI":"10.1109\/CVPR52688.2022.01627"},{"issue":"1","key":"3973_CR23","first-page":"1929","volume":"15","author":"Nitish Srivastava","year":"2014","unstructured":"Srivastava, Nitish, Hinton, Geoffrey, Krizhevsky, Alex, et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"3973_CR24","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., et\u00a0al. Curriculum learning. In Proceedings of the 26th annual international conference on machine learning, pp. 41\u201348 (2009)","DOI":"10.1145\/1553374.1553380"},{"key":"3973_CR25","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: Lvis: a dataset for large vocabulary instance segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"3973_CR26","doi-asserted-by":"crossref","unstructured":"Sun, S., Cheng, Y., Gan, Z., Liu, J.: Patient knowledge distillation for bert model compression. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 4323\u20134332 (2019)","DOI":"10.18653\/v1\/D19-1441"},{"key":"3973_CR27","unstructured":"Fan, A., Grave, E., Joulin, A.: Reducing transformer depth on demand with structured dropout. In International Conference on Learning Representations"},{"key":"3973_CR28","doi-asserted-by":"crossref","unstructured":"Xu, C., Zhou, W., Ge, T., et\u00a0al.: BERT-of-theseus: compressing BERT by progressive module replacing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), November (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.633"},{"key":"3973_CR29","unstructured":"Zhao, X., Ding, W., An, Y., et\u00a0al.: Fast segment anything. arXiv preprint arXiv:2306.12156 (2023)"},{"key":"3973_CR30","unstructured":"Zhang, C., Han, D., Qiao, Y., et\u00a0al.: Faster segment anything: towards lightweight sam for mobile applications. arXiv preprint arXiv:2306.14289 (2023)"},{"key":"3973_CR31","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., et\u00a0al.: Microsoft coco: common objects in context. In Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3973_CR32","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., et al.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vis. 88, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"3973_CR33","doi-asserted-by":"crossref","unstructured":"Ma, Z., Li, W., Zhang, M., et\u00a0al.: Htcvit: an effective network for image classification and segmentation based on natural disaster datasets. The Visual Computer, pp. 3285\u20133297 (2023)","DOI":"10.1007\/s00371-023-02954-3"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03973-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03973-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03973-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T11:04:32Z","timestamp":1751886272000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03973-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,27]]},"references-count":33,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["3973"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03973-y","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2025,5,27]]},"assertion":[{"value":"25 April 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 May 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}