{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T16:10:02Z","timestamp":1755879002300,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,19]]},"DOI":"10.1145\/3653804.3656266","type":"proceedings-article","created":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T12:22:26Z","timestamp":1717244546000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised Domain Adaptation Model Based Semantic Segmentation of Transformer Scenes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3472-5912","authenticated-orcid":false,"given":"Chengfu","family":"Sun","sequence":"first","affiliation":[{"name":"College of Computer, Huaiyin Institute of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4527-403X","authenticated-orcid":false,"given":"Hongyan","family":"Fei","sequence":"additional","affiliation":[{"name":"College of Computer, Huaiyin Institute of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1905-8945","authenticated-orcid":false,"given":"Biao","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer, Huaiyin Institute of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6941-7840","authenticated-orcid":false,"given":"Manhao","family":"Yuan","sequence":"additional","affiliation":[{"name":"College of Computer, Huaiyin Institute of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8530-3922","authenticated-orcid":false,"given":"Wenyu","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer, Huaiyin Institute of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1884-8466","authenticated-orcid":false,"given":"Jingsong","family":"Shan","sequence":"additional","affiliation":[{"name":"College of Computer, Huaiyin Institute of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"3361","volume-title":"IEEE Conf. Comput. Vis.Pattern Recog.","author":"Geiger Andreas","unstructured":"Andreas Geiger, Philip Lenz, and Raquel Urtasun. Are we ready for autonomous driving? In IEEE Conf. Comput. Vis.Pattern Recog., pages 3354\u20133361. 1"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.223"},{"key":"e_1_3_2_1_3_1","unstructured":"Tianjiao Li \u00a0Jun Liu \u00a0Wei Zhang. SIPSA-Net: Shift-Invariant Pan Sharpening with Moving Object Alignment for Satellite Imagery."},{"key":"e_1_3_2_1_4_1","volume-title":"Driving in the matrix: Can virtual worlds replace human-generated annotations for real-world tasks?","author":"Johnson-Roberson M.","year":"2016","unstructured":"M. Johnson-Roberson, C. Barto, R. Mehta, S. N. Sridhar, K. Rosaen, and R. Vasudevan, \u201cDriving in the matrix: Can virtual worlds replace human-generated annotations for real-world tasks?\u201d in IEEE Robotics and Automation Society, 2016"},{"key":"e_1_3_2_1_5_1","volume-title":"ICML","author":"Ganin Y.","year":"2015","unstructured":"Y. Ganin and V. Lempitsky. Unsupervised domain adaptation by backpropagation. In ICML, 2015. 2"},{"key":"e_1_3_2_1_6_1","volume-title":"Image to Image Translation for Domain Adaptation. ArXiv e-prints","author":"Murez Z.","year":"2017","unstructured":"Z. Murez, S. Koulouri, D. Kriegman, R. Ramamoorthi, and K. Kim. Image to Image Translation for Domain Adaptation. ArXiv e-prints, 2017. 2"},{"key":"e_1_3_2_1_7_1","volume-title":"Model adaptation: Unsupervised domain adaptation without source data","author":"Li R.","year":"2020","unstructured":"R. Li, Q. Jiao, W. Cao, H.-S. Wong, and S. Wu. Model adaptation: Unsupervised domain adaptation without source data.In The IEEE Conference on Computer Vision and pattern recognition (CVPR), 2020. 8"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00913"},{"key":"e_1_3_2_1_9_1","volume-title":"NIPS","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez,Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NIPS, 2017."},{"key":"e_1_3_2_1_10_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov DirkWeissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly An image is worth 16x16 words: Transformers for image recognition at scale\u2014arXiv preprint."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17027"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01007"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00969"},{"key":"e_1_3_2_1_14_1","volume-title":"NeurIPS","volume":"31","author":"Long M.","year":"2018","unstructured":"M. Long, Z. Cao, J. Wang, and M. I. Jordan. Conditional adversarial domain adaptation. In NeurIPS, volume 31, 2018."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01637"},{"key":"e_1_3_2_1_16_1","first-page":"714","volume-title":"European Conference on Computer Vision.","author":"Lopes L.C.","unstructured":"Chen, L.C., Lopes, R.G., Cheng, B., Collins, M.D., Cubuk, E.D., Zoph, B., Adam, H., Shlens, J.:Na\u00efve student: Leveraging semi-supervised learning in video sequences for urban scene segmentation. In: European Conference on Computer Vision. pp. 695\u2013714. Springer (2020)"},{"key":"e_1_3_2_1_17_1","first-page":"1","article-title":"Domain stylization: A fast covariance matching framework towards domain adaptation","author":"Yu M.Y.","year":"2020","unstructured":"Dundar, A., Liu, M.Y., Yu, Z., Wang, T.C., Zedlewski, J., Kautz, J.: Domain stylization: A fast covariance matching framework towards domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence pp. 1\u20131 (2020).","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"volume-title":"Domain Adaptation for Semantic Segmentation with Maximum Squares Loss. In Proceedings of the IEEE International Conference on Computer Vision (ICCV)","key":"e_1_3_2_1_18_1","unstructured":"Chen, M.; Xue, H.; and Cai, D. 2019. Domain Adaptation for Semantic Segmentation with Maximum Squares Loss. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2090\u20132099."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00154"},{"key":"e_1_3_2_1_20_1","volume-title":"NeurIPS","author":"Kang Guoliang","year":"2020","unstructured":"Guoliang Kang, Yunchao Wei, Yi Yang, and Alex Hauptmann. Pixel-level cycle association: A new perspective for domain adaptive semantic segmentation. In NeurIPS, 2020."},{"key":"e_1_3_2_1_21_1","unstructured":"Yang Zou Zhi ding Yu B. V. K. Vijaya Kumar and Jin song Wang. Unsupervised domain adaptation for semantic segmentation via class-"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00608"},{"key":"e_1_3_2_1_23_1","first-page":"105","volume-title":"International conference on machine learning","author":"Long Mingsheng","unstructured":"Mingsheng Long, Yue Cao, Jianmin Wang, and Michael Jordan. Learning transferable features with deep adaptation networks. In International conference on machine learning, pages 97\u2013105. PMLR, 2015. 1, 2, 6, 7, 8"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"e_1_3_2_1_25_1","volume-title":"One-shot learning of supervised deep convolutional models. In ar Xiv 1312.6204","author":"Hoffman J.","year":"2014","unstructured":"J. Hoffman, E. Tzeng, J. Donahue, Y. Jia, K. Saenko, and T. Darrell. One-shot learning of supervised deep convolutional models. In ar Xiv 1312.6204; presented at ICLR Work shop, 2014. 1, 2"},{"key":"e_1_3_2_1_26_1","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"Yosinski J.","year":"2014","unstructured":"J. Yosinski, J. Clune, Y. Bengio, and H. Lipson, \u201cHow transferable are features in deep neural networks?\u201d in Advances In Neural Information Processing Systems, 2014, pp. 3320\u20133328.","journal-title":"Advances In Neural Information Processing Systems"},{"key":"e_1_3_2_1_27_1","first-page":"105","volume-title":"International conference on machine learning","author":"Long Mingsheng","unstructured":"Mingsheng Long, Yue Cao, Jianmin Wang, and Michael Jordan. Learning transferable features with deep adaptation networks. In International conference on machine learning, pages 97\u2013105. PMLR, 2015. 1, 2, 6, 7, 8."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00262"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00262"},{"key":"e_1_3_2_1_30_1","volume-title":"Uncertainty-aware consistency regularization for crossdomain semantic segmentation. Computer Vision and Image Understanding, page 103448","author":"Zhou Qianyu","year":"2022","unstructured":"Qianyu Zhou, Zhengyang Feng, Qiqi Gu, Guangliang Cheng, Xuequan Lu, Jianping Shi, and Lizhuang Ma. Uncertainty-aware consistency regularization for crossdomain semantic segmentation. Computer Vision and Image Understanding, page 103448, 2022."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"e_1_3_2_1_32_1","first-page":"1389","volume-title":"IEEE Winter Conf. on Applications of Comput. Vis.","author":"Tranheden Wilhelm","year":"2021","unstructured":"Wilhelm Tranheden, Viktor Olsson, Juliano Pinto, and Lennart Svensson. DACS: Domain Adaptation via Crossdomain Mixed Sampling. In IEEE Winter Conf. on Applications of Comput. Vis., pages 1379\u20131389, 2021. 2, 3, 5, 8, 15, 19"},{"key":"e_1_3_2_1_33_1","first-page":"1998","volume-title":"Int. Conf. Mach. Learn.","author":"Hoffman Judy","year":"2018","unstructured":"Judy Hoffman, Eric Tzeng, Taesung Park, Jun-Yan Zhu, Phillip Isola, Kate Saenko, Alexei Efros, and Trevor Darrell. Cycada: Cycle-consistent adversarial domain adaptation. In Int. Conf. Mach. Learn., pages 1989\u20131998, 2018.2, 19"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3064379"},{"key":"e_1_3_2_1_35_1","volume-title":"NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011","author":"Netzer Yuval","year":"2011","unstructured":"Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y. Ng. Reading digits in natural images with unsupervised feature learning. In NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011, 2011. 6"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00780"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00262"},{"key":"e_1_3_2_1_38_1","volume-title":"NIPS","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NIPS, 2017."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00608"},{"key":"e_1_3_2_1_40_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner,Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020. 2, 3"}],"event":{"name":"CVDL 2024: The International Conference on Computer Vision and Deep Learning","acronym":"CVDL 2024","location":"Changsha China"},"container-title":["Proceedings of the International Conference on Computer Vision and Deep Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3653804.3656266","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3653804.3656266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:28:11Z","timestamp":1755876491000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3653804.3656266"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,19]]},"references-count":40,"alternative-id":["10.1145\/3653804.3656266","10.1145\/3653804"],"URL":"https:\/\/doi.org\/10.1145\/3653804.3656266","relation":{},"subject":[],"published":{"date-parts":[[2024,1,19]]},"assertion":[{"value":"2024-06-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}