{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T02:07:00Z","timestamp":1773281220875,"version":"3.50.1"},"reference-count":115,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T00:00:00Z","timestamp":1731715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T00:00:00Z","timestamp":1731715200000},"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":"publisher","award":["U21B2042"],"award-info":[{"award-number":["U21B2042"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11263-024-02285-3","type":"journal-article","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T13:37:53Z","timestamp":1731764273000},"page":"2287-2310","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2333-1844","authenticated-orcid":false,"given":"Haochen","family":"Wang","sequence":"first","affiliation":[]},{"given":"Yujun","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Jingjing","family":"Fei","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Liwei","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yuxi","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,16]]},"reference":[{"key":"2285_CR1","doi-asserted-by":"crossref","unstructured":"Araslanov, N., & Roth, S. (2021). Self-supervised augmentation consistency for adapting semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 15384\u201315394).","DOI":"10.1109\/CVPR46437.2021.01513"},{"key":"2285_CR2","unstructured":"Balaji, Y., Sankaranarayanan, S., & Chellappa, R. (2018). Metareg: Towards domain generalization using meta-regularization. Advances in Neural Information Processing Systems (NeurIPS), 31, 13."},{"key":"2285_CR3","doi-asserted-by":"crossref","unstructured":"Ben-David, S., Blitzer, J., Crammer, K., & Pereira, F. (2006). Analysis of representations for domain adaptation. Advances in Neural Information Processing Systems (NeurIPS), 19.","DOI":"10.7551\/mitpress\/7503.003.0022"},{"key":"2285_CR4","doi-asserted-by":"crossref","unstructured":"Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., & Krishnan, D. (2017). Unsupervised pixel-level domain adaptation with generative adversarial networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 3722\u20133731).","DOI":"10.1109\/CVPR.2017.18"},{"key":"2285_CR5","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 9650\u20139660).","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2285_CR6","doi-asserted-by":"crossref","unstructured":"Chang, W. -L., Wang, H. -P., Peng, W. -H., & Chiu, W. -C. (2019). All about structure: Adapting structural information across domains for boosting semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 1900\u20131909).","DOI":"10.1109\/CVPR.2019.00200"},{"key":"2285_CR7","doi-asserted-by":"crossref","unstructured":"Chen, C., Xie, W., Huang, W., Rong, Y., Ding, X., Huang, Y., Xu, T., & Huang, J. (2019a). Progressive feature alignment for unsupervised domain adaptation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 627\u2013636).","DOI":"10.1109\/CVPR.2019.00072"},{"key":"2285_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L., Chen, H., Wei, Z., Jin, X., Tan, X., Jin, Y., & Chen, E. (2022a). Reusing the task-specific classifier as a discriminator: Discriminator-free adversarial domain adaptation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7181\u20137190).","DOI":"10.1109\/CVPR52688.2022.00704"},{"key":"2285_CR9","unstructured":"Chen, L., Wei, Z., Jin, X., Chen, H., Zheng, M., Chen, K., & Jin, Y. (2022b). Deliberated domain bridging for domain adaptive semantic segmentation. arXiv preprint[SPACE]arXiv:2209.07695."},{"issue":"4","key":"2285_CR10","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2017). DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 40(4), 834\u2013848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"2285_CR11","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In International conference on machine learning (ICML) (pp. 1597\u20131607)."},{"key":"2285_CR12","doi-asserted-by":"crossref","unstructured":"Chen, X. & He, K. (2021). Exploring simple siamese representation learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 15750\u201315758).","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"2285_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, W., Chen, X., & Gool, L.\u00a0V. (2019b). Learning semantic segmentation from synthetic data: A geometrically guided input-output adaptation approach. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 1841\u20131850).","DOI":"10.1109\/CVPR.2019.00194"},{"key":"2285_CR14","doi-asserted-by":"crossref","unstructured":"Choi, S., Jung, S., Yun, H., Kim, J.\u00a0T., Kim, S., & Choo, J. (2021). Robustnet: Improving domain generalization in urban-scene segmentation via instance selective whitening. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 11580\u201311590).","DOI":"10.1109\/CVPR46437.2021.01141"},{"key":"2285_CR15","doi-asserted-by":"crossref","unstructured":"Chung, I., Kim, D., & Kwak, N. (2022). Maximizing cosine similarity between spatial features for unsupervised domain adaptation in semantic segmentation. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision (WACV) (pp. 1351\u20131360).","DOI":"10.1109\/WACV51458.2022.00204"},{"key":"2285_CR16","unstructured":"Contributors, M. (2020). MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark. https:\/\/github.com\/open-mmlab\/mmsegmentation."},{"key":"2285_CR17","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 3213\u20133223).","DOI":"10.1109\/CVPR.2016.350"},{"key":"2285_CR18","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. In International conference on learning representations (ICLR)."},{"key":"2285_CR19","unstructured":"Dou, Q., Coelho\u00a0de Castro, D., Kamnitsas, K., & Glocker, B. (2019). Domain generalization via model-agnostic learning of semantic features. Advances in Neural Information Processing Systems (NeurIPS), 32."},{"key":"2285_CR20","doi-asserted-by":"crossref","unstructured":"Du, Y., Fu, Z., Liu, Q., & Wang, Y. (2022a). Weakly supervised semantic segmentation by pixel-to-prototype contrast. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 4320\u20134329).","DOI":"10.1109\/CVPR52688.2022.00428"},{"key":"2285_CR21","first-page":"4749","volume":"35","author":"Y Du","year":"2022","unstructured":"Du, Y., Shen, Y., Wang, H., Fei, J., Li, W., Wu, L., Zhao, R., Fu, Z., & Liu, Q. (2022). Learning from future: A novel self-training framework for semantic segmentation. Advances in Neural Information Processing Systems (NeurIPS), 35, 4749\u20134761.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2285_CR22","doi-asserted-by":"crossref","unstructured":"Frigo, M. & Johnson, S.\u00a0G. (1998). FFTW: An adaptive software architecture for the FFT. In Proceedings of the IEEE international conference on acoustics, speech and signal processing) (vol.\u00a03, pp. 1381\u20131384). IEEE.","DOI":"10.1109\/ICASSP.1998.681704"},{"issue":"59","key":"2285_CR23","first-page":"1","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2016). Domain-adversarial training of neural networks. Journal of Machine Learning Research (JMLR), 17(59), 1\u201335.","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"2285_CR24","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. Advances in Neural Information Processing Systems (NeurIPS), 27."},{"key":"2285_CR25","unstructured":"Gretton, A., Sejdinovic, D., Strathmann, H., Balakrishnan, S., Pontil, M., Fukumizu, K., & Sriperumbudur, B.\u00a0K. (2012). Optimal kernel choice for large-scale two-sample tests. Advances in Neural Information Processing Systems (NeurIPS), 25."},{"key":"2285_CR26","first-page":"21271","volume":"33","author":"J-B Grill","year":"2020","unstructured":"Grill, J.-B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P., Buchatskaya, E., Doersch, C., Avila Pires, B., Guo, Z., Gheshlaghi Azar, M., et al. (2020). Bootstrap your own latent-a new approach to self-supervised learning. Advances in Neural Information Processing Systems (NeurIPS), 33, 21271\u201321284.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2285_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 9729\u20139738).","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2285_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2285_CR29","unstructured":"Hoffman, J., Tzeng, E., Park, T., Zhu, J. -Y., Isola, P., Saenko, K., Efros, A., & Darrell, T. (2018). CyCADA: Cycle-consistent adversarial domain adaptation. In International conference on machine learning (ICML) (pp. 1989\u20131998)."},{"key":"2285_CR30","unstructured":"Hoffman, J., Wang, D., Yu, F., & Darrell, T. (2016). FCNs in the wild: Pixel-level adversarial and constraint-based adaptation. arXiv preprint[SPACE]arXiv:1612.02649."},{"key":"2285_CR31","doi-asserted-by":"crossref","unstructured":"Hong, W., Wang, Z., Yang, M., & Yuan, J. (2018). Conditional generative adversarial network for structured domain adaptation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 1335\u20131344).","DOI":"10.1109\/CVPR.2018.00145"},{"key":"2285_CR32","doi-asserted-by":"crossref","unstructured":"Hoyer, L., Dai, D., & Van\u00a0Gool, L. (2022a). DAFormer: Improving network architectures and training strategies for domain-adaptive semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 9924\u20139935).","DOI":"10.1109\/CVPR52688.2022.00969"},{"key":"2285_CR33","doi-asserted-by":"crossref","unstructured":"Hoyer, L., Dai, D., & Van\u00a0Gool, L. (2022b). HRDA: Context-aware high-resolution domain-adaptive semantic segmentation. In European conference on computer vision (ECCV) (pp. 372\u2013391).","DOI":"10.1007\/978-3-031-20056-4_22"},{"key":"2285_CR34","doi-asserted-by":"crossref","unstructured":"Hoyer, L., Dai, D., Wang, H., & Van\u00a0Gool, L. (2023). Mic: Masked image consistency for context-enhanced domain adaptation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 11721\u201311732).","DOI":"10.1109\/CVPR52729.2023.01128"},{"key":"2285_CR35","doi-asserted-by":"crossref","unstructured":"Hu, H., Cui, J., & Wang, L. (2021). Region-aware contrastive learning for semantic segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 16291\u201316301).","DOI":"10.1109\/ICCV48922.2021.01598"},{"key":"2285_CR36","doi-asserted-by":"crossref","unstructured":"Huang, J., Guan, D., Xiao, A., & Lu, S. (2021a). FSDR: Frequency space domain randomization for domain generalization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 6891\u20136902).","DOI":"10.1109\/CVPR46437.2021.00682"},{"key":"2285_CR37","first-page":"3635","volume":"34","author":"J Huang","year":"2021","unstructured":"Huang, J., Guan, D., Xiao, A., & Lu, S. (2021). Model adaptation: Historical contrastive learning for unsupervised domain adaptation without source data. In Advances in Neural Information Processing Systems (NeurIPS), 34, 3635\u20133649.","journal-title":"In Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2285_CR38","doi-asserted-by":"crossref","unstructured":"Huang, J., Guan, D., Xiao, A., Lu, S., & Shao, L. (2022). Category contrast for unsupervised domain adaptation in visual tasks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 1203\u20131214).","DOI":"10.1109\/CVPR52688.2022.00127"},{"key":"2285_CR39","doi-asserted-by":"crossref","unstructured":"Huang, L., Zhou, Y., Zhu, F., Liu, L., & Shao, L. (2019). Iterative normalization: Beyond standardization towards efficient whitening. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 4874\u20134883).","DOI":"10.1109\/CVPR.2019.00501"},{"key":"2285_CR40","doi-asserted-by":"crossref","unstructured":"Huang, X., & Belongie, S. (2017). Arbitrary style transfer in real-time with adaptive instance normalization. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 1501\u20131510).","DOI":"10.1109\/ICCV.2017.167"},{"key":"2285_CR41","unstructured":"Jackson, P. T., Abarghouei, A. A., Bonner, S., Breckon, T. P., & Obara, B. (2019). Style augmentation: data augmentation via style randomization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshop (CVPRW), (vol. 6, pp. 10\u201311)."},{"key":"2285_CR42","unstructured":"Jung, A.\u00a0B., Wada, K., Crall, J., Tanaka, S., Graving, J., Reinders, C., Yadav, S., Banerjee, J., Vecsei, G., Kraft, A., Rui, Z., Borovec, J., Vallentin, C., Zhydenko, S., Pfeiffer, K., Cook, B., Fern\u00e1ndez, I., De\u00a0Rainville, F.-M., Weng, C.-H., Ayala-Acevedo, A., Meudec, R., & Laporte, M. (2020). imgaug. https:\/\/github.com\/aleju\/imgaug. Accessed February 01, 2020."},{"key":"2285_CR43","unstructured":"Kang, G., Wei, Y., Yang, Y., Zhuang, Y., & Hauptmann, A. (2020). Pixel-level cycle association: A new perspective for domain adaptive semantic segmentation. Advances in neural information processing systems (NeurIPS) (pp. 3569\u20133580)."},{"key":"2285_CR44","doi-asserted-by":"crossref","unstructured":"Kundu, J.\u00a0N., Kulkarni, A., Singh, A., Jampani, V., & Babu, R.\u00a0V. (2021). Generalize then adapt: Source-free domain adaptive semantic segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 7046\u20137056).","DOI":"10.1109\/ICCV48922.2021.00696"},{"issue":"11","key":"2285_CR45","first-page":"2579","volume":"9","author":"GH Laurens Van der Maaten","year":"2008","unstructured":"Laurens Van der Maaten, G. H. (2008). Visualizing data using t-SNE. Journal of Machine Learning Research (JMLR), 9(11), 2579\u20132605.","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"2285_CR46","doi-asserted-by":"crossref","unstructured":"Lee, C. -Y., Batra, T., Baig, M. H., & Ulbricht, D. (2019). Sliced Wasserstein discrepancy for unsupervised domain adaptation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 10285\u201310295).","DOI":"10.1109\/CVPR.2019.01053"},{"key":"2285_CR47","doi-asserted-by":"crossref","unstructured":"Li, D., Yang, Y., Song, Y. -Z., & Hospedales, T.\u00a0M. (2018a). Learning to generalize: Meta-learning for domain generalization. In Proceedings of the AAAI conference on artificial intelligence (AAAI) (vol. 32).","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"2285_CR48","doi-asserted-by":"crossref","unstructured":"Li, D., Zhang, J., Yang, Y., Liu, C., Song, Y. -Z., & Hospedales, T.\u00a0M. (2019a). Episodic training for domain generalization. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 1446\u20131455).","DOI":"10.1109\/ICCV.2019.00153"},{"key":"2285_CR49","doi-asserted-by":"crossref","unstructured":"Li, H., Pan, S.\u00a0J., Wang, S., & Kot, A.\u00a0C. (2018b). Domain generalization with adversarial feature learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 5400\u20135409).","DOI":"10.1109\/CVPR.2018.00566"},{"key":"2285_CR50","doi-asserted-by":"crossref","unstructured":"Li, R., Li, S., He, C., Zhang, Y., Jia, X., & Zhang, L. (2022). Class-balanced pixel-level self-labeling for domain adaptive semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 11593\u201311603).","DOI":"10.1109\/CVPR52688.2022.01130"},{"key":"2285_CR51","unstructured":"Li, Y., Liang, F., Zhao, L., Cui, Y., Ouyang, W., Shao, J., Yu, F., & Yan, J. (2021). Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm. In International conference on learning representations (ICLR)."},{"key":"2285_CR52","doi-asserted-by":"crossref","unstructured":"Li, Y., Tian, X., Gong, M., Liu, Y., Liu, T., Zhang, K., & Tao, D. (2018c). Deep domain generalization via conditional invariant adversarial networks. In European conference on computer vision (ECCV) (pp. 624\u2013639)","DOI":"10.1007\/978-3-030-01267-0_38"},{"key":"2285_CR53","unstructured":"Li, Y., Yang, Y., Zhou, W., & Hospedales, T. (2019b). Feature-critic networks for heterogeneous domain generalization. In International conference on machine learning (ICML) (pp. 3915\u20133924)."},{"key":"2285_CR54","doi-asserted-by":"crossref","unstructured":"Li, Y., Yuan, L., & Vasconcelos, N. (2019c). Bidirectional learning for domain adaptation of semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 6936\u20136945).","DOI":"10.1109\/CVPR.2019.00710"},{"key":"2285_CR55","doi-asserted-by":"crossref","unstructured":"Lian, Q., Lv, F., Duan, L., & Gong, B. (2019). Constructing self-motivated pyramid curriculums for cross-domain semantic segmentation: A non-adversarial approach. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 6758\u20136767).","DOI":"10.1109\/ICCV.2019.00686"},{"key":"2285_CR56","unstructured":"Liu, S., Zhi, S., Johns, E., & Davison, A.\u00a0J. (2022). Bootstrapping semantic segmentation with regional contrast. In International conference on learning representations (ICLR)."},{"key":"2285_CR57","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015a). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 3431\u20133440).","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2285_CR58","unstructured":"Long, M., Cao, Y., Wang, J., & Jordan, M. (2015b). Learning transferable features with deep adaptation networks. In International conference on machine learning (ICML) (pp. 97\u2013105)."},{"key":"2285_CR59","unstructured":"Long, M., Cao, Z., Wang, J., & Jordan, M.\u00a0I. (2018). Conditional adversarial domain adaptation. Advances in Neural Information Processing Systems (NeurIPS), 31."},{"key":"2285_CR60","unstructured":"Long, M., Zhu, H., Wang, J., & Jordan, M.\u00a0I. (2016). Unsupervised domain adaptation with residual transfer networks. Advances in Neural Information Processing Systems (NeurIPS), 29."},{"key":"2285_CR61","unstructured":"Loshchilov, I., & Hutter, F. (2019). Decoupled weight decay regularization. In International conference on learning representations (ICLR)."},{"issue":"8","key":"2285_CR62","first-page":"3940","volume":"44","author":"Y Luo","year":"2021","unstructured":"Luo, Y., Liu, P., Zheng, L., Guan, T., Yu, J., & Yang, Y. (2021). Category-level adversarial adaptation for semantic segmentation using purified features. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 44(8), 3940\u20133956.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"2285_CR63","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zheng, L., Guan, T., Yu, J., & Yang, Y. (2019). Taking a closer look at domain shift: Category-level adversaries for semantics consistent domain adaptation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 2507\u20132516).","DOI":"10.1109\/CVPR.2019.00261"},{"key":"2285_CR64","doi-asserted-by":"crossref","unstructured":"Lv, F., Liang, T., Chen, X., & Lin, G. (2020). Cross-domain semantic segmentation via domain-invariant interactive relation transfer. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 4334\u20134343).","DOI":"10.1109\/CVPR42600.2020.00439"},{"key":"2285_CR65","doi-asserted-by":"crossref","unstructured":"Mei, K., Zhu, C., Zou, J., & Zhang, S. (2020). Instance adaptive self-training for unsupervised domain adaptation. In European conference on computer vision (ECCV) (pp. 415\u2013430).","DOI":"10.1007\/978-3-030-58574-7_25"},{"key":"2285_CR66","unstructured":"Michaelis, C., Mitzkus, B., Geirhos, R., Rusak, E., Bringmann, O., Ecker, A.\u00a0S., Bethge, M., & Brendel, W. (2019). Benchmarking robustness in object detection: Autonomous driving when winter is coming. arXiv preprint[SPACE]arXiv:1907.07484."},{"key":"2285_CR67","doi-asserted-by":"crossref","unstructured":"Motiian, S., Piccirilli, M., Adjeroh, D.\u00a0A., & Doretto, G. (2017). Unified deep supervised domain adaptation and generalization. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 5715\u20135725).","DOI":"10.1109\/ICCV.2017.609"},{"key":"2285_CR68","doi-asserted-by":"crossref","unstructured":"Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., & Kim, K. (2018). Image to image translation for domain adaptation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 4500\u20134509).","DOI":"10.1109\/CVPR.2018.00473"},{"key":"2285_CR69","unstructured":"Nowozin, S., Cseke, B., & Tomioka, R. (2016). f-GAN: Training generative neural samplers using variational divergence minimization. Advances in Neural Information Processing Systems (NeurIPS), 29."},{"key":"2285_CR70","unstructured":"Oord, A. v.\u00a0d., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv preprint[SPACE]arXiv:1807.03748."},{"key":"2285_CR71","doi-asserted-by":"crossref","unstructured":"Pan, F., Shin, I., Rameau, F., Lee, S., & Kweon, I.\u00a0S. (2020). Unsupervised intra-domain adaptation for semantic segmentation through self-supervision. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 3764\u20133773).","DOI":"10.1109\/CVPR42600.2020.00382"},{"key":"2285_CR72","doi-asserted-by":"crossref","unstructured":"Pan, X., Luo, P., Shi, J., & Tang, X. (2018). Two at once: Enhancing learning and generalization capacities via ibn-net. In European conference on computer vision (ECCV) (pp. 464\u2013479).","DOI":"10.1007\/978-3-030-01225-0_29"},{"key":"2285_CR73","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., & Antiga, L. (2019). PyTorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems (NeurIPS), 32."},{"key":"2285_CR74","doi-asserted-by":"crossref","unstructured":"Peng, D., Lei, Y., Hayat, M., Guo, Y., & Li, W. (2022). Semantic-aware domain generalized segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 2594\u20132605).","DOI":"10.1109\/CVPR52688.2022.00262"},{"key":"2285_CR75","doi-asserted-by":"publisher","first-page":"107124","DOI":"10.1016\/j.patcog.2019.107124","volume":"100","author":"MM Rahman","year":"2020","unstructured":"Rahman, M. M., Fookes, C., Baktashmotlagh, M., & Sridharan, S. (2020). Correlation-aware adversarial domain adaptation and generalization. Pattern Recognition, 100, 107124.","journal-title":"Pattern Recognition"},{"key":"2285_CR76","doi-asserted-by":"crossref","unstructured":"Richter, S.\u00a0R., Vineet, V., Roth, S., & Koltun, V. (2016). Playing for data: Ground truth from computer games. In European conference on computer vision (ECCV) (pp. 102\u2013118).","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"2285_CR77","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2021). High-resolution image synthesis with latent diffusion models.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2285_CR78","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International conference on medical image computing and computer-assisted intervention (pp. 234\u2013241).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2285_CR79","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D., & Lopez, A.\u00a0M. (2016). The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 3234\u20133243).","DOI":"10.1109\/CVPR.2016.352"},{"key":"2285_CR80","doi-asserted-by":"crossref","unstructured":"Saito, K., Watanabe, K., Ushiku, Y., & Harada, T. (2018). Maximum classifier discrepancy for unsupervised domain adaptation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 3723\u20133732).","DOI":"10.1109\/CVPR.2018.00392"},{"key":"2285_CR81","doi-asserted-by":"crossref","unstructured":"Sankaranarayanan, S., Balaji, Y., Jain, A., Lim, S.\u00a0N., & Chellappa, R. (2018). Learning from synthetic data: Addressing domain shift for semantic segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3752\u20133761.","DOI":"10.1109\/CVPR.2018.00395"},{"key":"2285_CR82","doi-asserted-by":"crossref","unstructured":"Shin, I., Woo, S., Pan, F., & Kweon, I.\u00a0S. (2020). Two-phase pseudo label densification for self-training based domain adaptation. In European conference on computer vision (ECCV) (pp. 532\u2013548).","DOI":"10.1007\/978-3-030-58601-0_32"},{"key":"2285_CR83","doi-asserted-by":"crossref","unstructured":"Sun, B., Feng, J., & Saenko, K. (2016). Return of frustratingly easy domain adaptation. In Proceedings of the AAAI conference on artificial intelligence (AAAI) (vol. 30).","DOI":"10.1609\/aaai.v30i1.10306"},{"key":"2285_CR84","doi-asserted-by":"crossref","unstructured":"Sun, B. & Saenko, K. (2016). Deep coral: Correlation alignment for deep domain adaptation. In European conference on computer vision (ECCV) (pp. 443\u2013450).","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"2285_CR85","unstructured":"Tarvainen, A., & Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in Neural Information Processing Systems (NeurIPS), 30."},{"key":"2285_CR86","doi-asserted-by":"crossref","unstructured":"Tranheden, W., Olsson, V., Pinto, J., & Svensson, L. (2021). Dacs: Domain adaptation via cross-domain mixed sampling. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision (WACV) (pp 1379\u20131389).","DOI":"10.1109\/WACV48630.2021.00142"},{"key":"2285_CR87","doi-asserted-by":"crossref","unstructured":"Tsai, Y. -H., Hung, W. -C., Schulter, S., Sohn, K., Yang, M. -H., & Chandraker, M. (2018). Learning to adapt structured output space for semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 7472\u20137481).","DOI":"10.1109\/CVPR.2018.00780"},{"key":"2285_CR88","doi-asserted-by":"crossref","unstructured":"Tsai, Y. -H., Sohn, K., Schulter, S., & Chandraker, M. (2019). Domain adaptation for structured output via discriminative patch representations. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 1456\u20131465).","DOI":"10.1109\/ICCV.2019.00154"},{"key":"2285_CR89","doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Saenko, K., & Darrell, T. (2017). Adversarial discriminative domain adaptation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 7167\u20137176).","DOI":"10.1109\/CVPR.2017.316"},{"key":"2285_CR90","doi-asserted-by":"crossref","unstructured":"Vu, T. -H., Jain, H., Bucher, M., Cord, M., & P\u00e9rez, P. (2019). Advent: Adversarial entropy minimization for domain adaptation in semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 2517\u20132526).","DOI":"10.1109\/CVPR.2019.00262"},{"key":"2285_CR91","unstructured":"Wang, H., Fan, J., Wang, Y., Song, K., Wang, T., Zhang, X., & Zhang, Z. (2023a). Bootstrap masked visual modeling via hard patches mining. arXiv preprint[SPACE]arXiv:2312.13714."},{"key":"2285_CR92","unstructured":"Wang, H., Fan, J., Wang, Y., Song, K., Wang, T., & Zhang, Z. (2023b). DropPos: Pre-training vision transformers by reconstructing dropped positions. Advances in Neural Information Processing Systems (NeurIPS), 36."},{"key":"2285_CR93","doi-asserted-by":"crossref","unstructured":"Wang, H., Shen, T., Zhang, W., Duan, L. -Y., & Mei, T. (2020a). Classes matter: A fine-grained adversarial approach to cross-domain semantic segmentation. In European conference on computer vision (ECCV) (pp. 642\u2013659).","DOI":"10.1007\/978-3-030-58568-6_38"},{"key":"2285_CR94","doi-asserted-by":"crossref","unstructured":"Wang, H., Song, K., Fan, J., Wang, Y., Xie, J., & Zhang, Z. (2023c). Hard patches mining for masked image modeling. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 10375\u201310385).","DOI":"10.1109\/CVPR52729.2023.01000"},{"key":"2285_CR95","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, Y., Shen, Y., Fan, J., Wang, Y., & Zhang, Z. (2024a). Using unreliable pseudo-labels for label-efficient semantic segmentation. International Journal of Computer Vision (IJCV), 1\u201323.","DOI":"10.1007\/s11263-024-02229-x"},{"key":"2285_CR96","unstructured":"Wang, H., Zheng, A., Zhao, Y., Wang, T., Zheng, G., Zhang, X., & Zhang, Z. (2024b). Reconstructive visual instruction tuning. arXiv preprint[SPACE]arXiv:2410.09575."},{"key":"2285_CR97","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhou, T., Yu, F., Dai, J., Konukoglu, E., & Van\u00a0Gool, L. (2021a). Exploring cross-image pixel contrast for semantic segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 7303\u20137313).","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"2285_CR98","doi-asserted-by":"crossref","unstructured":"Wang, Y., Fei, J., Wang, H., Li, W., Wu, L., Zhao, R., & Shen, Y. (2023d). Balancing logit variation for long-tail semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 19561\u201319573).","DOI":"10.1109\/CVPR52729.2023.01874"},{"key":"2285_CR99","doi-asserted-by":"crossref","unstructured":"Wang, Y., Peng, J., & Zhang, Z. (2021b). Uncertainty-aware pseudo label refinery for domain adaptive semantic segmentation. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 9092\u20139101).","DOI":"10.1109\/ICCV48922.2021.00896"},{"key":"2285_CR100","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, H., Shen, Y., Fei, J., Li, W., Jin, G., Wu, L., Zhao, R., & Le, X. (2022). Semi-supervised semantic segmentation using unreliable pseudo labels. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 4248\u20134257).","DOI":"10.1109\/CVPR52688.2022.00421"},{"key":"2285_CR101","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yu, M., Wei, Y., Feris, R., Xiong, J., Hwu, W.-M., Huang, T.\u00a0S., & Shi, H. (2020b). Differential treatment for stuff and things: A simple unsupervised domain adaptation method for semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 12635\u201312644).","DOI":"10.1109\/CVPR42600.2020.01265"},{"issue":"7","key":"2285_CR102","doi-asserted-by":"publisher","first-page":"9004","DOI":"10.1109\/TPAMI.2023.3237740","volume":"45","author":"B Xie","year":"2023","unstructured":"Xie, B., Li, S., Li, M., Liu, C. H., Huang, G., & Wang, G. (2023). SePiCo: Semantic-guided pixel contrast for domain adaptive semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 45(7), 9004\u20139021.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"2285_CR103","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., & Luo, P. (2021). SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems (NeurIPS), 34, 12077\u201312090.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2285_CR104","doi-asserted-by":"crossref","unstructured":"Yang, Y. & Soatto, S. (2020). FDA: Fourier domain adaptation for semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 4085\u20134095).","DOI":"10.1109\/CVPR42600.2020.00414"},{"key":"2285_CR105","doi-asserted-by":"crossref","unstructured":"Yue, X., Zhang, Y., Zhao, S., Sangiovanni-Vincentelli, A., Keutzer, K., & Gong, B. (2019). Domain randomization and pyramid consistency: Simulation-to-real generalization without accessing target domain data. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV) (pp. 2100\u20132110).","DOI":"10.1109\/ICCV.2019.00219"},{"key":"2285_CR106","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., & Agrawala, M. (2023). Adding conditional control to text-to-image diffusion models.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"2285_CR107","doi-asserted-by":"crossref","unstructured":"Zhang, P., Zhang, B., Zhang, T., Chen, D., Wang, Y., & Wen, F. (2021). Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 12414\u201312424).","DOI":"10.1109\/CVPR46437.2021.01223"},{"key":"2285_CR108","unstructured":"Zhang, Q., Zhang, J., Liu, W., & Tao, D. (2019). Category anchor-guided unsupervised domain adaptation for semantic segmentation. Advances in Neural Information Processing Systems (NeurIPS), 32."},{"key":"2285_CR109","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 2881\u20132890).","DOI":"10.1109\/CVPR.2017.660"},{"key":"2285_CR110","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zhong, Z., Zhao, N., Sebe, N., & Lee, G.\u00a0H. (2022). Style-hallucinated dual consistency learning for domain generalized semantic segmentation. In European conference on computer vision (ECCV) (pp. 535\u2013552). Springer.","DOI":"10.1007\/978-3-031-19815-1_31"},{"key":"2285_CR111","doi-asserted-by":"crossref","unstructured":"Zheng, Z., & Yang, Y. (2021). Rectifying pseudo label learning via uncertainty estimation for domain adaptive semantic segmentation. International Journal of Computer Vision (IJCV), 129(4), 1106\u20131120.","DOI":"10.1007\/s11263-020-01395-y"},{"key":"2285_CR112","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017). Scene parsing through ade20k dataset. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 633\u2013641).","DOI":"10.1109\/CVPR.2017.544"},{"key":"2285_CR113","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Zhuang, C., Lu, X., & Ma, L. (2022). Domain adaptive semantic segmentation with regional contrastive consistency regularization. In Proceedings of the IEEE international conference on multimedia and expo (ICME) (pp. 1\u20136).","DOI":"10.1109\/ICME52920.2022.9859793"},{"key":"2285_CR114","doi-asserted-by":"crossref","unstructured":"Zou, Y., Yu, Z., Kumar, B., & Wang, J. (2018). Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In European conference on computer vision (ECCV) (pp. 289\u2013305).","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"2285_CR115","doi-asserted-by":"crossref","unstructured":"Zou, Y., Yu, Z., Liu, X., Kumar, B., & Wang, J. (2019). Confidence regularized self-training. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 5982\u20135991).","DOI":"10.1109\/ICCV.2019.00608"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02285-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02285-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02285-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T06:01:28Z","timestamp":1744869688000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02285-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,16]]},"references-count":115,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["2285"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02285-3","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,16]]},"assertion":[{"value":"28 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}