{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T17:35:59Z","timestamp":1779903359855,"version":"3.53.1"},"reference-count":137,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:00:00Z","timestamp":1728345600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:00:00Z","timestamp":1728345600000},"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 Foundation of China","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s11263-024-02229-x","type":"journal-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T14:02:33Z","timestamp":1728396153000},"page":"1476-1498","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Using Unreliable Pseudo-Labels for Label-Efficient 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":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujun","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junsong","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,8]]},"reference":[{"key":"2229_CR1","unstructured":"Abramov, A., Bayer, C., and Heller, C. (2020). Keep it simple: Image statistics matching for domain adaptation. arXiv preprint arXiv:2005.12551."},{"key":"2229_CR2","doi-asserted-by":"crossref","unstructured":"Ahn, J. and Kwak, S. (2018). Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2018.00523"},{"key":"2229_CR3","doi-asserted-by":"crossref","unstructured":"Alonso, I., Sabater, A., Ferstl, D., Montesano, L., and Murillo, A.\u00a0C. (2021). Semi-supervised semantic segmentation with pixel-level contrastive learning from a class-wise memory bank. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00811"},{"key":"2229_CR4","doi-asserted-by":"crossref","unstructured":"Araslanov, N. and Roth, S. (2020). Single-stage semantic segmentation from image labels. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00431"},{"key":"2229_CR5","doi-asserted-by":"crossref","unstructured":"Araslanov, N. and Roth, S. (2021). Self-supervised augmentation consistency for adapting semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01513"},{"key":"2229_CR6","doi-asserted-by":"crossref","unstructured":"Arazo, E., Ortego, D., Albert, P., O\u2019Connor, N.\u00a0E., and McGuinness, K. (2020). Pseudo-labeling and confirmation bias in deep semi-supervised learning. In International Joint Conference on Neural Networks (IJCNN.","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"2229_CR7","unstructured":"Bachman, P., Alsharif, O., and Precup, D. (2014). Learning with pseudo-ensembles. NeurIPS."},{"issue":"12","key":"2229_CR8","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). Segnet: A deep convolutional encoder-decoder architecture for image segmentation. TPAMI, 39(12), 2481\u20132495.","journal-title":"TPAMI"},{"key":"2229_CR9","doi-asserted-by":"crossref","unstructured":"Chang, W.-L., Wang, H.-P., Peng, W.-H., and Chiu, W.-C. (2019). All about structure: Adapting structural information across domains for boosting semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2019.00200"},{"key":"2229_CR10","doi-asserted-by":"crossref","unstructured":"Chang, Y.-T., Wang, Q., Hung, W.-C., Piramuthu, R., Tsai, Y.-H., and Yang, M.-H. (2020). Weakly-supervised semantic segmentation via sub-category exploration. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00901"},{"key":"2229_CR11","doi-asserted-by":"crossref","unstructured":"Chen, C., Xie, W., Huang, W., Rong, Y., Ding, X., Huang, Y., Xu, T., and Huang, J. (2019). Progressive feature alignment for unsupervised domain adaptation. In CVPR.","DOI":"10.1109\/CVPR.2019.00072"},{"issue":"1","key":"2229_CR12","first-page":"4991","volume":"13","author":"H Chen","year":"2021","unstructured":"Chen, H., Jin, Y., Jin, G., Zhu, C., & Chen, E. (2021). Semi-supervised semantic segmentation by improving prediction confidence. IEEE Transactions on Neural Networks and Learning Systems, 13(1), 4991\u20135003.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"4","key":"2229_CR13","doi-asserted-by":"crossref","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. TPAMI, 40(4), 834\u2013848.","journal-title":"TPAMI"},{"key":"2229_CR14","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., and Adam, H. (2017b). Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587."},{"key":"2229_CR15","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In ECCV.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"2229_CR16","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M., and Hinton, G. (2020). Big self-supervised models are strong semi-supervised learners. NeurIPS."},{"key":"2229_CR17","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., and He, K. (2021b). An empirical study of training self-supervised vision transformers. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"2229_CR18","doi-asserted-by":"crossref","unstructured":"Chen, X., Yuan, Y., Zeng, G., and Wang, J. (2021c). Semi-supervised semantic segmentation with cross pseudo supervision. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00264"},{"key":"2229_CR19","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.\u00a0G., Kirillov, A., and Girdhar, R. (2022). Masked-attention mask transformer for universal image segmentation. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"2229_CR20","unstructured":"Cheng, B., Schwing, A., and Kirillov, A. (2021). Per-pixel classification is not all you need for semantic segmentation. NeurIPS."},{"key":"2229_CR21","doi-asserted-by":"crossref","unstructured":"Choi, J., Kim, T., and Kim, C. (2019). Self-ensembling with gan-based data augmentation for domain adaptation in semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV.2019.00693"},{"key":"2229_CR22","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. In CVPR.","DOI":"10.1109\/CVPR.2016.350"},{"key":"2229_CR23","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., and Sun, J. (2015). Boxsup: Exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV.2015.191"},{"key":"2229_CR24","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In CVPR.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2229_CR25","unstructured":"DeVries, T. and Taylor, G.\u00a0W. (2017). Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552."},{"key":"2229_CR26","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR."},{"key":"2229_CR27","doi-asserted-by":"crossref","unstructured":"Du, Y., Fu, Z., Liu, Q., and Wang, Y. (2022a). Weakly supervised semantic segmentation by pixel-to-prototype contrast. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00428"},{"key":"2229_CR28","unstructured":"Du, Y., Shen, Y., Wang, H., Fei, J., Li, W., Wu, L., Zhao, R., Fu, Z., and Liu, Q. (2022b). Learning from future: A novel self-training framework for semantic segmentation. NeurIPS."},{"issue":"2","key":"2229_CR29","doi-asserted-by":"crossref","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., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (VOC) challenge. IJCV, 88(2), 303\u2013338.","journal-title":"IJCV"},{"key":"2229_CR30","doi-asserted-by":"crossref","unstructured":"Fan, J., Zhang, Z., Song, C., and Tan, T. (2020a). Learning integral objects with intra-class discriminator for weakly-supervised semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00434"},{"key":"2229_CR31","doi-asserted-by":"crossref","unstructured":"Fan, J., Zhang, Z., and Tan, T. (2020b). Employing multi-estimations for weakly-supervised semantic segmentation. In ECCV.","DOI":"10.1007\/978-3-030-58520-4_20"},{"key":"2229_CR32","volume-title":"Pointly-supervised panoptic segmentation","author":"J Fan","year":"2022","unstructured":"Fan, J., Zhang, Z., & Tan, T. (2022). Pointly-supervised panoptic segmentation. In ECCV: Springer."},{"key":"2229_CR33","doi-asserted-by":"crossref","unstructured":"Fan, J., Zhang, Z., Tan, T., Song, C., and Xiao, J. (2020c). Cian: Cross-image affinity net for weakly supervised semantic segmentation. In AAAI.","DOI":"10.1609\/aaai.v34i07.6705"},{"key":"2229_CR34","unstructured":"French, G., Laine, S., Aila, T., Mackiewicz, M., and Finlayson, G. (2020). Semi-supervised semantic segmentation needs strong, varied perturbations. In BMVC."},{"key":"2229_CR35","doi-asserted-by":"crossref","unstructured":"Gong, R., Li, W., Chen, Y., and Gool, L.\u00a0V. (2019). Dlow: Domain flow for adaptation and generalization. In CVPR.","DOI":"10.1109\/CVPR.2019.00258"},{"key":"2229_CR36","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. NeurIPS."},{"key":"2229_CR37","unstructured":"Grandvalet, Y. and Bengio, Y. (2004). Semi-supervised learning by entropy minimization. NeurIPS."},{"key":"2229_CR38","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Bourdev, L., Maji, S., and Malik, J. (2011). Semantic contours from inverse detectors. In ICCV.","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"2229_CR39","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., and Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2229_CR40","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2229_CR41","unstructured":"Hoffman, J., Tzeng, E., Park, T., Zhu, J.-Y., Isola, P., Saenko, K., Efros, A., and Darrell, T. (2018). Cycada: Cycle-consistent adversarial domain adaptation. In ICML."},{"key":"2229_CR42","unstructured":"Hoffman, J., Wang, D., Yu, F., and Darrell, T. (2016). Fcns in the wild: Pixel-level adversarial and constraint-based adaptation. arXiv preprint arXiv:1612.02649."},{"key":"2229_CR43","doi-asserted-by":"crossref","unstructured":"Hong, W., Wang, Z., Yang, M., and Yuan, J. (2018). Conditional generative adversarial network for structured domain adaptation. In CVPR.","DOI":"10.1109\/CVPR.2018.00145"},{"key":"2229_CR44","doi-asserted-by":"crossref","unstructured":"Hoyer, L., Dai, D., and Van\u00a0Gool, L. (2022). Daformer: Improving network architectures and training strategies for domain-adaptive semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00969"},{"key":"2229_CR45","unstructured":"Hu, H., Wei, F., Hu, H., Ye, Q., Cui, J., and Wang, L. (2021). Semi-supervised semantic segmentation via adaptive equalization learning. NeurIPS."},{"key":"2229_CR46","doi-asserted-by":"crossref","unstructured":"Ji, W., Li, J., Bi, Q., Liu, T., Li, W., and Cheng, L. (2023). Segment anything is not always perfect: An investigation of sam on different real-world applications. arXiv preprint arXiv:2304.05750.","DOI":"10.1007\/s11633-023-1385-0"},{"key":"2229_CR47","doi-asserted-by":"crossref","unstructured":"Jiang, P.-T., Hou, Q., Cao, Y., Cheng, M.-M., Wei, Y., and Xiong, H.-K. (2019). Integral object mining via online attention accumulation. In ICCV.","DOI":"10.1109\/ICCV.2019.00216"},{"key":"2229_CR48","unstructured":"Kang, G., Wei, Y., Yang, Y., Zhuang, Y., and Hauptmann, A. (2020). Pixel-level cycle association: A new perspective for domain adaptive semantic segmentation. NeurIPS."},{"key":"2229_CR49","doi-asserted-by":"crossref","unstructured":"Ke, Z., Qiu, D., Li, K., Yan, Q., and Lau, R.\u00a0W. (2020). Guided collaborative training for pixel-wise semi-supervised learning. In ECCV.","DOI":"10.1007\/978-3-030-58601-0_26"},{"key":"2229_CR50","doi-asserted-by":"crossref","unstructured":"Kim, B., Han, S., and Kim, J. (2021). Discriminative region suppression for weakly-supervised semantic segmentation. In AAAI.","DOI":"10.1609\/aaai.v35i2.16269"},{"key":"2229_CR51","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.\u00a0C., Lo, W.-Y., et\u00a0al. (2023). Segment anything. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2229_CR52","unstructured":"Kr\u00e4henb\u00fchl, P. and Koltun, V. (2011). Efficient inference in fully connected crfs with gaussian edge potentials. NeurIPS."},{"key":"2229_CR53","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al. (2009). Learning multiple layers of features from tiny images."},{"key":"2229_CR54","doi-asserted-by":"crossref","unstructured":"Lee, C.-Y., Batra, T., Baig, M.\u00a0H., and Ulbricht, D. (2019a). Sliced wasserstein discrepancy for unsupervised domain adaptation. In CVPR.","DOI":"10.1109\/CVPR.2019.01053"},{"key":"2229_CR55","unstructured":"Lee, D.-H. et\u00a0al. (2013). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In ICML, volume\u00a03, page 896."},{"key":"2229_CR56","unstructured":"Lee, J., Choi, J., Mok, J., and Yoon, S. (2021a). Reducing information bottleneck for weakly supervised semantic segmentation. NeurIPS."},{"key":"2229_CR57","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, E., Lee, S., Lee, J., and Yoon, S. (2019b). Ficklenet: Weakly and semi-supervised semantic image segmentation using stochastic inference. In CVPR.","DOI":"10.1109\/CVPR.2019.00541"},{"key":"2229_CR58","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, E., and Yoon, S. (2021b). Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00406"},{"key":"2229_CR59","doi-asserted-by":"crossref","unstructured":"Lee, S., Lee, M., Lee, J., and Shim, H. (2021c). Railroad is not a train: Saliency as pseudo-pixel supervision for weakly supervised semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00545"},{"key":"2229_CR60","doi-asserted-by":"crossref","unstructured":"Li, J., Fan, J., and Zhang, Z. (2022a). Towards noiseless object contours for weakly supervised semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01635"},{"key":"2229_CR61","doi-asserted-by":"crossref","unstructured":"Li, R., Jia, X., He, J., Chen, S., and Hu, Q. (2021a). T-svdnet: Exploring high-order prototypical correlations for multi-source domain adaptation. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00984"},{"key":"2229_CR62","doi-asserted-by":"crossref","unstructured":"Li, R., Li, S., He, C., Zhang, Y., Jia, X., and Zhang, L. (2022b). Class-balanced pixel-level self-labeling for domain adaptive semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01130"},{"key":"2229_CR63","doi-asserted-by":"crossref","unstructured":"Li, Y., Kuang, Z., Liu, L., Chen, Y., and Zhang, W. (2021b). Pseudo-mask matters in weakly-supervised semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00688"},{"key":"2229_CR64","doi-asserted-by":"crossref","unstructured":"Li, Y., Yuan, L., and Vasconcelos, N. (2019). Bidirectional learning for domain adaptation of semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2019.00710"},{"key":"2229_CR65","doi-asserted-by":"crossref","unstructured":"Lin, D., Dai, J., Jia, J., He, K., and Sun, J. (2016). Scribblesup: Scribble-supervised convolutional networks for semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2016.344"},{"key":"2229_CR66","unstructured":"Liu, S., Zhi, S., Johns, E., and Davison, A.\u00a0J. (2021). Bootstrapping semantic segmentation with regional contrast. arXiv preprint arXiv:2104.04465."},{"key":"2229_CR67","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015a). Fully convolutional networks for semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2229_CR68","unstructured":"Long, M., Cao, Y., Wang, J., and Jordan, M. (2015b). Learning transferable features with deep adaptation networks. In ICML."},{"key":"2229_CR69","unstructured":"Loshchilov, I. and Hutter, F. (2017). Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101."},{"key":"2229_CR70","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zheng, L., Guan, T., Yu, J., and Yang, Y. (2019). Taking a closer look at domain shift: Category-level adversaries for semantics consistent domain adaptation. In CVPR.","DOI":"10.1109\/CVPR.2019.00261"},{"issue":"1","key":"2229_CR71","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma, J., He, Y., Li, F., Han, L., You, C., & Wang, B. (2024). Segment anything in medical images. Nature Communications, 15(1), 654.","journal-title":"Nature Communications"},{"key":"2229_CR72","doi-asserted-by":"crossref","unstructured":"Mei, K., Zhu, C., Zou, J., and Zhang, S. (2020). Instance adaptive self-training for unsupervised domain adaptation. In ECCV.","DOI":"10.1007\/978-3-030-58574-7_25"},{"key":"2229_CR73","doi-asserted-by":"crossref","unstructured":"Melas-Kyriazi, L. and Manrai, A.\u00a0K. (2021). Pixmatch: Unsupervised domain adaptation via pixelwise consistency training. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01225"},{"key":"2229_CR74","doi-asserted-by":"crossref","unstructured":"Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., and Kim, K. (2018). Image to image translation for domain adaptation. In CVPR.","DOI":"10.1109\/CVPR.2018.00473"},{"key":"2229_CR75","unstructured":"Nowozin, S., Cseke, B., and Tomioka, R. (2016). f-gan: Training generative neural samplers using variational divergence minimization. NeurIPS."},{"key":"2229_CR76","doi-asserted-by":"crossref","unstructured":"Olsson, V., Tranheden, W., Pinto, J., and Svensson, L. (2021). Classmix: Segmentation-based data augmentation for semi-supervised learning. In CVPR.","DOI":"10.1109\/WACV48630.2021.00141"},{"key":"2229_CR77","unstructured":"Oord, A. v.\u00a0d., Li, Y., and Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748."},{"key":"2229_CR78","doi-asserted-by":"crossref","unstructured":"Ouali, Y., Hudelot, C., and Tami, M. (2020). Semi-supervised semantic segmentation with cross-consistency training. In CVPR.","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"2229_CR79","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Chen, L.-C., Murphy, K.\u00a0P., and Yuille, A.\u00a0L. (2015). Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation. In ICCV.","DOI":"10.1109\/ICCV.2015.203"},{"key":"2229_CR80","doi-asserted-by":"crossref","unstructured":"Pinheiro, P.\u00a0O. and Collobert, R. (2015). From image-level to pixel-level labeling with convolutional networks. In CVPR.","DOI":"10.1109\/CVPR.2015.7298780"},{"key":"2229_CR81","doi-asserted-by":"crossref","unstructured":"Richter, S.\u00a0R., Vineet, V., Roth, S., and Koltun, V. (2016). Playing for data: Ground truth from computer games. In ECCV.","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"2229_CR82","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer Assisted Intervention, pages 234\u2013241. Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2229_CR83","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D., and Lopez, A.\u00a0M. (2016). The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes. In CVPR.","DOI":"10.1109\/CVPR.2016.352"},{"key":"2229_CR84","doi-asserted-by":"crossref","unstructured":"Roy, A. and Todorovic, S. (2017). Combining bottom-up, top-down, and smoothness cues for weakly supervised image segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3529\u20133538.","DOI":"10.1109\/CVPR.2017.770"},{"key":"2229_CR85","doi-asserted-by":"crossref","unstructured":"Ru, L., Zhan, Y., Yu, B., and Du, B. (2022). Learning affinity from attention: end-to-end weakly-supervised semantic segmentation with transformers. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01634"},{"key":"2229_CR86","doi-asserted-by":"crossref","unstructured":"Ru, L., Zheng, H., Zhan, Y., and Du, B. (2023). Token contrast for weakly-supervised semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR52729.2023.00302"},{"key":"2229_CR87","doi-asserted-by":"crossref","unstructured":"Saito, K., Watanabe, K., Ushiku, Y., and Harada, T. (2018). Maximum classifier discrepancy for unsupervised domain adaptation. In CVPR.","DOI":"10.1109\/CVPR.2018.00392"},{"key":"2229_CR88","unstructured":"Sajjadi, M., Javanmardi, M., and Tasdizen, T. (2016). Regularization with stochastic transformations and perturbations for deep semi-supervised learning. NeurIPS."},{"key":"2229_CR89","doi-asserted-by":"crossref","unstructured":"Sakaridis, C., Dai, D., and Van\u00a0Gool, L. (2021). Acdc: The adverse conditions dataset with correspondences for semantic driving scene understanding. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"2229_CR90","doi-asserted-by":"crossref","unstructured":"Sankaranarayanan, S., Balaji, Y., Jain, A., Lim, S.\u00a0N., and Chellappa, R. (2018). Learning from synthetic data: Addressing domain shift for semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2018.00395"},{"key":"2229_CR91","unstructured":"Sohn, K., Berthelot, D., Carlini, N., Zhang, Z., Zhang, H., Raffel, C.\u00a0A., Cubuk, E.\u00a0D., Kurakin, A., and Li, C.-L. (2020). Fixmatch: Simplifying semi-supervised learning with consistency and confidence. NeurIPS."},{"key":"2229_CR92","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., and Schmid, C. (2021). Segmenter: Transformer for semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"2229_CR93","doi-asserted-by":"crossref","unstructured":"Su, Y., Sun, R., Lin, G., and Wu, Q. (2021). Context decoupling augmentation for weakly supervised semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00692"},{"key":"2229_CR94","volume-title":"Mining cross-image semantics for weakly supervised semantic segmentation","author":"G Sun","year":"2020","unstructured":"Sun, G., Wang, W., Dai, J., & Van Gool, L. (2020). Mining cross-image semantics for weakly supervised semantic segmentation. In ECCV: Springer."},{"key":"2229_CR95","doi-asserted-by":"crossref","unstructured":"Sun, K., Shi, H., Zhang, Z., and Huang, Y. (2021). Ecs-net: Improving weakly supervised semantic segmentation by using connections between class activation maps. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00719"},{"key":"2229_CR96","unstructured":"Tarvainen, A. and Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. NeurIPS."},{"key":"2229_CR97","doi-asserted-by":"crossref","unstructured":"Tsai, Y.-H., Hung, W.-C., Schulter, S., Sohn, K., Yang, M.-H., and Chandraker, M. (2018). Learning to adapt structured output space for semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2018.00780"},{"key":"2229_CR98","doi-asserted-by":"crossref","unstructured":"Vu, T.-H., Jain, H., Bucher, M., Cord, M., and P\u00e9rez, P. (2019). Advent: Adversarial entropy minimization for domain adaptation in semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2019.00262"},{"key":"2229_CR99","doi-asserted-by":"crossref","unstructured":"Wan, Z., Zhang, B., Chen, D., Zhang, P., Chen, D., Liao, J., and Wen, F. (2020). Bringing old photos back to life. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00282"},{"key":"2229_CR100","unstructured":"Wang, H., Fan, J., Wang, Y., Song, K., Wang, T., and Zhang, Z. (2023a). Droppos: Pre-training vision transformers by reconstructing dropped positions. Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"2229_CR101","doi-asserted-by":"crossref","unstructured":"Wang, H., Shen, T., Zhang, W., Duan, L.-Y., and Mei, T. (2020a). Classes matter: A fine-grained adversarial approach to cross-domain semantic segmentation. In ECCV.","DOI":"10.1007\/978-3-030-58568-6_38"},{"key":"2229_CR102","doi-asserted-by":"crossref","unstructured":"Wang, H., Shen, Y., Fei, J., Li, W., Wu, L., Wang, Y., and Zhang, Z. (2023b). Pulling target to source: A new perspective on domain adaptive semantic segmentation. arXiv preprint arXiv:2305.13752.","DOI":"10.1007\/s11263-024-02285-3"},{"key":"2229_CR103","doi-asserted-by":"crossref","unstructured":"Wang, H., Song, K., Fan, J., Wang, Y., Xie, J., and Zhang, Z. (2023c). Hard patches mining for masked image modeling. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01000"},{"key":"2229_CR104","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhou, T., Yu, F., Dai, J., Konukoglu, E., and Van\u00a0Gool, L. (2021). Exploring cross-image pixel contrast for semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"2229_CR105","unstructured":"Wang, Y., Chen, H., Fan, Y., Sun, W., Tao, R., Hou, W., Wang, R., Yang, L., Zhou, Z., Guo, L.-Z., Qi, H., Wu, Z., Li, Y.-F., Nakamura, S., Ye, W., Savvides, M., Raj, B., Shinozaki, T., Schiele, B., Wang, J., Xie, X., and Zhang, Y. (2022a). Usb: A unified semi-supervised learning benchmark for classification. In NeurIPS."},{"key":"2229_CR106","unstructured":"Wang, Y., Chen, H., Heng, Q., Hou, W., Fan, Y., Wu, Z., Wang, J., Savvides, M., Shinozaki, T., Raj, B., et\u00a0al. (2023d). Freematch: Self-adaptive thresholding for semi-supervised learning. In ICLR."},{"key":"2229_CR107","doi-asserted-by":"crossref","unstructured":"Wang, Y., Fei, J., Wang, H., Li, W., Wu, L., Zhao, R., and Shen, Y. (2023e). Balancing logit variation for long-tail semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01874"},{"key":"2229_CR108","doi-asserted-by":"crossref","unstructured":"Wang, Y., Ma, X., Chen, Z., Luo, Y., Yi, J., and Bailey, J. (2019). Symmetric cross entropy for robust learning with noisy labels. In CVPR.","DOI":"10.1109\/ICCV.2019.00041"},{"key":"2229_CR109","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, H., Shen, Y., Fei, J., Li, W., Jin, G., Wu, L., Zhao, R., and Le, X. (2022b). Semi-supervised semantic segmentation using unreliable pseudo labels. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00421"},{"key":"2229_CR110","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, J., Kan, M., Shan, S., and Chen, X. (2020b). Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"2229_CR111","doi-asserted-by":"crossref","unstructured":"Wei, Y., Feng, J., Liang, X., Cheng, M.-M., Zhao, Y., and Yan, S. (2017). Object region mining with adversarial erasing: A simple classification to semantic segmentation approach. In CVPR.","DOI":"10.1109\/CVPR.2017.687"},{"key":"2229_CR112","doi-asserted-by":"crossref","unstructured":"Wu, T., Huang, J., Gao, G., Wei, X., Wei, X., Luo, X., and Liu, C.\u00a0H. (2021). Embedded discriminative attention mechanism for weakly supervised semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01649"},{"key":"2229_CR113","doi-asserted-by":"crossref","unstructured":"Wu, Z., Wang, X., Gonzalez, J.\u00a0E., Goldstein, T., and Davis, L.\u00a0S. (2019). Ace: Adapting to changing environments for semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV.2019.00221"},{"key":"2229_CR114","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.\u00a0M., and Luo, P. (2021). Segformer: Simple and efficient design for semantic segmentation with transformers. NeurIPS."},{"key":"2229_CR115","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.-T., Hovy, E., and Le, Q.\u00a0V. (2020). Self-training with noisy student improves imagenet classification. In CVPR.","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"2229_CR116","doi-asserted-by":"crossref","unstructured":"Xu, J., De\u00a0Mello, S., Liu, S., Byeon, W., Breuel, T., Kautz, J., and Wang, X. (2022). Groupvit: Semantic segmentation emerges from text supervision. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"2229_CR117","doi-asserted-by":"crossref","unstructured":"Xu, L., Ouyang, W., Bennamoun, M., Boussaid, F., Sohel, F., and Xu, D. (2021a). Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00690"},{"key":"2229_CR118","unstructured":"Xu, Y., Shang, L., Ye, J., Qian, Q., Li, Y.-F., Sun, B., Li, H., and Jin, R. (2021b). Dash: Semi-supervised learning with dynamic thresholding. In ICML."},{"key":"2229_CR119","doi-asserted-by":"crossref","unstructured":"Yang, L., Zhuo, W., Qi, L., Shi, Y., and Gao, Y. (2022). St++: Make self-training work better for semi-supervised semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00423"},{"key":"2229_CR120","doi-asserted-by":"crossref","unstructured":"Yao, Y., Chen, T., Xie, G.-S., Zhang, C., Shen, F., Wu, Q., Tang, Z., and Zhang, J. (2021). Non-salient region object mining for weakly supervised semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00265"},{"key":"2229_CR121","unstructured":"Yu, F. and Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122."},{"key":"2229_CR122","doi-asserted-by":"crossref","unstructured":"Yuan, J., Liu, Y., Shen, C., Wang, Z., and Li, H. (2021). A simple baseline for semi-supervised semantic segmentation with strong data augmentation. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00812"},{"key":"2229_CR123","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.\u00a0J., Chun, S., Choe, J., and Yoo, Y. (2019). Cutmix: Regularization strategy to train strong classifiers with localizable features. In ICCV.","DOI":"10.1109\/ICCV.2019.00612"},{"key":"2229_CR124","doi-asserted-by":"crossref","unstructured":"Zhang, B., Xiao, J., Wei, Y., Sun, M., and Huang, K. (2020a). Reliability does matter: An end-to-end weakly supervised semantic segmentation approach. In AAAI.","DOI":"10.1609\/aaai.v34i07.6971"},{"key":"2229_CR125","doi-asserted-by":"crossref","unstructured":"Zhang, F., Gu, C., Zhang, C., and Dai, Y. (2021a). Complementary patch for weakly supervised semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00715"},{"key":"2229_CR126","doi-asserted-by":"crossref","unstructured":"Zhang, P., Zhang, B., Chen, D., Yuan, L., and Wen, F. (2020b). Cross-domain correspondence learning for exemplar-based image translation. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00519"},{"key":"2229_CR127","doi-asserted-by":"crossref","unstructured":"Zhang, P., Zhang, B., Zhang, T., Chen, D., Wang, Y., and Wen, F. (2021b). Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01223"},{"key":"2229_CR128","unstructured":"Zhang, Q., Zhang, J., Liu, W., and Tao, D. (2019). Category anchor-guided unsupervised domain adaptation for semantic segmentation. NeurIPS."},{"key":"2229_CR129","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2017). Pyramid scene parsing network. In CVPR.","DOI":"10.1109\/CVPR.2017.660"},{"key":"2229_CR130","doi-asserted-by":"crossref","unstructured":"Zhao, X., Vemulapalli, R., Mansfield, P.\u00a0A., Gong, B., Green, B., Shapira, L., and Wu, Y. (2021). Contrastive learning for label efficient semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01045"},{"key":"2229_CR131","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P.\u00a0H., et\u00a0al. (2021). Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"2229_CR132","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Yuan, B., Wu, H., Yuan, Z., Peng, J., and Wang, Y.-X. (2021). Pixel contrastive-consistent semi-supervised semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00718"},{"key":"2229_CR133","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., and Torralba, A. (2016). Learning deep features for discriminative localization. In CVPR.","DOI":"10.1109\/CVPR.2016.319"},{"key":"2229_CR134","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Zhuang, C., Lu, X., and Ma, L. (2021). Domain adaptive semantic segmentation with regional contrastive consistency regularization. arXiv preprint arXiv:2110.05170.","DOI":"10.1109\/ICME52920.2022.9859793"},{"key":"2229_CR135","doi-asserted-by":"crossref","unstructured":"Zou, Y., Yu, Z., Kumar, B., and Wang, J. (2018). Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In ECCV.","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"2229_CR136","unstructured":"Zou, Y., Zhang, Z., Zhang, H., Li, C.-L., Bian, X., Huang, J.-B., and Pfister, T. (2020). Pseudoseg: Designing pseudo labels for semantic segmentation. In ICLR."},{"key":"2229_CR137","doi-asserted-by":"crossref","unstructured":"Zuo, S., Yu, Y., Liang, C., Jiang, H., Er, S., Zhang, C., Zhao, T., and Zha, H. (2021). Self-training with differentiable teacher. arXiv preprint arXiv:2109.07049.","DOI":"10.18653\/v1\/2022.findings-naacl.70"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02229-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02229-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02229-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T21:57:22Z","timestamp":1743371842000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02229-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,8]]},"references-count":137,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["2229"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02229-x","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,8]]},"assertion":[{"value":"3 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}