{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:15:24Z","timestamp":1787937324534,"version":"build-2784847793"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T00:00:00Z","timestamp":1580342400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T00:00:00Z","timestamp":1580342400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s11263-020-01293-3","type":"journal-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T13:02:37Z","timestamp":1580389357000},"page":"1736-1749","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":90,"title":["Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning"],"prefix":"10.1007","volume":"128","author":[{"given":"Xiang","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sifei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huimin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4848-2304","authenticated-orcid":false,"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,1,30]]},"reference":[{"key":"1293_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, J., & Kwak, S. (2018). Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 4981\u20134990).","DOI":"10.1109\/CVPR.2018.00523"},{"key":"1293_CR2","doi-asserted-by":"crossref","unstructured":"Bearman, A., Russakovsky, O., Ferrari, V., & Fei-Fei, L. (2016). What\u2019s the point: Semantic segmentation with point supervision. In Proceedings of European conference on computer vision (ECCV) (pp. 549\u2013565).","DOI":"10.1007\/978-3-319-46478-7_34"},{"key":"1293_CR3","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Torresani, L., Stella, X. Y., & Shi, J. (2017). Convolutional random walk networks for semantic image segmentation. In Proceedings of IEEE conference on computer vision and pattern recognition (CVPR) (pp. 858\u2013866).","DOI":"10.1109\/CVPR.2017.650"},{"issue":"4","key":"1293_CR4","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 40(4), 834\u2013848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)"},{"key":"1293_CR5","unstructured":"Chen, L. C., Papandreou, G., Schroff, F., & Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587"},{"key":"1293_CR6","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., & Sun, J. (2015) Boxsup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In Proceedings of IEEE international conference on computer vision (ICCV) (pp. 1635\u20131643).","DOI":"10.1109\/ICCV.2015.191"},{"issue":"2","key":"1293_CR7","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (VOC) challenge. International Journal of Computer Vision (IJCV), 88(2), 303\u2013338.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1293_CR8","doi-asserted-by":"crossref","unstructured":"Fan, R., Cheng, M. M., Hou, Q., Mu, T. J., Wang, J., & Hu, S. M. (2019). S4net: Single stage salient-instance segmentation. In Proceedings of IEEE conference on computer vision and pattern recognition (CVPR) (pp. 6103\u20136112).","DOI":"10.1109\/CVPR.2019.00626"},{"key":"1293_CR9","doi-asserted-by":"crossref","unstructured":"Fan, R., Hou, Q., Cheng, M. M., Yu, G., Martin, R. R., & Hu, S. M. (2018). Associating inter-image salient instances for weakly supervised semantic segmentation. In Proceedings of European conference on computer vision (ECCV) (pp. 367\u2013383).","DOI":"10.1007\/978-3-030-01240-3_23"},{"issue":"2","key":"1293_CR10","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"PF Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P. F., & Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. International Journal of Computer Vision (IJCV), 59(2), 167\u2013181.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1293_CR11","doi-asserted-by":"publisher","first-page":"1074","DOI":"10.1109\/43.159993","volume":"11","author":"L Hagen","year":"1992","unstructured":"Hagen, L., & Kahng, A. B. (1992). New spectral methods for ratio cut partitioning and clustering. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 11, 1074\u20131085.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"1293_CR12","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Bourdev, L., Maji, S., & Malik, J. (2011). Semantic contours from inverse detectors. In Proceedings of IEEE international conference on computer vision (ICCV) (pp. 991\u2013998).","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"1293_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1293_CR14","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Wang, J., Liu, W., & Wang, J. (2018). Weakly-supervised semantic segmentation network with deep seeded region growing. In Proceedings of IEEE conference on computer vision and pattern recognition (CVPR) (pp. 7014\u20137023).","DOI":"10.1109\/CVPR.2018.00733"},{"key":"1293_CR15","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014). Caffe: Convolutional architecture for fast feature embedding. In Proceedings of ACM international conference on Multimedia (ACM MM) (pp. 675\u2013678).","DOI":"10.1145\/2647868.2654889"},{"issue":"12","key":"1293_CR16","doi-asserted-by":"publisher","first-page":"2395","DOI":"10.1364\/JOSAA.4.002395","volume":"4","author":"D Kersten","year":"1987","unstructured":"Kersten, D. (1987). Predictability and redundancy of natural images. JOSA A, 4(12), 2395\u20132400.","journal-title":"JOSA A"},{"key":"1293_CR17","doi-asserted-by":"crossref","unstructured":"Khoreva, A., Benenson, R., Hosang, J., Hein, M., & Schiele, B. (2017). Simple does it: Weakly supervised instance and semantic segmentation. In Proceedings of IEEE conference on computer vision and pattern recognition (CVPR) (pp. 876\u2013885).","DOI":"10.1109\/CVPR.2017.181"},{"key":"1293_CR18","doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., & Lampert, C. H. (2016). Seed, expand and constrain: Three principles for weakly-supervised image segmentation. In Proceedings of European conference on computer vision (ECCV) (pp. 695\u2013711).","DOI":"10.1007\/978-3-319-46493-0_42"},{"key":"1293_CR19","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1109\/TPAMI.2007.1177","volume":"30","author":"A Levin","year":"2008","unstructured":"Levin, A., Lischinski, D., & Weiss, Y. (2008). A closed-form solution to natural image matting. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 30, 228\u2013242.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)"},{"key":"1293_CR20","doi-asserted-by":"crossref","unstructured":"Lin, D., Dai, J., Jia, J., He, K., & Sun, J. (2016). Scribblesup: Scribble-supervised convolutional networks for semantic segmentation. In Proceedings of IEEE conference on computer vision and pattern recognition (CVPR) (pp. 3159\u20133167).","DOI":"10.1109\/CVPR.2016.344"},{"key":"1293_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft COCO: Common objects in context. In Proceedings of European conference on computer vision (ECCV) (pp. 740\u2013755).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1293_CR22","doi-asserted-by":"crossref","unstructured":"Liu, S., De\u00a0Mello, S., Gu, J., Zhong, G., Yang, M. H., & Kautz, J. (2017). Learning affinity via spatial propagation networks. In Proceedings of annual conference on neural information processing systems (NeurIPS) (pp. 1520\u20131530).","DOI":"10.1007\/978-3-319-70139-4"},{"key":"1293_CR23","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of IEEE conference on computer vision and pattern recognition (CVPR) (pp. 3431\u20133440).","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1293_CR24","doi-asserted-by":"crossref","unstructured":"Maire, M., Narihira, T., & Yu, S. X. (2016). Affinity CNN: Learning pixel-centric pairwise relations for figure\/ground embedding. In Proceedings of IEEE conference on computer vision and pattern recognition (CVPR) (pp. 174\u2013182).","DOI":"10.1109\/CVPR.2016.26"},{"key":"1293_CR25","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Chen, L. C., Murphy, K. P., & Yuille, A. L. (2015). Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation. In Proceedings of IEEE international conference on computer vision (ICCV) (pp. 1742\u20131750).","DOI":"10.1109\/ICCV.2015.203"},{"key":"1293_CR26","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., & Darrell, T. (2015). Constrained convolutional neural networks for weakly supervised segmentation. In Proceedings of IEEE international conference on computer vision (ICCV) (pp. 1796\u20131804).","DOI":"10.1109\/ICCV.2015.209"},{"key":"1293_CR27","unstructured":"Pathak, D., Shelhamer, E., Long, J., & Darrell, T. (2014). Fully convolutional multi-class multiple instance learning. arXiv preprint arXiv:1412.7144."},{"key":"1293_CR28","doi-asserted-by":"crossref","unstructured":"Pinheiro, P. O., & Collobert, R. (2015). From image-level to pixel-level labeling with convolutional networks. In Proceedings of IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1713\u20131721).","DOI":"10.1109\/CVPR.2015.7298780"},{"key":"1293_CR29","doi-asserted-by":"crossref","unstructured":"Qi, X., Liu, Z., Shi, J., Zhao, H., & Jia, J. (2016). Augmented feedback in semantic segmentation under image level supervision. In Proceedings of European conference on computer vision (ECCV) (pp. 90\u2013105).","DOI":"10.1007\/978-3-319-46484-8_6"},{"key":"1293_CR30","doi-asserted-by":"crossref","unstructured":"Roy, A., & Todorovic, S. (2017). Combining bottom-up, top-down, and smoothness cues for weakly supervised image segmentation. In Proceedings of IEEE conference on computer vision and pattern recognition (CVPR) (pp. 3529\u20133538).","DOI":"10.1109\/CVPR.2017.770"},{"key":"1293_CR31","doi-asserted-by":"crossref","unstructured":"Saleh, F., Aliakbarian, M. S., Salzmann, M., Petersson, L., Gould, S., & Alvarez, J. M. (2016). Built-in foreground\/background prior for weakly-supervised semantic segmentation. In Proceedings of European Conference on Computer Vision (ECCV) (pp. 413\u2013432).","DOI":"10.1007\/978-3-319-46484-8_25"},{"issue":"8","key":"1293_CR32","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J Shi","year":"2000","unstructured":"Shi, J., & Malik, J. (2000). Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 22(8), 888\u2013905.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)"},{"key":"1293_CR33","doi-asserted-by":"crossref","unstructured":"Shimoda, W., & Yanai, K. (2016). Distinct class-specific saliency maps for weakly supervised semantic segmentation. In Proceedings of European conference on computer vision (ECCV) (pp. 218\u2013234).","DOI":"10.1007\/978-3-319-46493-0_14"},{"key":"1293_CR34","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"issue":"1","key":"1293_CR35","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/TIP.2017.2756825","volume":"27","author":"X Wang","year":"2018","unstructured":"Wang, X., Ma, H., Chen, X., & You, S. (2018a). Edge preserving and multi-scale contextual neural network for salient object detection. IEEE Transactions on Image Processing (TIP), 27(1), 121\u2013134.","journal-title":"IEEE Transactions on Image Processing (TIP)"},{"key":"1293_CR36","doi-asserted-by":"crossref","unstructured":"Wang, X., You, S., Li, X., & Ma, H. (2018b). Weakly-supervised semantic segmentation by iteratively mining common object features. In Proceedings of IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1354\u20131362).","DOI":"10.1109\/CVPR.2018.00147"},{"key":"1293_CR37","unstructured":"Wei, Y. C., Cheng, C. K., et\u00a0al. (1989) Towards efficient hierarchical designs by ratio cut partitioning. In IEEE international conference on computer-aided design (pp. 298\u2013301)."},{"key":"1293_CR38","doi-asserted-by":"crossref","unstructured":"Wei, Y., Feng, J., Liang, X., Cheng, M. M., Zhao, Y., & Yan, S. (2017a). Object region mining with adversarial erasing: A simple classification to semantic segmentation approach. In Proceedings of IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1568\u20131576).","DOI":"10.1109\/CVPR.2017.687"},{"issue":"11","key":"1293_CR39","doi-asserted-by":"publisher","first-page":"2314","DOI":"10.1109\/TPAMI.2016.2636150","volume":"39","author":"Y Wei","year":"2017","unstructured":"Wei, Y., Liang, X., Chen, Y., Shen, X., Cheng, M. M., Feng, J., et al. (2017b). STC: A simple to complex framework for weakly-supervised semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 39(11), 2314\u20132320.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)"},{"key":"1293_CR40","doi-asserted-by":"crossref","unstructured":"Wei, Y., Xiao, H., Shi, H., Jie, Z., Feng, J., & Huang, T. S. (2018). Revisiting dilated convolution: A simple approach for weakly-and semi-supervised semantic segmentation. In Proceedings of IEEE conference on computer vision and pattern recognition (CVPR) (pp. 7268\u20137277).","DOI":"10.1109\/CVPR.2018.00759"},{"key":"1293_CR41","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. In Proceedings of IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2881\u20132890).","DOI":"10.1109\/CVPR.2017.660"},{"key":"1293_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2921\u20132929).","DOI":"10.1109\/CVPR.2016.319"},{"issue":"3","key":"1293_CR43","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., Zhao, H., Puig, X., Xiao, T., Fidler, S., Barriuso, A., et al. (2019). Semantic understanding of scenes through the ade20k dataset. International Journal of Computer Vision (IJCV), 127(3), 302\u2013321.","journal-title":"International Journal of Computer Vision (IJCV)"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01293-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-020-01293-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-020-01293-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,29]],"date-time":"2021-01-29T00:26:58Z","timestamp":1611880018000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-020-01293-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,30]]},"references-count":43,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["1293"],"URL":"https:\/\/doi.org\/10.1007\/s11263-020-01293-3","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,30]]},"assertion":[{"value":"21 April 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}