{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T14:02:44Z","timestamp":1762351364193,"version":"3.41.0"},"reference-count":57,"publisher":"Association for Computing Machinery (ACM)","issue":"7","license":[{"start":{"date-parts":[[2023,5,4]],"date-time":"2023-05-04T00:00:00Z","timestamp":1683158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62072463, 71531012"],"award-info":[{"award-number":["62072463, 71531012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Foundation of China","doi-asserted-by":"crossref","award":["18ZDA309"],"award-info":[{"award-number":["18ZDA309"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Research Seed Funds of School of Interdisciplinary Studies of Renmin University of China"},{"name":"Opening Project of State Key Laboratory of Digital Publishing Technology of Founder Group"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2023,8,31]]},"abstract":"<jats:p>Weakly Supervised Semantic Segmentation with image-level annotation uses localization maps from the classifier to generate pseudo labels. However, such localization maps focus only on sparse salient object regions, it is difficult to generate high-quality segmentation labels, which deviates from the requirement of semantic segmentation. To address this issue, we propose a dual-aware domain mining and cross-aware supervision (DDMCAS) method for weakly-supervised semantic segmentation. Specifically, we propose a dual-aware domain mining (DDM) module consisting of graph-based global reasoning unit and salient-region extension controller, which produces dense localization maps by exploring object features in salient regions and adjacent non-salient regions simultaneously. In order to further bridge the gap between salient regions and adjacent non-salient regions to generate more refined localization maps, we propose a cross-aware supervision (CAS) strategy to recover missing parts of the target objects and enhance weak attention in adjacent non-salient regions, leading to pseudo labels of higher quality for training the segmentation network. Based on the generated pseudo-labels, extensive experiments on PASCAL VOC 2012 dataset demonstrate that our method outperforms state-of-the-art methods using image-level labels for weakly supervised semantic segmentation.<\/jats:p>","DOI":"10.1145\/3589343","type":"journal-article","created":{"date-parts":[[2023,3,25]],"date-time":"2023-03-25T18:56:25Z","timestamp":1679770585000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Dual-aware Domain Mining and Cross-aware Supervision for Weakly-supervised Semantic Segmentation"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4833-7003","authenticated-orcid":false,"given":"Yuhui","family":"Guo","sequence":"first","affiliation":[{"name":"Renmin University of China, Haidian Qu, Beijing Shi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3431-5954","authenticated-orcid":false,"given":"Xun","family":"Liang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Haidian Qu, Beijing Shi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7266-084X","authenticated-orcid":false,"given":"Bo","family":"Wu","sequence":"additional","affiliation":[{"name":"Renmin University of China, Haidian Qu, Beijing Shi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8653-6225","authenticated-orcid":false,"given":"Xiangping","family":"Zheng","sequence":"additional","affiliation":[{"name":"Renmin University of China, Haidian Qu, Beijing Shi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4071-0977","authenticated-orcid":false,"given":"Xuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Haidian Qu, Beijing Shi, China"}]}],"member":"320","published-online":{"date-parts":[[2023,5,4]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00523"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_34"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00901"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.20"},{"key":"e_1_3_1_7_2","volume-title":"Proceedings of the 3rd International Conference on Learning Representations.","author":"Chen Liang-Chieh","year":"2015","unstructured":"Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L. Yuille. 2015. Semantic image segmentation with deep convolutional nets and fully connected CRFs. In Proceedings of the 3rd International Conference on Learning Representations.."},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_21"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00052"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.191"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00434"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_20"},{"key":"e_1_3_1_17_2","first-page":"10762","volume-title":"Proceedings of the The 34th AAAI Conference on Artificial Intelligence, AAAI 2020, The 32nd Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The 10th AAAI Symposium on Educational Advances in Artificial Intelligence, February 7\u201312, 2020","author":"Fan Junsong","year":"2020","unstructured":"Junsong Fan, Zhaoxiang Zhang, Tieniu Tan, Chunfeng Song, and Jun Xiao. 2020. CIAN: Cross-image affinity net for weakly supervised semantic segmentation. In Proceedings of the The 34th AAAI Conference on Artificial Intelligence, AAAI 2020, The 32nd Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The 10th AAAI Symposium on Educational Advances in Artificial Intelligence, February 7\u201312, 2020. AAAI Press, 10762\u201310769."},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_23"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354978"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.3390\/sym10080338"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.239"},{"key":"e_1_3_1_24_2","volume-title":"Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018 (NeurIPS\u201918, December 3-8, 2018, Montr\u00e9al, Canada)","author":"Hou Qibin","year":"2018","unstructured":"Qibin Hou, Peng-Tao Jiang, Yunchao Wei, and Ming-Ming Cheng. 2018. Self-erasing network for integral object attention. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018 (NeurIPS\u201918, December 3-8, 2018, Montr\u00e9al, Canada), Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicol\u00f2 Cesa-Bianchi, and Roman Garnett (Eds.). 547\u2013557."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004210"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00733"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00216"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.181"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16269"},{"key":"e_1_3_1_30_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings. OpenReview.net."},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_42"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00541"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00960"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.344"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.162"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.77"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460962"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00100"},{"key":"e_1_3_1_39_2","volume-title":"Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, May 7\u20139, 2015, Conference Track Proceedings","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, May 7\u20139, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.)."},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00325"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_21"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.315"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00147"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.687"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2636150"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00759"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2966647"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00265"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00732"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6971"},{"issue":"9","key":"e_1_3_1_52_2","first-page":"5866","article-title":"Weakly supervised object localization and detection: A survey","volume":"44","author":"Zhang Dingwen","year":"2022","unstructured":"Dingwen Zhang, Junwei Han, Gong Cheng, and Ming-Hsuan Yang. 2022. Weakly supervised object localization and detection: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 9 (2022), 5866\u20135885.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3046647"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_40"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00144"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01655"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589343","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:16Z","timestamp":1750291396000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589343"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,4]]},"references-count":57,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,8,31]]}},"alternative-id":["10.1145\/3589343"],"URL":"https:\/\/doi.org\/10.1145\/3589343","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"type":"print","value":"1556-4681"},{"type":"electronic","value":"1556-472X"}],"subject":[],"published":{"date-parts":[[2023,5,4]]},"assertion":[{"value":"2021-11-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-21","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}