{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,20]],"date-time":"2026-11-20T18:56:00Z","timestamp":1795200960426,"version":"4.10.3"},"reference-count":61,"publisher":"Association for Computing Machinery (ACM)","issue":"8","license":[{"start":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T00:00:00Z","timestamp":1718150400000},"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":["U20B2074"],"award-info":[{"award-number":["U20B2074"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Research and Development Project of Zhejiang Province","award":["2023C03026, 2021C03001, 2021C03003"],"award-info":[{"award-number":["2023C03026, 2021C03001, 2021C03003"]}]},{"name":"Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province","award":["2020E10010"],"award-info":[{"award-number":["2020E10010"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2024,8,31]]},"abstract":"<jats:p>Domain generalization primarily mitigates domain shift among multiple source domains, generalizing the trained model to an unseen target domain. However, the spurious correlation usually caused by context prior (e.g., background) makes it challenging to get rid of the domain shift. Therefore, it is critical to model the intrinsic causal mechanism. The existing domain generalization methods only attend to disentangle the semantic and context-related features by modeling the causation between input and labels, which totally ignores the unidentifiable but important confounders. In this article, a Causal Disentangled Intervention Model (CDIM) is proposed for the first time, to the best of our knowledge, to construct confounders via causal intervention. Specifically, a generative model is employed to disentangle the semantic and context-related features. The contextual information of each domain from generative model can be considered as a confounder layer, and the center of all context-related features is utilized for fine-grained hierarchical modeling of confounders. Then the semantic and confounding features from each layer are combined to train an unbiased classifier, which exhibits both transferability and robustness across an unknown distribution domain. CDIM is evaluated on three widely recognized benchmark datasets, namely, Digit-DG, PACS, and NICO, through extensive ablation studies. The experimental results clearly demonstrate that the proposed model achieves state-of-the-art performance.<\/jats:p>","DOI":"10.1145\/3659953","type":"journal-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T10:59:48Z","timestamp":1713956388000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Unbiased Semantic Representation Learning Based on Causal Disentanglement for Domain Generalization"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5542-3340","authenticated-orcid":false,"given":"Xuanyu","family":"Jin","sequence":"first","affiliation":[{"name":"School of Computer Science, Hangzhou Dianzi University, Hangzhou, China and Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8428-9136","authenticated-orcid":false,"given":"Ni","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hangzhou Dianzi University, Hangzhou, China and Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0113-6968","authenticated-orcid":false,"given":"Wanzeng","family":"Kong","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hangzhou Dianzi University, Hangzhou, China and Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6120-833X","authenticated-orcid":false,"given":"Jiajia","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hangzhou Dianzi University, Hangzhou, China and Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0585-0579","authenticated-orcid":false,"given":"Bing","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hangzhou Dianzi University, Hangzhou, China and Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,12]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"372","volume-title":"International Conference on Machine Learning","author":"Ahuja Kartik","year":"2023","unstructured":"Kartik Ahuja, Divyat Mahajan, Yixin Wang, and Yoshua Bengio. 2023. Interventional causal representation learning. In International Conference on Machine Learning. PMLR, 372\u2013407."},{"key":"e_1_3_1_3_2","first-page":"145","volume-title":"International Conference on Machine Learning","author":"Ahuja Kartik","year":"2020","unstructured":"Kartik Ahuja, Karthikeyan Shanmugam, Kush Varshney, and Amit Dhurandhar. 2020. Invariant risk minimization games. In International Conference on Machine Learning. PMLR, 145\u2013155."},{"key":"e_1_3_1_4_2","article-title":"Invariant risk minimization","author":"Arjovsky Martin","year":"2019","unstructured":"Martin Arjovsky, L\u00e9on Bottou, Ishaan Gulrajani, and David Lopez-Paz. 2019. Invariant risk minimization. arXiv:1907.02893. Retrieved from https:\/\/arxiv.org\/abs\/1907.02893","journal-title":"arXiv:1907.02893"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16829"},{"key":"e_1_3_1_6_2","article-title":"Metareg: Towards domain generalization using meta-regularization","volume":"31","author":"Balaji Yogesh","year":"2018","unstructured":"Yogesh Balaji, Swami Sankaranarayanan, and Rama Chellappa. 2018. Metareg: Towards domain generalization using meta-regularization. In Advances in Neural Information Processing Systems, Vol. 31 (2018).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00233"},{"key":"e_1_3_1_8_2","first-page":"301","volume-title":"Proceedings of the 16th European Conference on Computer Vision (ECCV\u201920), Part IX 16","author":"Chattopadhyay Prithvijit","year":"2020","unstructured":"Prithvijit Chattopadhyay, Yogesh Balaji, and Judy Hoffman. 2020. Learning to balance specificity and invariance for in and out of domain generalization. In Proceedings of the 16th European Conference on Computer Vision (ECCV\u201920), Part IX 16. Springer, 301\u2013318."},{"key":"e_1_3_1_9_2","article-title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","volume":"29","author":"Chen Xi","year":"2016","unstructured":"Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, and Pieter Abbeel. 2016. Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In Advances in Neural Information Processing Systems, Vol. 29.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_1_11_2","article-title":"Domain generalization via model-agnostic learning of semantic features","volume":"32","author":"Dou Qi","year":"2019","unstructured":"Qi Dou, Daniel Coelho de Castro, Konstantinos Kamnitsas, and Ben Glocker. 2019. Domain generalization via model-agnostic learning of semantic features. In Advances in Neural Information Processing Systems, Vol. 32 (2019).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_12_2","first-page":"1126","volume-title":"International Conference on Machine Learning","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In International Conference on Machine Learning. PMLR, 1126\u20131135."},{"key":"e_1_3_1_13_2","first-page":"116","volume-title":"Conference on Lifelong Learning Agents","author":"Funke Christina M.","year":"2022","unstructured":"Christina M. Funke, Paul Vicol, Kuan-Chieh Wang, Matthias K\u00fcmmerer, Richard Zemel, and Matthias Bethge. 2022. Disentanglement and generalization under correlation shifts. In Conference on Lifelong Learning Agents, Vol. 199. PMLR, 116\u2013141."},{"key":"e_1_3_1_14_2","first-page":"1180","volume-title":"International Conference on Machine Learning","author":"Ganin Yaroslav","year":"2015","unstructured":"Yaroslav Ganin and Victor Lempitsky. 2015. Unsupervised domain adaptation by backpropagation. In International Conference on Machine Learning, Vol. 37. PMLR, 1180\u20131189."},{"issue":"1","key":"e_1_3_1_15_2","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin Yaroslav","year":"2016","unstructured":"Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Fran\u00e7ois Laviolette, Mario Marchand, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17, 1 (2016), 2096\u20132030.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/11564089_7"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107383"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3333190"},{"key":"e_1_3_1_21_2","first-page":"4555","volume-title":"International Conference on Machine Learning","author":"Ilse Maximilian","year":"2021","unstructured":"Maximilian Ilse, Jakub M. Tomczak, and Patrick Forr\u00e9. 2021. Selecting data augmentation for simulating interventions. In International Conference on Machine Learning, Vol. 139. PMLR, 4555\u20134562."},{"key":"e_1_3_1_22_2","first-page":"322","volume-title":"Medical Imaging with Deep Learning","author":"Ilse Maximilian","year":"2020","unstructured":"Maximilian Ilse, Jakub M. Tomczak, Christos Louizos, and Max Welling. 2020. Diva: Domain invariant variational autoencoders. In Medical Imaging with Deep Learning, Vol. 121. PMLR, 322\u2013348."},{"key":"e_1_3_1_23_2","unstructured":"Diederik P. Kingma and Max Welling. 2013. Auto-encoding variational bayes. Retrieved from https:\/\/arxiv.org\/abs\/1312.6114"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00153"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00566"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3487194"},{"key":"e_1_3_1_29_2","first-page":"8866","volume-title":"Proceedings of the International Conference on Computer Vision","author":"Li Pan","year":"2022","unstructured":"Pan Li, Da Li, Wei Li, Shaogang Gong, Yanwei Fu, and Timothy M. Hospedales. 2022. A simple feature augmentation for domain generalization. In Proceedings of the International Conference on Computer Vision. IEEE, 8866\u20138875."},{"key":"e_1_3_1_30_2","first-page":"11797","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Lin Shiqi","year":"2023","unstructured":"Shiqi Lin, Zhizheng Zhang, Zhipeng Huang, Yan Lu, Cuiling Lan, Peng Chu, Quanzeng You, Jiang Wang, Zicheng Liu, Amey Parulkar, et\u00a0al. 2023. Deep frequency filtering for domain generalization. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 11797\u201311807."},{"key":"e_1_3_1_31_2","volume-title":"UAI 2022 Workshop on Causal Representation Learning","author":"Lippe Phillip","year":"2022","unstructured":"Phillip Lippe, Sara Magliacane, Sindy L\u00f6we, Yuki M. Asano, Taco Cohen, and Efstratios Gavves. 2022. Intervention design for causal representation learning. In UAI 2022 Workshop on Causal Representation Learning."},{"key":"e_1_3_1_32_2","article-title":"Learning causal semantic representation for out-of-distribution prediction","volume":"34","author":"Liu Chang","year":"2021","unstructured":"Chang Liu, Xinwei Sun, Jindong Wang, Haoyue Tang, Tao Li, Tao Qin, Wei Chen, and Tie-Yan Liu. 2021. Learning causal semantic representation for out-of-distribution prediction. In Advances in Neural Information Processing Systems 34 (2021), 6155\u20136170.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20065"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524136"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00924"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3628797.3629009"},{"key":"e_1_3_1_37_2","first-page":"4212","volume-title":"International Conference on Machine Learning","author":"Ma Jianxin","year":"2019","unstructured":"Jianxin Ma, Peng Cui, Kun Kuang, Xin Wang, and Wenwu Zhu. 2019. Disentangled graph convolutional networks. In International Conference on Machine Learning, Vol. 97. PMLR, 4212\u20134221."},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.609"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3263549"},{"key":"e_1_3_1_40_2","first-page":"4036","volume-title":"International Conference on Machine Learning","author":"Parascandolo Giambattista","year":"2018","unstructured":"Giambattista Parascandolo, Niki Kilbertus, Mateo Rojas-Carulla, and Bernhard Sch\u00f6lkopf. 2018. Learning independent causal mechanisms. In International Conference on Machine Learning, Vol. 80. PMLR, 4036\u20134044."},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/82.4.669"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS057"},{"key":"e_1_3_1_43_2","first-page":"5102","volume-title":"International Conference on Machine Learning","author":"Peng Xingchao","year":"2019","unstructured":"Xingchao Peng, Zijun Huang, Ximeng Sun, and Kate Saenko. 2019. Domain agnostic learning with disentangled representations. In International Conference on Machine Learning, Vol. 97. PMLR, 5102\u20135112."},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12167"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.5555\/3202377"},{"key":"e_1_3_1_46_2","first-page":"1256","article-title":"Gradient starvation: A learning proclivity in neural networks","volume":"34","author":"Pezeshki Mohammad","year":"2021","unstructured":"Mohammad Pezeshki, Oumar Kaba, Yoshua Bengio, Aaron C. Courville, Doina Precup, and Guillaume Lajoie. 2021. Gradient starvation: A learning proclivity in neural networks. In Advances in Neural Information Processing Systems 34 (2021), 1256\u20131272.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3552434"},{"key":"e_1_3_1_48_2","article-title":"On causal and anticausal learning","author":"Sch\u00f6lkopf Bernhard","year":"2012","unstructured":"Bernhard Sch\u00f6lkopf, Dominik Janzing, Jonas Peters, Eleni Sgouritsa, Kun Zhang, and Joris Mooij. 2012. On causal and anticausal learning. arXiv:1206.6471. Retrieved from https:\/\/arxiv.org\/abs\/1206.6471","journal-title":"arXiv:1206.6471"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_1_51_2","first-page":"68","volume-title":"Proceedings of the 16th European Conference on Computer Vision (ECCV\u201920), Part XXII 16","author":"Seo Seonguk","year":"2020","unstructured":"Seonguk Seo, Yumin Suh, Dongwan Kim, Geeho Kim, Jongwoo Han, and Bohyung Han. 2020. Learning to optimize domain specific normalization for domain generalization. In Proceedings of the 16th European Conference on Computer Vision (ECCV\u201920), Part XXII 16. Springer, 68\u201383."},{"key":"e_1_3_1_52_2","article-title":"Generalizing across domains via cross-gradient training","author":"Shankar Shiv","year":"2018","unstructured":"Shiv Shankar, Vihari Piratla, Soumen Chakrabarti, Siddhartha Chaudhuri, Preethi Jyothi, and Sunita Sarawagi. 2018. Generalizing across domains via cross-gradient training. arXiv:1804.10745. Retrieved from https:\/\/arxiv.org\/abs\/1804.10745","journal-title":"arXiv:1804.10745"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3152615"},{"key":"e_1_3_1_55_2","first-page":"499","volume-title":"Proceedings of the 14th European Conference on Computer Vision (ECCV\u201916), Part VII 14","author":"Wen Yandong","year":"2016","unstructured":"Yandong Wen, Kaipeng Zhang, Zhifeng Li, and Yu Qiao. 2016. A discriminative feature learning approach for deep face recognition. In Proceedings of the 14th European Conference on Computer Vision (ECCV\u201916), Part VII 14. Springer, 499\u2013515."},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3486251"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3501800"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604809"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00219"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_33"},{"key":"e_1_3_1_62_2","article-title":"Domain generalization with mixstyle","author":"Zhou Kaiyang","year":"2021","unstructured":"Kaiyang Zhou, Yongxin Yang, Yu Qiao, and Tao Xiang. 2021. Domain generalization with mixstyle. arXiv:2104.02008. Retrieved from https:\/\/arxiv.org\/abs\/2104.02008","journal-title":"arXiv:2104.02008"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3659953","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3659953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:30Z","timestamp":1750294710000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3659953"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,12]]},"references-count":61,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8,31]]}},"alternative-id":["10.1145\/3659953"],"URL":"https:\/\/doi.org\/10.1145\/3659953","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,12]]},"assertion":[{"value":"2023-08-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-03","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}