{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T07:05:34Z","timestamp":1772780734975,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","funder":[{"name":"National Key Research and Development Project of China","award":["2023YFF0905502"],"award-info":[{"award-number":["2023YFF0905502"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92467204 & 62472249 & 62402264"],"award-info":[{"award-number":["92467204 & 62472249 & 62402264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20220818101014030 & KJZD20240903102300001"],"award-info":[{"award-number":["JCYJ20220818101014030 & KJZD20240903102300001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755856","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"11937-11946","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5791-0664","authenticated-orcid":false,"given":"Jiacheng","family":"Jiang","sequence":"first","affiliation":[{"name":"SIGS, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7450-9438","authenticated-orcid":false,"given":"Yuan","family":"Meng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Pervasive Computing, Ministry of Education Department of Computer Science and Technology, Tsinghua University, Beijing, China and Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0108-6729","authenticated-orcid":false,"given":"Chen","family":"Tang","sequence":"additional","affiliation":[{"name":"MMLab, The Chinese University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2828-4541","authenticated-orcid":false,"given":"Han","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7448-6261","authenticated-orcid":false,"given":"Qun","family":"Li","sequence":"additional","affiliation":[{"name":"SIGS, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5462-6178","authenticated-orcid":false,"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"SIGS, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2236-9290","authenticated-orcid":false,"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China and Key Laboratory of Pervasive Computing, Ministry of Education Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Metareg: Towards domain generalization using meta-regularization. Advances in neural information processing systems","author":"Balaji Yogesh","year":"2018","unstructured":"Yogesh Balaji, Swami Sankaranarayanan, and Rama Chellappa. 2018. Metareg: Towards domain generalization using meta-regularization. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_2_1","volume-title":"Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Nicholas L\u00e9onard, and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00233"},{"key":"e_1_3_2_1_4_1","first-page":"22405","article-title":"Swad: Domain generalization by seeking flat minima","volume":"34","author":"Cha Junbum","year":"2021","unstructured":"Junbum Cha, Sanghyuk Chun, Kyungjae Lee, Han-Cheol Cho, Seunghyun Park, Yunsung Lee, and Sungrae Park. 2021. Swad: Domain generalization by seeking flat minima. Advances in Neural Information Processing Systems, Vol. 34 (2021), 22405-22418.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_5_1","unstructured":"Xinlei Chen Haoqi Fan Ross Girshick and Kaiming He. 2020. Improved Baselines with Momentum Contrastive Learning. arXiv:2003.04297 [cs.CV] https:\/\/arxiv.org\/abs\/2003.04297"},{"key":"e_1_3_2_1_6_1","volume-title":"Vijayalakshmi Srinivasan, and Kailash Gopalakrishnan.","author":"Choi Jungwook","year":"2018","unstructured":"Jungwook Choi, Zhuo Wang, Swagath Venkataramani, Pierce I-Jen Chuang, Vijayalakshmi Srinivasan, and Kailash Gopalakrishnan. 2018. Pact: Parameterized clipping activation for quantized neural networks. arXiv preprint arXiv:1805.06085 (2018)."},{"key":"e_1_3_2_1_7_1","volume-title":"Konstantinos Kamnitsas, and Ben Glocker.","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. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_8_1","volume-title":"Learned step size quantization. arXiv preprint arXiv:1902.08153","author":"Esser Steven K","year":"2019","unstructured":"Steven K Esser, Jeffrey L McKinstry, Deepika Bablani, Rathinakumar Appuswamy, and Dharmendra S Modha. 2019. Learned step size quantization. arXiv preprint arXiv:1902.08153 (2019)."},{"key":"e_1_3_2_1_9_1","volume-title":"Sharpness-aware minimization for efficiently improving generalization. arXiv preprint arXiv:2010.01412","author":"Foret Pierre","year":"2020","unstructured":"Pierre Foret, Ariel Kleiner, Hossein Mobahi, and Behnam Neyshabur. 2020. Sharpness-aware minimization for efficiently improving generalization. arXiv preprint arXiv:2010.01412 (2020)."},{"key":"e_1_3_2_1_10_1","unstructured":"Ishaan Gulrajani and David Lopez-Paz. 2020. In search of lost domain generalization. arXiv preprint arXiv:2007.01434 (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_12_1","volume-title":"Characterizing and understanding the behavior of quantized models for reliable deployment. arXiv preprint arXiv:2204.04220","author":"Hu Qiang","year":"2022","unstructured":"Qiang Hu, Yuejun Guo, Maxime Cordy, Xiaofei Xie, Wei Ma, Mike Papadakis, and Yves Le Traon. 2022. Characterizing and understanding the behavior of quantized models for reliable deployment. arXiv preprint arXiv:2204.04220 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_8"},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Machine Learning. PMLR, 4466-4475","author":"Hubara Itay","year":"2021","unstructured":"Itay Hubara, Yury Nahshan, Yair Hanani, Ron Banner, and Daniel Soudry. 2021. Accurate post training quantization with small calibration sets. In International Conference on Machine Learning. PMLR, 4466-4475."},{"key":"e_1_3_2_1_15_1","unstructured":"Brody Huval Tao Wang Sameep Tandon Jeff Kiske Will Song Joel Pazhayampallil Mykhaylo Andriluka Pranav Rajpurkar Toki Migimatsu Royce Cheng-Yue et al. 2015. An empirical evaluation of deep learning on highway driving. arXiv preprint arXiv:1504.01716 (2015)."},{"key":"e_1_3_2_1_16_1","volume-title":"Averaging weights leads to wider optima and better generalization. arXiv preprint arXiv:1803.05407","author":"Izmailov Pavel","year":"2018","unstructured":"Pavel Izmailov, Dmitrii Podoprikhin, Timur Garipov, Dmitry Vetrov, and Andrew Gordon Wilson. 2018. Averaging weights leads to wider optima and better generalization. arXiv preprint arXiv:1803.05407 (2018)."},{"key":"e_1_3_2_1_17_1","volume-title":"QT-DoG: Quantization-aware Training for Domain Generalization. arXiv preprint arXiv:2410.06020","author":"Javed Saqib","year":"2024","unstructured":"Saqib Javed, Hieu Le, and Mathieu Salzmann. 2024. QT-DoG: Quantization-aware Training for Domain Generalization. arXiv preprint arXiv:2410.06020 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on machine learning. PMLR, 5637-5664","author":"Koh Pang Wei","year":"2021","unstructured":"Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, et al., 2021. Wilds: A benchmark of in-the-wild distribution shifts. In International conference on machine learning. PMLR, 5637-5664."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00638"},{"key":"e_1_3_2_1_22_1","first-page":"163","article-title":"Towards fully autonomous driving: Systems and algorithms. In 2011 IEEE intelligent vehicles symposium (IV)","author":"Levinson Jesse","year":"2011","unstructured":"Jesse Levinson, Jake Askeland, Jan Becker, Jennifer Dolson, David Held, Soeren Kammel, J Zico Kolter, Dirk Langer, Oliver Pink, Vaughan Pratt, et al., 2011. Towards fully autonomous driving: Systems and algorithms. In 2011 IEEE intelligent vehicles symposium (IV). IEEE, 163-168.","journal-title":"IEEE"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV).","author":"Li Da","unstructured":"Da Li, Yongxin Yang, Yi-Zhe Song, and Timothy M. Hospedales. 2017. Deeper, Broader and Artier Domain Generalization. In Proceedings of the IEEE International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_25_1","volume-title":"Visualizing the loss landscape of neural nets. Advances in neural information processing systems","author":"Li Hao","year":"2018","unstructured":"Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, and Tom Goldstein. 2018b. Visualizing the loss landscape of neural nets. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11682"},{"key":"e_1_3_2_1_27_1","volume-title":"Sharpness-aware quantization for deep neural networks. arXiv preprint arXiv:2111.12273","author":"Liu Jing","year":"2021","unstructured":"Jing Liu, Jianfei Cai, and Bohan Zhuang. 2021a. Sharpness-aware quantization for deep neural networks. arXiv preprint arXiv:2111.12273 (2021)."},{"key":"e_1_3_2_1_28_1","volume-title":"Towards out-of-distribution generalization: A survey. arXiv preprint arXiv:2108.13624","author":"Liu Jiashuo","year":"2021","unstructured":"Jiashuo Liu, Zheyan Shen, Yue He, Xingxuan Zhang, Renzhe Xu, Han Yu, and Peng Cui. 2021b. Towards out-of-distribution generalization: A survey. arXiv preprint arXiv:2108.13624 (2021)."},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Machine Learning. PMLR, 21813-21824","author":"Liu Shih-Yang","year":"2023","unstructured":"Shih-Yang Liu, Zechun Liu, and Kwang-Ting Cheng. 2023. Oscillation-free quantization for low-bit vision transformers. In International Conference on Machine Learning. PMLR, 21813-21824."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01204"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00788"},{"key":"e_1_3_2_1_32_1","volume-title":"International conference on machine learning. PMLR, 7313-7324","author":"Mahajan Divyat","year":"2021","unstructured":"Divyat Mahajan, Shruti Tople, and Amit Sharma. 2021. Domain generalization using causal matching. In International conference on machine learning. PMLR, 7313-7324."},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on machine learning. PMLR, 10-18","author":"Muandet Krikamol","year":"2013","unstructured":"Krikamol Muandet, David Balduzzi, and Bernhard Sch\u00f6lkopf. 2013. Domain generalization via invariant feature representation. In International conference on machine learning. PMLR, 10-18."},{"key":"e_1_3_2_1_34_1","first-page":"7197","volume-title":"Adaptive Rounding for Post-Training Quantization. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research","author":"Nagel Markus","year":"2020","unstructured":"Markus Nagel, Rana Ali Amjad, Mart Van Baalen, Christos Louizos, and Tijmen Blankevoort. 2020. Up or Down? Adaptive Rounding for Post-Training Quantization. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 119), Hal Daum\u00e9 III and Aarti Singh (Eds.). PMLR, 7197-7206. https:\/\/proceedings.mlr.press\/v119\/nagel20a.html"},{"key":"e_1_3_2_1_35_1","volume-title":"Yelysei Bondarenko, Mart van Baalen, and Tijmen Blankevoort.","author":"Nagel Markus","year":"2021","unstructured":"Markus Nagel, Marios Fournarakis, Rana Ali Amjad, Yelysei Bondarenko, Mart van Baalen, and Tijmen Blankevoort. 2021. A White Paper on Neural Network Quantization. arXiv:2106.08295 [cs.LG] https:\/\/arxiv.org\/abs\/2106.08295"},{"key":"e_1_3_2_1_36_1","volume-title":"International Conference on Machine Learning. PMLR, 16318-16330","author":"Nagel Markus","year":"2022","unstructured":"Markus Nagel, Marios Fournarakis, Yelysei Bondarenko, and Tijmen Blankevoort. 2022. Overcoming oscillations in quantization-aware training. In International Conference on Machine Learning. PMLR, 16318-16330."},{"key":"e_1_3_2_1_37_1","volume-title":"International conference on machine learning. PMLR, 5102-5112","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. PMLR, 5102-5112."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847265"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00375"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01501"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_16"},{"key":"e_1_3_2_1_42_1","volume-title":"Principles of risk minimization for learning theory. Advances in neural information processing systems","author":"Vapnik Vladimir","year":"1991","unstructured":"Vladimir Vapnik. 1991. Principles of risk minimization for learning theory. Advances in neural information processing systems, Vol. 4 (1991)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"e_1_3_2_1_44_1","volume-title":"Generalizing to unseen domains: A survey on domain generalization","author":"Wang Jindong","year":"2022","unstructured":"Jindong Wang, Cuiling Lan, Chang Liu, Yidong Ouyang, Tao Qin, Wang Lu, Yiqiang Chen, Wenjun Zeng, and S Yu Philip. 2022. Generalizing to unseen domains: A survey on domain generalization. IEEE transactions on knowledge and data engineering, Vol. 35, 8 (2022), 8052-8072."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00367"},{"key":"e_1_3_2_1_46_1","volume-title":"GWQ: Group-Wise Quantization Framework for Neural Networks. In Asian Conference on Machine Learning. PMLR, 1526-1541","author":"Yang Jiaming","year":"2024","unstructured":"Jiaming Yang, Chenwei Tang, Caiyang Yu, and Jiancheng Lv. 2024. GWQ: Group-Wise Quantization Framework for Neural Networks. In Asian Conference on Machine Learning. PMLR, 1526-1541."},{"key":"e_1_3_2_1_47_1","volume-title":"A survey on evaluation of out-of-distribution generalization. arXiv preprint arXiv:2403.01874","author":"Yu Han","year":"2024","unstructured":"Han Yu, Jiashuo Liu, Xingxuan Zhang, Jiayun Wu, and Peng Cui. 2024a. A survey on evaluation of out-of-distribution generalization. arXiv preprint arXiv:2403.01874 (2024)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02068"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00786"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00479"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01939"},{"key":"e_1_3_2_1_52_1","volume-title":"Domain generalization via entropy regularization. Advances in neural information processing systems","author":"Zhao Shanshan","year":"2020","unstructured":"Shanshan Zhao, Mingming Gong, Tongliang Liu, Huan Fu, and Dacheng Tao. 2020. Domain generalization via entropy regularization. Advances in neural information processing systems, Vol. 33 (2020), 16096-16107."},{"key":"e_1_3_2_1_53_1","first-page":"4396","article-title":"Domain generalization: A survey","volume":"45","author":"Zhou Kaiyang","year":"2022","unstructured":"Kaiyang Zhou, Ziwei Liu, Yu Qiao, Tao Xiang, and Chen Change Loy. 2022. Domain generalization: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, 4 (2022), 4396-4415.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_54_1","volume-title":"Domain generalization with mixstyle. arXiv preprint arXiv:2104.02008","author":"Zhou Kaiyang","year":"2021","unstructured":"Kaiyang Zhou, Yongxin Yang, Yu Qiao, and Tao Xiang. 2021. Domain generalization with mixstyle. arXiv preprint arXiv:2104.02008 (2021)."},{"key":"e_1_3_2_1_55_1","volume-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160","author":"Zhou Shuchang","year":"2016","unstructured":"Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, and Yuheng Zou. 2016. Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 (2016)."},{"key":"e_1_3_2_1_56_1","volume-title":"Surrogate Gap Minimization Improves Sharpness-Aware Training. In International Conference on Learning Representations.","author":"Zhuang Juntang","year":"2022","unstructured":"Juntang Zhuang, Boqing Gong, Liangzhe Yuan, Yin Cui, Hartwig Adam, Nicha C Dvornek, James s Duncan, Ting Liu, et al., 2022. Surrogate Gap Minimization Improves Sharpness-Aware Training. In International Conference on Learning Representations."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:15:54Z","timestamp":1765340154000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755856"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":56,"alternative-id":["10.1145\/3746027.3755856","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755856","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}