{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:41:12Z","timestamp":1765309272325,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2662025PY019"],"award-info":[{"award-number":["2662025PY019"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754902","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"7481-7489","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DRMix: Decomposition-Recomposition Data Augmentation with Diffusion Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9410-4058","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"first","affiliation":[{"name":"College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5886-1639","authenticated-orcid":false,"given":"Zhichuan","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2564-2753","authenticated-orcid":false,"given":"Yanmin","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4546-7804","authenticated-orcid":false,"given":"Mengyao","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2663-0479","authenticated-orcid":false,"given":"Jun","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Data augmentation generative adversarial networks. arXiv preprint arXiv:1711.04340","author":"Antoniou Antreas","year":"2017","unstructured":"Antreas Antoniou, Amos Storkey, and Harrison Edwards. 2017. Data augmentation generative adversarial networks. arXiv preprint arXiv:1711.04340 (2017)."},{"key":"e_1_3_2_1_2_1","volume-title":"Synthetic data from diffusion models improves imagenet classification. arXiv preprint arXiv:2304.08466","author":"Azizi Shekoofeh","year":"2023","unstructured":"Shekoofeh Azizi, Simon Kornblith, Chitwan Saharia, Mohammad Norouzi, and David J Fleet. 2023. Synthetic data from diffusion models improves imagenet classification. arXiv preprint arXiv:2304.08466 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Leaving reality to imagination: Robust classification via generated datasets. arXiv preprint arXiv:2302.02503","author":"Bansal Hritik","year":"2023","unstructured":"Hritik Bansal and Aditya Grover. 2023. Leaving reality to imagination: Robust classification via generated datasets. arXiv preprint arXiv:2302.02503 (2023)."},{"key":"e_1_3_2_1_4_1","first-page":"834","volume-title":"IEEE TPAMI","volume":"40","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2017. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE TPAMI, Vol. 40, 4 (2017), 834-848."},{"key":"e_1_3_2_1_5_1","volume-title":"Adaaug: Learning class-and instance-adaptive data augmentation policies. In ICLR.","author":"Cheung Tsz-Him","year":"2021","unstructured":"Tsz-Him Cheung and Dit-Yan Yeung. 2021. Adaaug: Learning class-and instance-adaptive data augmentation policies. In ICLR."},{"key":"e_1_3_2_1_6_1","first-page":"702","article-title":"Randaugment: Practical automated data augmentation with a reduced search space","author":"Cubuk Ekin D","year":"2020","unstructured":"Ekin D Cubuk, Barret Zoph, Jonathon Shlens, and Quoc V Le. 2020. Randaugment: Practical automated data augmentation with a reduced search space. In CVPRW. 702-703.","journal-title":"CVPRW."},{"key":"e_1_3_2_1_7_1","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng Jia","year":"2009","unstructured":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In CVPR. Ieee, 248-255.","journal-title":"CVPR. Ieee"},{"key":"e_1_3_2_1_8_1","volume-title":"Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552","author":"DeVries Terrance","year":"2017","unstructured":"Terrance DeVries and Graham W Taylor. 2017. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)."},{"key":"e_1_3_2_1_9_1","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. NeurIPS, Vol. 34 (2021), 8780-8794.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_10_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_11_1","first-page":"7489","article-title":"Salient Object-Aware Background Generation using Text-Guided Diffusion Models","author":"Eshratifar Amir Erfan","year":"2024","unstructured":"Amir Erfan Eshratifar, Joao VB Soares, Kapil Thadani, Shaunak Mishra, Mikhail Kuznetsov, Yueh-Ning Ku, and Paloma De Juan. 2024. Salient Object-Aware Background Generation using Text-Guided Diffusion Models. In CVPR. 7489-7499.","journal-title":"CVPR."},{"key":"e_1_3_2_1_12_1","first-page":"8196","article-title":"You only cut once: Boosting data augmentation with a single cut","author":"Han Junlin","year":"2022","unstructured":"Junlin Han, Pengfei Fang, Weihao Li, Jie Hong, Mohammad Ali Armin, Ian Reid, Lars Petersson, and Hongdong Li. 2022. You only cut once: Boosting data augmentation with a single cut. In ICML. PMLR, 8196-8212.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_13_1","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770-778.","journal-title":"CVPR."},{"key":"e_1_3_2_1_14_1","volume-title":"Is synthetic data from generative models ready for image recognition? arXiv preprint arXiv:2210.07574","author":"He Ruifei","year":"2022","unstructured":"Ruifei He, Shuyang Sun, Xin Yu, Chuhui Xue, Wenqing Zhang, Philip Torr, Song Bai, and Xiaojuan Qi. 2022. Is synthetic data from generative models ready for image recognition? arXiv preprint arXiv:2210.07574 (2022)."},{"key":"e_1_3_2_1_15_1","volume-title":"Augmix: A simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:1912.02781","author":"Hendrycks Dan","year":"2019","unstructured":"Dan Hendrycks, Norman Mu, Ekin D Cubuk, Barret Zoph, Justin Gilmer, and Balaji Lakshminarayanan. 2019. Augmix: A simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:1912.02781 (2019)."},{"key":"e_1_3_2_1_16_1","first-page":"16783","article-title":"Pixmix: Dreamlike pictures comprehensively improve safety measures","author":"Hendrycks Dan","year":"2022","unstructured":"Dan Hendrycks, Andy Zou, Mantas Mazeika, Leonard Tang, Bo Li, Dawn Song, and Jacob Steinhardt. 2022. Pixmix: Dreamlike pictures comprehensively improve safety measures. In CVPR. 16783-16792.","journal-title":"CVPR."},{"key":"e_1_3_2_1_17_1","volume-title":"NeurIPS","volume":"30","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. NeurIPS, Vol. 30 (2017)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16255"},{"key":"e_1_3_2_1_19_1","first-page":"27621","article-title":"DiffuseMix","author":"Islam Khawar","year":"2024","unstructured":"Khawar Islam, Muhammad Zaigham Zaheer, Arif Mahmood, and Karthik Nandakumar. 2024. DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models. In CVPR. 27621-27630.","journal-title":"Label-Preserving Data Augmentation with Diffusion Models. In CVPR."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25191"},{"key":"e_1_3_2_1_21_1","volume-title":"Co-mixup: Saliency guided joint mixup with supermodular diversity. arXiv preprint arXiv:2102.03065","author":"Kim Jang-Hyun","year":"2021","unstructured":"Jang-Hyun Kim, Wonho Choo, Hosan Jeong, and Hyun Oh Song. 2021. Co-mixup: Saliency guided joint mixup with supermodular diversity. arXiv preprint arXiv:2102.03065 (2021)."},{"key":"e_1_3_2_1_22_1","first-page":"5275","article-title":"Puzzle mix: Exploiting saliency and local statistics for optimal mixup","author":"Kim Jang-Hyun","year":"2020","unstructured":"Jang-Hyun Kim, Wonho Choo, and Hyun Oh Song. 2020. Puzzle mix: Exploiting saliency and local statistics for optimal mixup. In ICML. PMLR, 5275-5285.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_23_1","first-page":"9404","article-title":"Panoptic segmentation","author":"Kirillov Alexander","year":"2019","unstructured":"Alexander Kirillov, Kaiming He, Ross Girshick, Carsten Rother, and Piotr Doll\u00e1r. 2019. Panoptic segmentation. In CVPR. 9404-9413.","journal-title":"CVPR."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_2_1_25_1","volume-title":"Semantic-sam: Segment and recognize anything at any granularity. arXiv preprint arXiv:2307.04767","author":"Li Feng","year":"2023","unstructured":"Feng Li, Hao Zhang, Peize Sun, Xueyan Zou, Shilong Liu, Jianwei Yang, Chunyuan Li, Lei Zhang, and Jianfeng Gao. 2023b. Semantic-sam: Segment and recognize anything at any granularity. arXiv preprint arXiv:2307.04767 (2023)."},{"key":"e_1_3_2_1_26_1","first-page":"2928","article-title":"Invariant grounding for video question answering","author":"Li Yicong","year":"2022","unstructured":"Yicong Li, Xiang Wang, Junbin Xiao, Wei Ji, and Tat-Seng Chua. 2022. Invariant grounding for video question answering. In CVPR. 2928-2937.","journal-title":"CVPR."},{"key":"e_1_3_2_1_27_1","volume-title":"Is synthetic data from diffusion models ready for knowledge distillation? arXiv preprint arXiv:2305.12954","author":"Li Zheng","year":"2023","unstructured":"Zheng Li, Yuxuan Li, Penghai Zhao, Renjie Song, Xiang Li, and Jian Yang. 2023a. Is synthetic data from diffusion models ready for knowledge distillation? arXiv preprint arXiv:2305.12954 (2023)."},{"key":"e_1_3_2_1_28_1","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu Ze","year":"2021","unstructured":"Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV. 10012-10022.","journal-title":"ICCV."},{"key":"e_1_3_2_1_29_1","volume-title":"Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151","author":"Maji Subhransu","year":"2013","unstructured":"Subhransu Maji, Esa Rahtu, Juho Kannala, Matthew Blaschko, and Andrea Vedaldi. 2013. Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)."},{"key":"e_1_3_2_1_30_1","volume-title":"Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation. arXiv preprint arXiv:2406.14551","author":"Michaeli Eyal","year":"2024","unstructured":"Eyal Michaeli and Ohad Fried. 2024. Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation. arXiv preprint arXiv:2406.14551 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"e_1_3_2_1_32_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_1_33_1","volume-title":"Resizemix: Mixing data with preserved object information and true labels. arXiv preprint arXiv:2012.11101","author":"Qin Jie","year":"2020","unstructured":"Jie Qin, Jiemin Fang, Qian Zhang, Wenyu Liu, Xingang Wang, and Xinggang Wang. 2020. Resizemix: Mixing data with preserved object information and true labels. arXiv preprint arXiv:2012.11101 (2020)."},{"key":"e_1_3_2_1_34_1","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach Robin","year":"2022","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In CVPR. 10684-10695.","journal-title":"CVPR."},{"key":"e_1_3_2_1_35_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al., 2022. Photorealistic text-to-image diffusion models with deep language understanding. NeurIPS, Vol. 35 (2022), 36479-36494.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_36_1","first-page":"8011","article-title":"Fake it till you make it: Learning transferable representations from synthetic imagenet clones","author":"Sariyildiz Mert B\u00fclent","year":"2023","unstructured":"Mert B\u00fclent Sariyildiz, Karteek Alahari, Diane Larlus, and Yannis Kalantidis. 2023. Fake it till you make it: Learning transferable representations from synthetic imagenet clones. In CVPR. 8011-8021.","journal-title":"CVPR."},{"key":"e_1_3_2_1_37_1","first-page":"48382","article-title":"Stablerep: Synthetic images from text-to-image models make strong visual representation learners","volume":"36","author":"Tian Yonglong","year":"2023","unstructured":"Yonglong Tian, Lijie Fan, Phillip Isola, Huiwen Chang, and Dilip Krishnan. 2023. Stablerep: Synthetic images from text-to-image models make strong visual representation learners. NeurIPS, Vol. 36 (2023), 48382-48402.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_38_1","volume-title":"Effective data augmentation with diffusion models. arXiv preprint arXiv:2302.07944","author":"Trabucco Brandon","year":"2023","unstructured":"Brandon Trabucco, Kyle Doherty, Max Gurinas, and Ruslan Salakhutdinov. 2023. Effective data augmentation with diffusion models. arXiv preprint arXiv:2302.07944 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"Saliencymix: A saliency guided data augmentation strategy for better regularization. arXiv preprint arXiv:2006.01791","author":"Uddin AFM","year":"2020","unstructured":"AFM Uddin, Mst Monira, Wheemyung Shin, TaeChoong Chung, Sung-Ho Bae, et al., 2020. Saliencymix: A saliency guided data augmentation strategy for better regularization. arXiv preprint arXiv:2006.01791 (2020)."},{"key":"e_1_3_2_1_40_1","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","author":"Verma Vikas","year":"2019","unstructured":"Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, David Lopez-Paz, and Yoshua Bengio. 2019. Manifold mixup: Better representations by interpolating hidden states. In ICML. PMLR, 6438-6447.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_41_1","unstructured":"Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The caltech-ucsd birds-200-2011 dataset. (2011)."},{"key":"e_1_3_2_1_42_1","first-page":"17223","article-title":"Enhance image classification via inter-class image mixup with diffusion model","author":"Wang Zhicai","year":"2024","unstructured":"Zhicai Wang, Longhui Wei, Tan Wang, Heyu Chen, Yanbin Hao, Xiang Wang, Xiangnan He, and Qi Tian. 2024. Enhance image classification via inter-class image mixup with diffusion model. In CVPR. 17223-17233.","journal-title":"CVPR."},{"key":"e_1_3_2_1_43_1","first-page":"6023","article-title":"Cutmix: Regularization strategy to train strong classifiers with localizable features","author":"Yun Sangdoo","year":"2019","unstructured":"Sangdoo Yun, Dongyoon Han, Seong Joon Oh, Sanghyuk Chun, Junsuk Choe, and Youngjoon Yoo. 2019. Cutmix: Regularization strategy to train strong classifiers with localizable features. In ICCV. 6023-6032.","journal-title":"ICCV."},{"key":"e_1_3_2_1_44_1","first-page":"7866","article-title":"Incorporating bias-aware margins into contrastive loss for collaborative filtering","volume":"35","author":"Zhang An","year":"2022","unstructured":"An Zhang, Wenchang Ma, Xiang Wang, and Tat-Seng Chua. 2022. Incorporating bias-aware margins into contrastive loss for collaborative filtering. NeurIPS, Vol. 35 (2022), 7866-7878.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_45_1","volume-title":"mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412","author":"Zhang Hongyi","year":"2017","unstructured":"Hongyi Zhang. 2017. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00325"},{"key":"e_1_3_2_1_47_1","first-page":"586","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang Richard","year":"2018","unstructured":"Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In CVPR. 586-595.","journal-title":"CVPR."},{"key":"e_1_3_2_1_48_1","first-page":"54046","article-title":"Toward understanding generative data augmentation","volume":"36","author":"Zheng Chenyu","year":"2023","unstructured":"Chenyu Zheng, Guoqiang Wu, and Chongxuan Li. 2023. Toward understanding generative data augmentation. NeurIPS, Vol. 36 (2023), 54046-54060.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_49_1","first-page":"2921","article-title":"Learning deep features for discriminative localization","author":"Zhou Bolei","year":"2016","unstructured":"Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. 2016. Learning deep features for discriminative localization. In CVPR. 2921-2929.","journal-title":"CVPR."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754902","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:37:57Z","timestamp":1765309077000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754902"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":50,"alternative-id":["10.1145\/3746027.3754902","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754902","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"}}]}}