{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T19:08:57Z","timestamp":1781032137604,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC","award":["62201342,62101325"],"award-info":[{"award-number":["62201342,62101325"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680894","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"3568-3577","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Infusion: Preventing Customized Text-to-Image Diffusion from Overfitting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4893-8878","authenticated-orcid":false,"given":"Weili","family":"Zeng","sequence":"first","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3209-8965","authenticated-orcid":false,"given":"Yichao","family":"Yan","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7443-866X","authenticated-orcid":false,"given":"Qi","family":"Zhu","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1068-6525","authenticated-orcid":false,"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7768-811X","authenticated-orcid":false,"given":"Pengzhi","family":"Chu","sequence":"additional","affiliation":[{"name":"Student Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4042-7274","authenticated-orcid":false,"given":"Weiming","family":"Zhao","sequence":"additional","affiliation":[{"name":"Student Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2022. Stable Diffusion. https:\/\/huggingface.co\/runwayml\/stable-diffusion-v1-5"},{"key":"e_1_3_2_1_2_1","volume-title":"SIGGRAPH Asia 2023 Conference Papers. 1--10","author":"Arar Moab","unstructured":"Moab Arar, Rinon Gal, Yuval Atzmon, Gal Chechik, Daniel Cohen-Or, Ariel Shamir, and Amit H. Bermano. 2023. Domain-agnostic tuning-encoder for fast personalization of text-to-image models. In SIGGRAPH Asia 2023 Conference Papers. 1--10."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"e_1_3_2_1_6_1","volume-title":"Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096","author":"Brock Andrew","year":"2018","unstructured":"Andrew Brock, Jeff Donahue, and Karen Simonyan. 2018. Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"e_1_3_2_1_10_1","volume-title":"Subject-driven text-to-image generation via apprenticeship learning. arXiv preprint arXiv:2304.00186","author":"Chen Wenhu","year":"2023","unstructured":"Wenhu Chen, Hexiang Hu, Yandong Li, Nataniel Rui, Xuhui Jia, Ming-Wei Chang, and William W Cohen. 2023. Subject-driven text-to-image generation via apprenticeship learning. arXiv preprint arXiv:2304.00186 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2022. An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"e_1_3_2_1_14_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems 27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_15_1","volume-title":"Svdiff: Compact parameter space for diffusion fine-tuning. arXiv preprint arXiv:2303.11305","author":"Han Ligong","year":"2023","unstructured":"Ligong Han, Yinxiao Li, Han Zhang, Peyman Milanfar, Dimitris Metaxas, and Feng Yang. 2023. Svdiff: Compact parameter space for diffusion fine-tuning. arXiv preprint arXiv:2303.11305 (2023)."},{"key":"e_1_3_2_1_16_1","unstructured":"Yutong He Naoki Murata Chieh-Hsin Lai Yuhta Takida Toshimitsu Uesaka Dongjun Kim Wei-Hsiang Liao Yuki Mitsufuji J Zico Kolter Ruslan Salakhutdinov et al. 2023. Manifold preserving guided diffusion. arXiv preprint arXiv:2311.16424 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626","author":"Hertz Amir","year":"2022","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 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. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_19_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems 33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_20_1","volume-title":"Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_3_2_1_21_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_22_1","first-page":"852","article-title":"Alias-free generative adversarial networks","volume":"34","author":"Karras Tero","year":"2021","unstructured":"Tero Karras, Miika Aittala, Samuli Laine, Erik H\u00e4rk\u00f6nen, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2021. Alias-free generative adversarial networks. Advances in Neural Information Processing Systems 34 (2021), 852--863.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"e_1_3_2_1_25_1","first-page":"17359","article-title":"Locating and editing factual associations in GPT","volume":"35","author":"Meng Kevin","year":"2022","unstructured":"Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in GPT. Advances in Neural Information Processing Systems 35 (2022), 17359--17372.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_2_1_27_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_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"e_1_3_2_1_29_1","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_31_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 1, 2","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 1, 2 (2022), 3."},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Machine Learning. PMLR, 8821--8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning. PMLR, 8821--8831."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_35_1","volume-title":"Burcu Karagol Ayan, S Sara Mahdavi, Rapha Gontijo Lopes, et al. [n. d.]. Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily Denton, Seyed Kamyar Seyed Ghasemipour, Burcu Karagol Ayan, S Sara Mahdavi, Rapha Gontijo Lopes, et al. [n. d.]. Photorealistic text-to-image diffusion models with deep language understanding, 2022. URL https:\/\/arxiv. org\/abs\/2205.11487 4 ([n. d.])."},{"key":"e_1_3_2_1_36_1","first-page":"4713","article-title":"Image super-resolution via iterative refinement","volume":"45","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, David J Fleet, and Mohammad Norouzi. 2022. Image super-resolution via iterative refinement. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 4 (2022), 4713--4726.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_37_1","volume-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114","author":"Schuhmann Christoph","year":"2021","unstructured":"Christoph Schuhmann, Richard Vencu, Romain Beaumont, Robert Kaczmarczyk, Clayton Mullis, Aarush Katta, Theo Coombes, Jenia Jitsev, and Aran Komatsuzaki. 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)."},{"key":"e_1_3_2_1_38_1","volume-title":"International conference on machine learning. PMLR, 2256--2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning. PMLR, 2256--2265."},{"key":"e_1_3_2_1_39_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_40_1","volume-title":"Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems 32","author":"Song Yang","year":"2019","unstructured":"Yang Song and Stefano Ermon. 2019. Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"e_1_3_2_1_43_1","volume-title":"Multi-Concept T2I-Zero: Tweaking Only The Text Embeddings and Nothing Else. arXiv preprint arXiv:2310.07419","author":"Tunanyan Hazarapet","year":"2023","unstructured":"Hazarapet Tunanyan, Dejia Xu, Shant Navasardyan, Zhangyang Wang, and Humphrey Shi. 2023. Multi-Concept T2I-Zero: Tweaking Only The Text Embeddings and Nothing Else. arXiv preprint arXiv:2310.07419 (2023)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"C\u00e9dric Villani et al. 2009. Optimal transport: old and new. Vol. 338. Springer.","DOI":"10.1007\/978-3-540-71050-9"},{"key":"e_1_3_2_1_45_1","volume-title":"A connection between score matching and denoising autoencoders. Neural computation 23, 7","author":"Vincent Pascal","year":"2011","unstructured":"Pascal Vincent. 2011. A connection between score matching and denoising autoencoders. Neural computation 23, 7 (2011), 1661--1674."},{"key":"e_1_3_2_1_46_1","unstructured":"Patrick von Platen Suraj Patil Anton Lozhkov Pedro Cuenca Nathan Lambert Kashif Rasul Mishig Davaadorj and Thomas Wolf. [n. d.]. Diffusers: State-of-theart diffusion models. https:\/\/github.com\/huggingface\/diffusers"},{"key":"e_1_3_2_1_47_1","volume-title":"Extended Textual Conditioning in Text-to-Image Generation. arXiv preprint arXiv:2303.09522","author":"Voynov Andrey","year":"2023","unstructured":"Andrey Voynov, Qinghao Chu, Daniel Cohen-Or, and Kfir Aberman. 2023. P+: Extended Textual Conditioning in Text-to-Image Generation. arXiv preprint arXiv:2303.09522 (2023)."},{"key":"e_1_3_2_1_48_1","volume-title":"Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation. arXiv preprint arXiv:2302.13848","author":"Wei Yuxiang","year":"2023","unstructured":"Yuxiang Wei, Yabo Zhang, Zhilong Ji, Jinfeng Bai, Lei Zhang, and Wangmeng Zuo. 2023. Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation. arXiv preprint arXiv:2302.13848 (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721","author":"Ye Hu","year":"2023","unstructured":"Hu Ye, Jun Zhang, Sibo Liu, Xiao Han, and Wei Yang. 2023. Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00692"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00584"},{"key":"e_1_3_2_1_53_1","volume-title":"Non-uniform Timestep Sampling: Towards Faster Diffusion Model Training. ACMMM","author":"Zheng Tianyi","year":"2024","unstructured":"Tianyi Zheng, Cong Geng, Peng-Tao Jiang, Ben Wan, Hao Zhang, Jinwei Chen, Jia Wang, and Bo Li. 2024. Non-uniform Timestep Sampling: Towards Faster Diffusion Model Training. ACMMM (2024)."},{"key":"e_1_3_2_1_54_1","volume-title":"Beta-Tuned Timestep Diffusion Model. ECCV","author":"Zheng Tianyi","year":"2024","unstructured":"Tianyi Zheng, Peng-Tao Jiang, Ben Wan, Hao Zhang, Jinwei Chen, Jia Wang, and Bo Li. 2024. Beta-Tuned Timestep Diffusion Model. ECCV (2024)."},{"key":"e_1_3_2_1_55_1","volume-title":"Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach. arXiv preprint arXiv:2305.13579","author":"Zhou Yufan","year":"2023","unstructured":"Yufan Zhou, Ruiyi Zhang, Tong Sun, and Jinhui Xu. 2023. Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach. arXiv preprint arXiv:2305.13579 (2023)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680894","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680894","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:33Z","timestamp":1750295853000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680894"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":56,"alternative-id":["10.1145\/3664647.3680894","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680894","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}