{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:58:15Z","timestamp":1781585895549,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T00:00:00Z","timestamp":1720828800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100015599","name":"Toyota Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100015599","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NIFA Award","award":["2020-67021-32799"],"award-info":[{"award-number":["2020-67021-32799"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100004344","name":"Adobe Systems","doi-asserted-by":"publisher","id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100004344","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2106825"],"award-info":[{"award-number":["2106825"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,13]]},"DOI":"10.1145\/3641519.3657527","type":"proceedings-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T10:39:28Z","timestamp":1720780768000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Separate-and-Enhance: Compositional Finetuning for Text-to-Image Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9898-3741","authenticated-orcid":false,"given":"Zhipeng","family":"Bao","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7295-8750","authenticated-orcid":false,"given":"Yijun","family":"Li","sequence":"additional","affiliation":[{"name":"Adobe Research, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8066-6835","authenticated-orcid":false,"given":"Krishna Kumar","family":"Singh","sequence":"additional","affiliation":[{"name":"Adobe Research, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4414-0198","authenticated-orcid":false,"given":"Yu-Xiong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4566-5930","authenticated-orcid":false,"given":"Martial","family":"Hebert","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Aishwarya Agarwal Srikrishna Karanam KJ Joseph Apoorv Saxena Koustava Goswami and Balaji\u00a0Vasan Srinivasan. 2023. A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00217"},{"key":"e_1_3_2_2_2_1","volume-title":"Uniqueness of the Gaussian kernel for scale-space filtering. PAMI","author":"Babaud Jean","year":"1986","unstructured":"Jean Babaud, Andrew\u00a0P Witkin, Michel Baudin, and Richard\u00a0O Duda. 1986. Uniqueness of the Gaussian kernel for scale-space filtering. PAMI (1986)."},{"key":"e_1_3_2_2_3_1","volume-title":"Paint by word. arXiv preprint arXiv:2103.10951","author":"Bau David","year":"2021","unstructured":"David Bau, Alex Andonian, Audrey Cui, YeonHwan Park, Ali Jahanian, Aude Oliva, and Antonio Torralba. 2021. Paint by word. arXiv preprint arXiv:2103.10951 (2021)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Tim Brooks Aleksander Holynski and Alexei\u00a0A Efros. 2023. Instructpix2pix: Learning to follow image editing instructions. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_2_5_1","volume-title":"Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. In SIGGRAPH.","author":"Chefer Hila","year":"2023","unstructured":"Hila Chefer, Yuval Alaluf, Yael Vinker, Lior Wolf, and Daniel Cohen-Or. 2023. Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. In SIGGRAPH."},{"key":"e_1_3_2_2_6_1","volume-title":"Imagenet: A large-scale hierarchical image database. In CVPR.","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."},{"key":"e_1_3_2_2_7_1","volume-title":"The Fr\u00e9chet distance between multivariate normal distributions. Journal of multivariate analysis","author":"Dowson DC","year":"1982","unstructured":"DC Dowson and BV Landau. 1982. The Fr\u00e9chet distance between multivariate normal distributions. Journal of multivariate analysis (1982)."},{"key":"e_1_3_2_2_8_1","unstructured":"Dave Epstein Allan Jabri Ben Poole Alexei\u00a0A Efros and Aleksander Holynski. 2023. Diffusion self-guidance for controllable image generation. In NeurIPS."},{"key":"e_1_3_2_2_9_1","unstructured":"Weixi Feng Xuehai He Tsu-Jui Fu Varun Jampani Arjun Akula Pradyumna Narayana Sugato Basu Xin\u00a0Eric Wang and William\u00a0Yang Wang. 2023. Training-free structured diffusion guidance for compositional text-to-image synthesis. In ICLR."},{"key":"e_1_3_2_2_10_1","volume-title":"Generative adversarial nets. NeurIPS","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. NeurIPS (2014)."},{"key":"e_1_3_2_2_11_1","unstructured":"Shuyang Gu Dong Chen Jianmin Bao Fang Wen Bo Zhang Dongdong Chen Lu Yuan and Baining Guo. 2022. Vector quantized diffusion model for text-to-image synthesis. In CVPR."},{"key":"e_1_3_2_2_12_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_2_13_1","volume-title":"Denoising diffusion probabilistic models. NeurIPS","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. NeurIPS (2020)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Susung Hong Gyuseong Lee Wooseok Jang and Seungryong Kim. 2023. Improving sample quality of diffusion models using self-attention guidance. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00686"},{"key":"e_1_3_2_2_15_1","volume-title":"ReVersion: Diffusion-Based Relation Inversion from Images. arXiv preprint arXiv:2303.13495","author":"Huang Ziqi","year":"2023","unstructured":"Ziqi Huang, Tianxing Wu, Yuming Jiang, Kelvin\u00a0CK Chan, and Ziwei Liu. 2023. ReVersion: Diffusion-Based Relation Inversion from Images. arXiv preprint arXiv:2303.13495 (2023)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Yunji Kim Jiyoung Lee Jin-Hwa Kim Jung-Woo Ha and Jun-Yan Zhu. 2023. Dense text-to-image generation with attention modulation. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Nupur Kumari Bingliang Zhang Richard Zhang Eli Shechtman and Jun-Yan Zhu. 2023. Multi-Concept Customization of Text-to-Image Diffusion. In CVPR.","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"e_1_3_2_2_18_1","volume-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In ICML.","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In ICML."},{"key":"e_1_3_2_2_19_1","unstructured":"Yumeng Li Margret Keuper Dan Zhang and Anna Khoreva. 2023. Divide & Bind Your Attention for Improved Generative Semantic Nursing. In BMVC."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Nan Liu Shuang Li Yilun Du Antonio Torralba and Joshua\u00a0B Tenenbaum. 2022. Compositional visual generation with composable diffusion models. In ECCV.","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"e_1_3_2_2_21_1","volume-title":"Directed Diffusion: Direct Control of Object Placement through Attention Guidance. arXiv preprint arXiv:2302.13153","author":"Ma Duo\u00a0Kurt","year":"2023","unstructured":"Wan-Duo\u00a0Kurt Ma, JP Lewis, W\u00a0Bastiaan Kleijn, and Thomas Leung. 2023. Directed Diffusion: Direct Control of Object Placement through Attention Guidance. arXiv preprint arXiv:2302.13153 (2023)."},{"key":"e_1_3_2_2_22_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_2_23_1","doi-asserted-by":"crossref","unstructured":"Gaurav Parmar Richard Zhang and Jun-Yan Zhu. 2022. On Aliased Resizing and Surprising Subtleties in GAN Evaluation. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.56205"},{"key":"e_1_3_2_2_25_1","unstructured":"Alec Radford Jong\u00a0Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark 2021. Learning transferable visual models from natural language supervision. In ICML."},{"key":"e_1_3_2_2_26_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","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 (2022)."},{"key":"e_1_3_2_2_27_1","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 ICML."},{"key":"e_1_3_2_2_28_1","volume-title":"Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment. NeurIPS","author":"Rassin Royi","year":"2023","unstructured":"Royi Rassin, Eran Hirsch, Daniel Glickman, Shauli Ravfogel, Yoav Goldberg, and Gal Chechik. 2023. Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment. NeurIPS (2023)."},{"key":"e_1_3_2_2_29_1","unstructured":"Scott Reed Zeynep Akata Xinchen Yan Lajanugen Logeswaran Bernt Schiele and Honglak Lee. 2016. Generative adversarial text to image synthesis. In ICML."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_31_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In MICCAI.","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In MICCAI."},{"key":"e_1_3_2_2_32_1","volume-title":"Burcu\u00a0Karagol Ayan, S\u00a0Sara Mahdavi","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily Denton, Seyed Kamyar\u00a0Seyed Ghasemipour, Burcu\u00a0Karagol Ayan, S\u00a0Sara Mahdavi, Rapha\u00a0Gontijo Lopes, 2022. Photorealistic text-to-image diffusion models with deep language understanding. In NeurIPS."},{"key":"e_1_3_2_2_33_1","volume-title":"Laion-5b: An open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:2210.08402","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:2210.08402 (2022)."},{"key":"e_1_3_2_2_34_1","unstructured":"Jaskirat Singh and Liang Zheng. 2023. Divide Evaluate and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback. In NeurIPS."},{"key":"e_1_3_2_2_35_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_2_36_1","unstructured":"Yang Song Jascha Sohl-Dickstein Diederik\u00a0P Kingma Abhishek Kumar Stefano Ermon and Ben Poole. 2021. Score-based generative modeling through stochastic differential equations. In ICLR."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.4159\/9780674044371"},{"key":"e_1_3_2_2_38_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_2_39_1","volume-title":"Attention is all you need. NeurIPS","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. NeurIPS (2017)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"crossref","unstructured":"Ruichen Wang Zekang Chen Chen Chen Jian Ma Haonan Lu and Xiaodong Lin. 2024. Compositional text-to-image synthesis with attention map control of diffusion models. In AAAI.","DOI":"10.1609\/aaai.v38i6.28364"},{"key":"e_1_3_2_2_41_1","volume-title":"Semantic image synthesis via diffusion models. arXiv preprint arXiv:2207.00050","author":"Wang Weilun","year":"2022","unstructured":"Weilun Wang, Jianmin Bao, Wengang Zhou, Dongdong Chen, Dong Chen, Lu Yuan, and Houqiang Li. 2022. Semantic image synthesis via diffusion models. arXiv preprint arXiv:2207.00050 (2022)."},{"key":"e_1_3_2_2_42_1","unstructured":"Joachim Weickert. 1998. Anisotropic diffusion in image processing. Teubner Stuttgart."},{"key":"e_1_3_2_2_43_1","volume-title":"Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In CVPR.","author":"Xu Tao","year":"2018","unstructured":"Tao Xu, Pengchuan Zhang, Qiuyuan Huang, Han Zhang, Zhe Gan, Xiaolei Huang, and Xiaodong He. 2018. Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In CVPR."},{"key":"e_1_3_2_2_44_1","volume-title":"Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Yuanzhong Xu, Jing\u00a0Yu Koh, Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu\u00a0Karagol Ayan, 2022. Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789 (2022)."},{"key":"e_1_3_2_2_45_1","volume-title":"Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In ICCV.","author":"Zhang Han","year":"2017","unstructured":"Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, and Dimitris\u00a0N Metaxas. 2017. Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In ICCV."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2023. Adding conditional control to text-to-image diffusion models. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"crossref","unstructured":"Guangcong Zheng Xianpan Zhou Xuewei Li Zhongang Qi Ying Shan and Xi Li. 2023. LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation. In CVPR.","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"crossref","unstructured":"Xingyi Zhou Rohit Girdhar Armand Joulin Philipp Kr\u00e4henb\u00fchl and Ishan Misra. 2022. Detecting twenty-thousand classes using image-level supervision. In ECCV.","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"e_1_3_2_2_49_1","volume-title":"Dm-gan: Dynamic memory generative adversarial networks for text-to-image synthesis. In CVPR.","author":"Zhu Minfeng","year":"2019","unstructured":"Minfeng Zhu, Pingbo Pan, Wei Chen, and Yi Yang. 2019. Dm-gan: Dynamic memory generative adversarial networks for text-to-image synthesis. In CVPR."}],"event":{"name":"SIGGRAPH '24: Special Interest Group on Computer Graphics and Interactive Techniques Conference","location":"Denver CO USA","acronym":"SIGGRAPH '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657527","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641519.3657527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:50Z","timestamp":1750291550000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657527"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,13]]},"references-count":49,"alternative-id":["10.1145\/3641519.3657527","10.1145\/3641519"],"URL":"https:\/\/doi.org\/10.1145\/3641519.3657527","relation":{},"subject":[],"published":{"date-parts":[[2024,7,13]]},"assertion":[{"value":"2024-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}