{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T07:47:40Z","timestamp":1769154460007,"version":"3.49.0"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62227801"],"award-info":[{"award-number":["62227801"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0117902"],"award-info":[{"award-number":["2022ZD0117902"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tpami.2025.3609962","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:37:31Z","timestamp":1757957851000},"page":"557-571","source":"Crossref","is-referenced-by-count":1,"title":["Object Detection Data Synthesis via Box-to-Image Generation Based on Diffusion Models"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3995-8382","authenticated-orcid":false,"given":"Jingyuan","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5383-5667","authenticated-orcid":false,"given":"Huimin","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2040-7938","authenticated-orcid":false,"given":"Jiansheng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9734-6056","authenticated-orcid":false,"given":"Jian","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.7347926"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","article-title":"DALL-E for detection: Language-driven compositional image synthesis for object detection","author":"Ge","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref8","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuhmann","year":"2022"},{"key":"ref9","first-page":"1","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Podell","year":"2024"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref11","article-title":"Roboflow 100: A rich, multi-domain object detection benchmark","author":"Ciaglia","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2031"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref15","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref17","first-page":"12438","article-title":"Improved techniques for training score-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song","year":"2020"},{"key":"ref18","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal","year":"2021"},{"key":"ref19","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref20","first-page":"21696","article-title":"Variational diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref22","first-page":"1","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref26","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2013"},{"key":"ref27","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende","year":"2014"},{"key":"ref28","first-page":"19667","article-title":"NVAE: A deep hierarchical variational autoencoder","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vahdat","year":"2020"},{"key":"ref29","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia","year":"2022"},{"key":"ref30","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref31","article-title":"eDiff-I: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01356"},{"key":"ref33","article-title":"High-resolution complex scene synthesis with transformers","author":"Jahn","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref36","article-title":"LayoutDiffuse: Adapting foundational diffusion models for layout-to-image generation","author":"Jiaxin","year":"2023"},{"key":"ref37","first-page":"1737","article-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Bar-Tal","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref39","first-page":"1","article-title":"GeoDiffusion: Text-prompted geometric control for object detection data generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_23"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref44","first-page":"42098","article-title":"X-Paste: Revisiting scalable copy-paste for instance segmentation using CLIP and stablediffusion","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01001"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01339"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112141"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00129"},{"key":"ref49","first-page":"1","article-title":"Synthetic data from diffusion models improves imagenet classification","volume":"2023","author":"Azizi","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref50","first-page":"79024","article-title":"Diversify your vision datasets with automatic diffusion-based augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dunlap","year":"2024"},{"key":"ref51","first-page":"1","article-title":"Is synthetic data from generative models ready for image recognition?","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"He","year":"2022"},{"key":"ref52","article-title":"Is synthetic data from diffusion models ready for knowledge distillation?","author":"Li","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00774"},{"key":"ref54","first-page":"1","article-title":"Effective data augmentation with diffusion models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Trabucco","year":"2023"},{"key":"ref55","first-page":"54683","article-title":"DatasetDM: Synthesizing data with perception annotations using diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_6"},{"key":"ref57","article-title":"Prompting diffusion representations for cross-domain semantic segmentation","author":"Gong","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01317"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00081"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"ref61","first-page":"18659","article-title":"FreeMask: Synthetic images with dense annotations make stronger segmentation models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00705"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref66","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel","year":"2017"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref69","article-title":"The pascal visual object classes challenge 2007","author":"Everingham","year":"2009"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.10.039"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref77","first-page":"78723","article-title":"T2I-CompBench: A comprehensive benchmark for open-world compositional text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang","year":"2024"},{"key":"ref78","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11275622\/11164381.pdf?arnumber=11164381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T21:01:29Z","timestamp":1764882089000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11164381\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":78,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3609962","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}