{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T08:15:05Z","timestamp":1768896905652,"version":"3.49.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AI Singapore Programme","award":["AISG2-PhD-2022-01-029"],"award-info":[{"award-number":["AISG2-PhD-2022-01-029"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tpami.2025.3572476","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T13:58:37Z","timestamp":1747922317000},"page":"7675-7688","source":"Crossref","is-referenced-by-count":1,"title":["Benchmarking and Analyzing Generative Data for Visual Recognition"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8447-0928","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"first","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5822-7385","authenticated-orcid":false,"given":"Haotian","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5181-8457","authenticated-orcid":false,"given":"Liangyu","family":"Chen","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9863-1270","authenticated-orcid":false,"given":"Yong Jae","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"FER 2013: Kaggle challenges in representation learning facial expression recognition","year":"2013"},{"key":"ref2","article-title":"Leaving reality to imagination: Robust classification via generated datasets","author":"Bansal","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053146"},{"key":"ref4","article-title":"Retrieval-augmented diffusion models","author":"Blattmann","year":"2022"},{"key":"ref5","article-title":"Improving language models by retrieving from trillions of tokens","author":"Borgeaud","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref7","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2018"},{"key":"ref8","article-title":"Making your first choice: To address cold start problem in vision active learning","author":"Chen","year":"2022"},{"key":"ref9","article-title":"Analog bits: Generating discrete data using diffusion models with self-conditioning","author":"Chen","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.375"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref13","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2013.6728473"},{"key":"ref18","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref20","article-title":"REALM: Retrieval-augmented language model pre-training","author":"Guu","year":"2020"},{"key":"ref21","article-title":"Is synthetic data from generative models ready for image recognition?","author":"He","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2019.2918242"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref24","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref25","article-title":"Generative models as a data source for multiview representation learning","author":"Jahanian","year":"2021"},{"key":"ref26","article-title":"Generalization through memorization: Nearest neighbor language models","author":"Khandelwal","year":"2019"},{"key":"ref27","first-page":"2611","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kiela"},{"key":"ref28","article-title":"On fast sampling of diffusion probabilistic models","author":"Kong","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref30","first-page":"32","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref32","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lewis"},{"key":"ref33","article-title":"Elevater: A benchmark and toolkit for evaluating language-augmented visual models","author":"Li","year":"2022"},{"key":"ref34","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01454"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5681"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00683"},{"key":"ref39","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01389"},{"key":"ref41","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref42","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref45","article-title":"VisDA: The visual domain adaptation challenge","author":"Peng","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1005"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"issue":"1","key":"ref48","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref50","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref54","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00084"},{"key":"ref56","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref57","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033395"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00934-2_24"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20174"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref63","article-title":"Retrieval-augmented multimodal language modeling","author":"Yasunaga","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.150"},{"key":"ref65","article-title":"A large-scale study of representation learning with the visual task adaptation benchmark","author":"Zhai","year":"2019"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11118328\/11010883.pdf?arnumber=11010883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:44:11Z","timestamp":1754588651000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11010883\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":66,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3572476","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":[[2025,9]]}}}