{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T13:16:29Z","timestamp":1792588589989,"version":"4.5.0"},"reference-count":183,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tpami.2026.3658965","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:23:36Z","timestamp":1769721816000},"page":"7209-7228","source":"Crossref","is-referenced-by-count":16,"title":["Diffusion Models and Representation Learning: A Survey"],"prefix":"10.1109","volume":"48","author":[{"given":"Michael","family":"Fuest","sequence":"first","affiliation":[{"name":"Technical University of Munich, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1367-6195","authenticated-orcid":false,"given":"Pingchuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Ludwig Maximilian University of Munich, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4623-5912","authenticated-orcid":false,"given":"Ming","family":"Gui","sequence":"additional","affiliation":[{"name":"Ludwig Maximilian University of Munich, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9504-3844","authenticated-orcid":false,"given":"Johannes","family":"Schusterbauer","sequence":"additional","affiliation":[{"name":"Ludwig Maximilian University of Munich, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1561-3216","authenticated-orcid":false,"given":"Vincent Tao","family":"Hu","sequence":"additional","affiliation":[{"name":"Ludwig Maximilian University of Munich, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0766-120X","authenticated-orcid":false,"given":"Bj\u00f6rn","family":"Ommer","sequence":"additional","affiliation":[{"name":"Ludwig Maximilian University of Munich, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Exploring the limits of deep image clustering using pretrained models","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Adaloglou","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00355"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00523"},{"key":"ref5","article-title":"Building normalizing flows with stochastic interpolants","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Albergo","year":"2023"},{"key":"ref6","article-title":"Protein structure and sequence generation with equivariant denoising diffusion probabilistic models","volume-title":"Proc. Proc. Adv. Neural Inf. Process. Syst. Workshop","author":"Anand","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"ref8","article-title":"Self-labelling via simultaneous clustering and representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Asano","year":"2020"},{"key":"ref9","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Austin","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32174"},{"key":"ref11","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref13","first-page":"1692","article-title":"One transformer fits all distributions in multi-modal diffusion at scale","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bao","year":"2023"},{"key":"ref14","article-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bar-Tal","year":"2023"},{"key":"ref15","article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baranchuk","year":"2022"},{"key":"ref16","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref17","article-title":"D-Flow: Differentiating through flows for controlled generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ben-Hamu","year":"2024"},{"key":"ref18","article-title":"Generalized denoising auto-encoders as generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Bengio","year":"2013"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01119"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1114"},{"key":"ref21","article-title":"Large scale gan training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref24","first-page":"27517","article-title":"Instance-conditioned GAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Casanova","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111934"},{"key":"ref27","article-title":"The hidden language of diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chefer","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02597-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1412.7062"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref31","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref33","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen","year":"2020"},{"key":"ref34","article-title":"Deconstructing denoising diffusion models for self-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref37","article-title":"Flow matching in latent space","author":"Dao","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02126"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43415-0_32"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref41","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref42","article-title":"Large scale adversarial representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Donahue","year":"2019"},{"key":"ref43","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0714"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref47","article-title":"Scalable diffusion models with state space backbone","author":"Fei","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01208"},{"key":"ref49","article-title":"TokenFlow: Consistent diffusion features for consistent video editing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Geyer","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1070"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref53","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Gu","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32330"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00721"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2724510"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0363"},{"key":"ref60","article-title":"Multistep consistency models","author":"Heek","year":"2024"},{"key":"ref61","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref62","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshop","author":"Hinton","year":"2014"},{"key":"ref63","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. Proc. Adv. Neural Inf. Process. Syst. Workshop","author":"Ho","year":"2021"},{"key":"ref64","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00686"},{"key":"ref66","first-page":"8867","article-title":"Equivariant diffusion for molecule generation in 3D","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hoogeboom","year":"2022"},{"key":"ref67","first-page":"13213","article-title":"simple diffusion: End-to-end diffusion for high resolution images","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hoogeboom","year":"2023"},{"key":"ref68","article-title":"Guided diffusion from self-supervised diffusion features","author":"Hu","year":"2023"},{"key":"ref69","article-title":"Motion flow matching for human motion synthesis and editing","author":"Hu","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01766"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_9"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-short.33"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27998"},{"key":"ref74","article-title":"A variational perspective on diffusion-based generative models and score matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang","year":"2021"},{"key":"ref75","first-page":"13916","article-title":"Make-an-Audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Huang","year":"2023"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3541625"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02181"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1017\/S0027763000022819"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110474"},{"key":"ref82","first-page":"21696","article-title":"Variational diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kingma","year":"2021"},{"key":"ref83","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref87","article-title":"Diffusion models already have a semantic latent space","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kwon","year":"2023"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01531"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref92","article-title":"MoEController: Instruction-based arbitrary image manipulation with mixture-of-expert controllers","author":"Li","year":"2024"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"ref94","first-page":"125441","article-title":"Return of unconditional generation: A self-supervised representation generation method","volume":"37","author":"Li","year":"2024","journal-title":"Adv. Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref95","first-page":"4328","article-title":"Diffusion-LM improves controllable text generation","volume":"35","author":"Li","year":"2022","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref96","article-title":"SimSC: A simple framework for semantic correspondence with temperature learning","author":"Li","year":"2023"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02602"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.344"},{"key":"ref99","article-title":"Diffusion model with perceptual Loss","author":"Lin","year":"2024"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref101","article-title":"Flow matching for generative modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lipman","year":"2023"},{"key":"ref102","article-title":"Ringattention with blockwise transformers for near-infinite context","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2024"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01429"},{"key":"ref105","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2023"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658542"},{"key":"ref109","article-title":"Understanding diffusion models: A unified perspective","author":"Luo","year":"2022"},{"key":"ref110","first-page":"47500","article-title":"Diffusion hyperfeatures: Searching through time and space for semantic correspondence","volume":"36","author":"Luo","year":"2023","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00785"},{"key":"ref112","first-page":"76525","article-title":"Diff-instruct: A universal approach for transferring knowledge from pre-trained diffusion models","volume":"36","author":"Luo","year":"2024","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref113","article-title":"A variational perspective on solving inverse problems with diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mardani","year":"2024"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01846"},{"key":"ref115","article-title":"Long range language modeling via gated state spaces","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mehta","year":"2023"},{"key":"ref116","article-title":"SPair-71k: A large-scale benchmark for semantic correspondence","author":"Min","year":"2019"},{"key":"ref117","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014"},{"key":"ref118","article-title":"Diffusion based representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mittal","year":"2023"},{"key":"ref119","article-title":"Diffusion models beat GANs on image classification","author":"Mukhopadhyay","year":"2023"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_15"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0206"},{"key":"ref122","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00732"},{"key":"ref124","article-title":"Masked diffusion as self-supervised representation learner","author":"Pan","year":"2024"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00735"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15063"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"ref129","volume-title":"Understanding Deep Learning","author":"Prince","year":"2023"},{"key":"ref130","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref131","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":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref133","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Romero","year":"2015"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref136","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Salimans","year":"2022"},{"key":"ref137","first-page":"24","article-title":"PixelCNN++: A PixelCNN implementation with discretized logistic mixture likelihood and other modifications","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Salimans","year":"2017"},{"key":"ref138","first-page":"36046","article-title":"Multistep distillation of diffusion models via moment matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Salimans","year":"2024"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28270"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687625"},{"key":"ref141","article-title":"Generative data augmentation improves scribble-supervised semantic segmentation","author":"Schnell","year":"2023"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_19"},{"key":"ref143","article-title":"kNN-diffusion: Image generation via large-scale retrieval","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sheynin","year":"2023"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00084"},{"key":"ref145","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref146","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref147","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Song","year":"2019"},{"key":"ref148","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref149","article-title":"Consistency models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song","year":"2023"},{"key":"ref150","first-page":"49761","article-title":"Flow factorized representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Song","year":"2024"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref152","article-title":"ADDP: Learning general representations for image recognition and generation with alternating denoising diffusion process","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tian","year":"2024"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref157","first-page":"9786","article-title":"Unsupervised discovery of interpretable directions in the GAN latent space","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Voynov","year":"2020"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00669"},{"key":"ref159","first-page":"36336","article-title":"InfoDiffusion: Representation learning using information maximizing diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2023"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01492"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01448"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00787"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01736"},{"key":"ref167","article-title":"Your ViT is secretly a hybrid discriminative-generative diffusion model","author":"Yang","year":"2022"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00809"},{"key":"ref169","first-page":"43479","article-title":"Diffusion models and semi-supervised learners benefit mutually with few labels","volume-title":"Proc. Proc. Adv. Neural Inf. Process. Syst.","author":"You","year":"2023"},{"key":"ref170","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02118"},{"key":"ref173","article-title":"Exploring diffusion time-steps for unsupervised representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yue","year":"2024"},{"key":"ref174","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zagoruyko","year":"2017"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1973"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00297"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1607"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref181","first-page":"42363","article-title":"Improved techniques for maximum likelihood estimation for diffusion ODEs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng","year":"2023"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref183","article-title":"Score-based generative classifiers","volume-title":"Proc. NeurIPS Workshop Deep Generative Models Downstream Appl.","author":"Zimmermann","year":"2021"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11552636\/11367476.pdf?arnumber=11367476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:51:49Z","timestamp":1780948309000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11367476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":183,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3658965","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":[[2026,7]]}}}