{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T09:10:20Z","timestamp":1733130620821,"version":"3.30.0"},"reference-count":74,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1016\/j.neucom.2024.128764","type":"journal-article","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T17:15:51Z","timestamp":1730135751000},"page":"128764","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Diffusion model conditioning on Gaussian mixture model and negative Gaussian mixture gradient"],"prefix":"10.1016","volume":"614","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-7484-9221","authenticated-orcid":false,"given":"Weiguo","family":"Lu","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0009-0004-5130-3041","authenticated-orcid":false,"given":"Xuan","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Deng","family":"Ding","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-2077-990X","authenticated-orcid":false,"given":"Jinqiao","family":"Duan","sequence":"additional","affiliation":[]},{"given":"Jirong","family":"Zhuang","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-0582-512X","authenticated-orcid":false,"given":"Gangnan","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2024.128764_b1","series-title":"International Conference on Machine Learning","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015"},{"article-title":"Denoising diffusion probabilistic models","year":"2020","series-title":"NeurIPS","author":"Ho","key":"10.1016\/j.neucom.2024.128764_b2"},{"key":"10.1016\/j.neucom.2024.128764_b3","article-title":"Generative modeling by estimating gradients of the data distribution","volume":"32","author":"Song","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"year":"2021","series-title":"Variational diffusion models","author":"Kingma","key":"10.1016\/j.neucom.2024.128764_b4"},{"key":"10.1016\/j.neucom.2024.128764_b5","first-page":"12438","article-title":"Improved techniques for training score-based generative models","volume":"33","author":"Song","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2024.128764_b6","doi-asserted-by":"crossref","unstructured":"R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, High-resolution image synthesis with latent diffusion models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.neucom.2024.128764_b7","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2024.128764_b8","first-page":"6126","article-title":"SphereDiffusion: Spherical geometry-aware distortion resilient diffusion model","volume":"vol. 38","author":"Wu","year":"2024"},{"article-title":"Wavegrad: Estimating gradients for waveform generation","year":"2021","series-title":"ICLR","author":"Chen","key":"10.1016\/j.neucom.2024.128764_b9"},{"year":"2020","series-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","key":"10.1016\/j.neucom.2024.128764_b10"},{"year":"2021","series-title":"Symbolic music generation with diffusion models","author":"Mittal","key":"10.1016\/j.neucom.2024.128764_b11"},{"issue":"4","key":"10.1016\/j.neucom.2024.128764_b12","first-page":"4713","article-title":"Image super-resolution via iterative refinement","volume":"45","author":"Saharia","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2024.128764_b13","series-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.neucom.2024.128764_b14","unstructured":"D. Kingma, M. Welling, Auto-encoding variational bayes, in: 2nd International Conference on Learning Representations, ICLR, 2014."},{"key":"10.1016\/j.neucom.2024.128764_b15","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2024.128764_b16","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2024.128764_b17","first-page":"2","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"vol. 1","author":"Devlin","year":"2019"},{"key":"10.1016\/j.neucom.2024.128764_b18","doi-asserted-by":"crossref","unstructured":"Z. Liu, P. Luo, X. Wang, X. Tang, Deep Learning Face Attributes in the Wild, in: Proceedings of International Conference on Computer Vision, ICCV, 2015.","DOI":"10.1109\/ICCV.2015.425"},{"key":"10.1016\/j.neucom.2024.128764_b19","series-title":"International Conference on Machine Learning","first-page":"1060","article-title":"Generative adversarial text to image synthesis","author":"Reed","year":"2016"},{"key":"10.1016\/j.neucom.2024.128764_b20","doi-asserted-by":"crossref","unstructured":"P. Isola, J.Y. Zhu, T. Zhou, A.A. Efros, Image-to-image translation with conditional adversarial networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1125\u20131134.","DOI":"10.1109\/CVPR.2017.632"},{"key":"10.1016\/j.neucom.2024.128764_b21","doi-asserted-by":"crossref","unstructured":"T. Park, M.Y. Liu, T.C. Wang, J.Y. Zhu, Semantic image synthesis with spatially-adaptive normalization, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 2337\u20132346.","DOI":"10.1109\/CVPR.2019.00244"},{"key":"10.1016\/j.neucom.2024.128764_b22","doi-asserted-by":"crossref","unstructured":"G. Zheng, X. Zhou, X. Li, Z. Qi, Y. Shan, X. Li, Layoutdiffusion: Controllable diffusion model for layout-to-image generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 22490\u201322499.","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"10.1016\/j.neucom.2024.128764_b23","doi-asserted-by":"crossref","unstructured":"L. Zhang, A. Rao, M. Agrawala, Adding conditional control to text-to-image diffusion models, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 3836\u20133847.","DOI":"10.1109\/ICCV51070.2023.00355"},{"issue":"11","key":"10.1016\/j.neucom.2024.128764_b24","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"year":"2019","series-title":"Logan: Latent optimisation for generative adversarial networks","author":"Wu","key":"10.1016\/j.neucom.2024.128764_b25"},{"key":"10.1016\/j.neucom.2024.128764_b26","doi-asserted-by":"crossref","unstructured":"T. Karras, S. Laine, M. Aittala, J. Hellsten, J. Lehtinen, T. Aila, Analyzing and improving the image quality of stylegan, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 8110\u20138119.","DOI":"10.1109\/CVPR42600.2020.00813"},{"year":"2018","series-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","key":"10.1016\/j.neucom.2024.128764_b27"},{"year":"2014","series-title":"Conditional generative adversarial nets","author":"Mirza","key":"10.1016\/j.neucom.2024.128764_b28"},{"year":"2017","series-title":"A learned representation for artistic style","author":"Dumoulin","key":"10.1016\/j.neucom.2024.128764_b29"},{"key":"10.1016\/j.neucom.2024.128764_b30","article-title":"Modulating early visual processing by language","volume":"30","author":"De Vries","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"year":"2018","series-title":"cGANs with projection discriminator","author":"Miyato","key":"10.1016\/j.neucom.2024.128764_b31"},{"key":"10.1016\/j.neucom.2024.128764_b32","series-title":"International Conference on Machine Learning","first-page":"4183","article-title":"High-fidelity image generation with fewer labels","author":"Lucic","year":"2019"},{"year":"2017","series-title":"Tac-gan-text conditioned auxiliary classifier generative adversarial network","author":"Dash","key":"10.1016\/j.neucom.2024.128764_b33"},{"key":"10.1016\/j.neucom.2024.128764_b34","doi-asserted-by":"crossref","unstructured":"O. Lang, Y. Gandelsman, M. Yarom, Y. Wald, G. Elidan, A. Hassidim, W.T. Freeman, P. Isola, A. Globerson, M. Irani, I. Mosseri, Explaining in style: Training a gan to explain a classifier in stylespace, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 693\u2013702.","DOI":"10.1109\/ICCV48922.2021.00073"},{"year":"2023","series-title":"An efficient Gaussian mixture model and its application to neural network","author":"Lu","key":"10.1016\/j.neucom.2024.128764_b35"},{"year":"2017","series-title":"Towards principled methods for training generative adversarial networks","author":"Arjovsky","key":"10.1016\/j.neucom.2024.128764_b36"},{"key":"10.1016\/j.neucom.2024.128764_b37","series-title":"International Conference on Machine Learning","first-page":"214","article-title":"Wasserstein generative adversarial networks","author":"Arjovsky","year":"2017"},{"key":"10.1016\/j.neucom.2024.128764_b38","series-title":"MACIS","first-page":"579","article-title":"Maximum likelihood estimates for Gaussian mixtures are transcendental","author":"Am\u00e9ndola","year":"2015"},{"key":"10.1016\/j.neucom.2024.128764_b39","first-page":"3","article-title":"Analysis of stopping criteria for the EM algorithm in the context of patient grouping according to length of stay","volume":"1","author":"Abbi","year":"2008","journal-title":"IEEE Intell. Syst."},{"key":"10.1016\/j.neucom.2024.128764_b40","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1016\/S0167-9473(02)00163-9","article-title":"Choosing starting values for the EM algorithm for getting the highest likelihood in multivariate Gaussian mixture models","volume":"41","author":"Biernackia","year":"2003","journal-title":"Comput. Statist. Data Anal."},{"year":"2013","series-title":"Simple methods for initializing the EM algorithm for Gaussian mixture models","author":"Bl\u00f6mer","key":"10.1016\/j.neucom.2024.128764_b41"},{"volume":"vol. 29","article-title":"Local maxima in the likelihood of Gaussian mixture models: Structural results and algorithmic consequences","year":"2016","author":"Chi","key":"10.1016\/j.neucom.2024.128764_b42"},{"key":"10.1016\/j.neucom.2024.128764_b43","series-title":"IEEE NSS\/MIC","first-page":"1163","article-title":"Study of the convergence properties of the EM algorithm-a new stopping rule","author":"Kontaxakis","year":"1992"},{"key":"10.1016\/j.neucom.2024.128764_b44","series-title":"NEBEC","first-page":"52","article-title":"Further study of a stopping rule for the EM algorithm","author":"Kontaxakis","year":"1993"},{"key":"10.1016\/j.neucom.2024.128764_b45","series-title":"CORES","first-page":"81","article-title":"A new method for random initialization of the EM algorithm for multivariate Gaussian mixture learning","author":"Kwedlo","year":"2013"},{"key":"10.1016\/j.neucom.2024.128764_b46","first-page":"91","article-title":"Initializing the EM algorithm for use in Gaussian mixture modelling","author":"McKenzie","year":"1994","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2024.128764_b47","series-title":"ANNs\/GAs","first-page":"406","article-title":"A new method for random initialization of the EM algorithm for multivariate Gaussian mixture learning","author":"Pacl\u00edk","year":"2001"},{"issue":"1","key":"10.1016\/j.neucom.2024.128764_b48","doi-asserted-by":"crossref","first-page":"282","DOI":"10.3758\/s13428-015-0697-6","article-title":"Examining the effect of initialization strategies on the performance of Gaussian mixture modeling","volume":"49","author":"Shireman","year":"2017","journal-title":"Behav. Res. Methods"},{"key":"10.1016\/j.neucom.2024.128764_b49","series-title":"COLT","first-page":"628","article-title":"Are there local maxima in the infinite-sample likelihood of Gaussian mixture estimation?","author":"Srebro","year":"2007"},{"year":"2023","series-title":"An efficient 1 iteration learning algorithm for Gaussian mixture model and Gaussian mixture embedding for neural network","author":"Lu","key":"10.1016\/j.neucom.2024.128764_b50"},{"year":"2021","series-title":"Non Gaussian denoising diffusion models","author":"Nachmani","key":"10.1016\/j.neucom.2024.128764_b51"},{"key":"10.1016\/j.neucom.2024.128764_b52","doi-asserted-by":"crossref","unstructured":"S. Kolouri, G.K. Rohde, H. Hoffmann, Sliced Wasserstein distance for learning Gaussian mixture models, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 3427\u20133436.","DOI":"10.1109\/CVPR.2018.00361"},{"year":"2024","series-title":"Deconstructing denoising diffusion models for self-supervised learning","author":"Chen","key":"10.1016\/j.neucom.2024.128764_b53"},{"year":"2009","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","key":"10.1016\/j.neucom.2024.128764_b54"},{"key":"10.1016\/j.neucom.2024.128764_b55","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"year":"2015","series-title":"A neural algorithm of artistic style","author":"Gatys","key":"10.1016\/j.neucom.2024.128764_b56"},{"key":"10.1016\/j.neucom.2024.128764_b57","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2024.128764_b58","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2024.128764_b59","doi-asserted-by":"crossref","unstructured":"C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna, Rethinking the inception architecture for computer vision, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2818\u20132826.","DOI":"10.1109\/CVPR.2016.308"},{"year":"2023","series-title":"Improved techniques for training consistency models","author":"Song","key":"10.1016\/j.neucom.2024.128764_b60"},{"year":"2022","series-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","key":"10.1016\/j.neucom.2024.128764_b61"},{"year":"2022","series-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","key":"10.1016\/j.neucom.2024.128764_b62"},{"key":"10.1016\/j.neucom.2024.128764_b63","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume":"35","author":"Karras","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"year":"2020","series-title":"Denoising diffusion implicit models","author":"Song","key":"10.1016\/j.neucom.2024.128764_b64"},{"year":"2021","series-title":"Tackling the generative learning trilemma with denoising diffusion GANs","author":"Xiao","key":"10.1016\/j.neucom.2024.128764_b65"},{"key":"10.1016\/j.neucom.2024.128764_b66","doi-asserted-by":"crossref","unstructured":"G. Parmar, D. Li, K. Lee, Z. Tu, Dual contradistinctive generative autoencoder, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2021, 2021, pp. 823\u2013832.","DOI":"10.1109\/CVPR46437.2021.00088"},{"year":"2021","series-title":"Knowledge distillation in iterative generative models for improved sampling speed","author":"Luhman","key":"10.1016\/j.neucom.2024.128764_b67"},{"key":"10.1016\/j.neucom.2024.128764_b68","doi-asserted-by":"crossref","unstructured":"G. Parmar, R. Zhang, J.Y. Zhu, On aliased resizing and surprising subtleties in gan evaluation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11410\u201311420.","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"10.1016\/j.neucom.2024.128764_b69","doi-asserted-by":"crossref","unstructured":"S. Jayasumana, S. Ramalingam, A. Veit, D. Glasner, A. Chakrabarti, S. Kumar, Rethinking FID: Towards a better evaluation metric for image generation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 9307\u20139315.","DOI":"10.1109\/CVPR52733.2024.00889"},{"year":"2023","series-title":"Consistency trajectory models: Learning probability flow ode trajectory of diffusion","author":"Kim","key":"10.1016\/j.neucom.2024.128764_b70"},{"year":"2023","series-title":"Consistency models","author":"Song","key":"10.1016\/j.neucom.2024.128764_b71"},{"year":"2022","series-title":"Refining generative process with discriminator guidance in score-based diffusion models","author":"Kim","key":"10.1016\/j.neucom.2024.128764_b72"},{"issue":"1","key":"10.1016\/j.neucom.2024.128764_b73","first-page":"2249","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2024.128764_b74","series-title":"NIPS","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231224015352?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231224015352?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T08:29:23Z","timestamp":1733128163000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231224015352"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":74,"alternative-id":["S0925231224015352"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2024.128764","relation":{},"ISSN":["0925-2312"],"issn-type":[{"type":"print","value":"0925-2312"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Diffusion model conditioning on Gaussian mixture model and negative Gaussian mixture gradient","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2024.128764","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"128764"}}
