{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T04:24:00Z","timestamp":1769315040894,"version":"3.49.0"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730290","type":"print"},{"value":"9783031730306","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T00:00:00Z","timestamp":1732406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73030-6_4","type":"book-chapter","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T16:58:11Z","timestamp":1732553891000},"page":"54-71","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Mixture of\u00a0Efficient Diffusion Experts Through Automatic Interval and\u00a0Sub-network Selection"],"prefix":"10.1007","author":[{"given":"Alireza","family":"Ganjdanesh","sequence":"first","affiliation":[]},{"given":"Yan","family":"Kang","sequence":"additional","affiliation":[]},{"given":"Yuchen","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Richard","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhe","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Heng","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,24]]},"reference":[{"key":"4_CR1","unstructured":"Balaji, Y., et\u00a0al.: ediffi: Text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"4_CR2","unstructured":"Bao, F., Li, C., Zhu, J., Zhang, B.: Analytic-DPM: an analytic estimate of the optimal reverse variance in diffusion probabilistic models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=0xiJLKH-ufZ"},{"key":"4_CR3","unstructured":"Bengio, Y., L\u00e9onard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)"},{"key":"4_CR4","unstructured":"Betker, J., et\u00a0al.: Improving image generation with better captions. Comput. Sci. 2(3), 8 (2023). https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf"},{"key":"4_CR5","unstructured":"Cai, H., Gan, C., Wang, T., Zhang, Z., Han, S.: Once-for-all: train one network and specialize it for efficient deployment. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=HylxE1HKwS"},{"key":"4_CR6","doi-asserted-by":"publisher","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, 25\u201329 October 2014, Doha, Qatar, A Meeting of SIGDAT, a Special Interest Group of the ACL. ACL (2014). https:\/\/doi.org\/10.3115\/v1\/d14-1179","DOI":"10.3115\/v1\/d14-1179"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Choi, J., Lee, J., Shin, C., Kim, S., Kim, H., Yoon, S.: Perception prioritized training of diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11472\u201311481 (2022)","DOI":"10.1109\/CVPR52688.2022.01118"},{"key":"4_CR8","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems, vol. 34, pp. 8780\u20138794 (2021)"},{"key":"4_CR9","unstructured":"Fang, G., Ma, X., Wang, X.: Structural pruning for diffusion models. In: Advances in Neural Information Processing Systems (2023)"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Feng, Z., et\u00a0al.: Ernie-vilg 2.0: improving text-to-image diffusion model with knowledge-enhanced mixture-of-denoising-experts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10135\u201310145 (2023)","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Gao, S., et al.: Implicit diffusion models for continuous super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10021\u201310030 (2023)","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"4_CR12","unstructured":"Go, H., et al.: Addressing negative transfer in diffusion models. In: Thirty-Seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=3G2ec833mW"},{"key":"4_CR13","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. IN: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"4_CR14","unstructured":"Gumbel, E.J.: Statistical Theory of Extreme Values and Some Practical Applications: A Series of Lectures, vol.\u00a033. US Government Printing Office (1954)"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Habibian, A., et al.: Clockwork diffusion: efficient generation with model-step distillation. arXiv preprint arXiv:2312.08128 (2023)","DOI":"10.1109\/CVPR52733.2024.00798"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR17","unstructured":"Ho, J., et\u00a0al.: Imagen video: high definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"4_CR18","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"4_CR19","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. In: International Conference on Learning Representations (2017). https:\/\/openreview.net\/forum?id=rkE3y85ee"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"4_CR21","unstructured":"Kingma, D., Salimans, T., Poole, B., Ho, J.: Variational diffusion models. In: Advances in Neural Information Processing Systems, vol. 34, pp. 21696\u201321707 (2021)"},{"key":"4_CR22","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: Bengio, Y., LeCun, Y. (eds.) 2nd International Conference on Learning Representations. ICLR 2014, Banff, AB, Canada, 14\u201316 April 2014, Conference Track Proceedings (2014). http:\/\/arxiv.org\/abs\/1312.6114"},{"key":"4_CR23","unstructured":"Lee, Y., Kim, J.Y., Go, H., Jeong, M., Oh, S., Choi, S.: Multi-architecture multi-expert diffusion models. arXiv preprint arXiv:2306.04990 (2023)"},{"key":"4_CR24","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. In: International Conference on Learning Representations (2017). https:\/\/openreview.net\/forum?id=rJqFGTslg"},{"key":"4_CR25","unstructured":"Liu, E., Ning, X., Lin, Z., Yang, H., Wang, Y.: OMS-DPM: optimizing the model schedule for diffusion probabilistic models. In: International Conference on Machine Learning, pp. 21915\u201321936. PMLR (2023)"},{"key":"4_CR26","unstructured":"Liu, L., Ren, Y., Lin, Z., Zhao, Z.: Pseudo numerical methods for diffusion models on manifolds. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=PlKWVd2yBkY"},{"key":"4_CR27","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. In: Advances in Neural Information Processing Systems, vol. 35, pp. 5775\u20135787 (2022)"},{"key":"4_CR28","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver++: fast solver for guided sampling of diffusion probabilistic models (2023). https:\/\/openreview.net\/forum?id=4vGwQqviud5"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Ma, X., Fang, G., Wang, X.: Deepcache: accelerating diffusion models for free. arXiv preprint arXiv:2312.00858 (2023)","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"4_CR30","unstructured":"Maddison, C.J., Mnih, A., Teh, Y.W.: The concrete distribution: a continuous relaxation of discrete random variables. In: International Conference on Learning Representations (2017). https:\/\/openreview.net\/forum?id=S1jE5L5gl"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Meng, C., et al.: On distillation of guided diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14297\u201314306 (2023)","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"4_CR32","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"4_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015, Part III. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"issue":"3","key":"4_CR35","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision (IJCV) 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vision (IJCV)"},{"issue":"4","key":"4_CR36","first-page":"4713","volume":"45","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D.J., Norouzi, M.: Image super-resolution via iterative refinement. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4713\u20134726 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR37","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=TIdIXIpzhoI"},{"key":"4_CR38","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"4_CR39","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"4_CR40","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"4_CR41","unstructured":"Vaswani, A., et al.:: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"4_CR42","unstructured":"Watson, D., Chan, W., Ho, J., Norouzi, M.: Learning fast samplers for diffusion models by differentiating through sample quality. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=VFBjuF8HEp"},{"key":"4_CR43","unstructured":"Watson, D., Ho, J., Norouzi, M., Chan, W.: Learning to efficiently sample from diffusion probabilistic models (2022). https:\/\/openreview.net\/forum?id=LOz0xDpw4Y"},{"key":"4_CR44","unstructured":"Xu, Y., Deng, M., Cheng, X., Tian, Y., Liu, Z., Jaakkola, T.: Restart sampling for improving generative processes. arXiv preprint arXiv:2306.14878 (2023)"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Yang, X., Zhou, D., Feng, J., Wang, X.: Diffusion probabilistic model made slim. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22552\u201322562 (2023)","DOI":"10.1109\/CVPR52729.2023.02160"},{"key":"4_CR46","unstructured":"Yu, F., Zhang, Y., Song, S., Seff, A., Xiao, J.: Lsun: construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365 (2015)"},{"key":"4_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, H., Lu, Y., Alkhouri, I., Ravishankar, S., Song, D., Qu, Q.: Improving efficiency of diffusion models via multi-stage framework and tailored multi-decoder architectures. arXiv preprint arXiv:2312.09181 (2023)","DOI":"10.1109\/CVPR52733.2024.00704"},{"key":"4_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"4_CR49","unstructured":"Zhang, Q., Chen, Y.: Fast sampling of diffusion models with exponential integrator. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=Loek7hfb46P"},{"key":"4_CR50","unstructured":"Zhang, Q., Tao, M., Chen, Y.: gDDIM: Generalized denoising diffusion implicit models. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=1hKE9qjvz-"},{"key":"4_CR51","unstructured":"Zhao, S., et al.: Uni-controlnet: all-in-one control to text-to-image diffusion models. arXiv preprint arXiv:2305.16322 (2023)"},{"key":"4_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xu, Y., Xiao, Z., Hou, T.: Mobilediffusion: subsecond text-to-image generation on mobile devices. arXiv preprint arXiv:2311.16567 (2023)","DOI":"10.1007\/978-3-031-73033-7_13"},{"key":"4_CR53","unstructured":"Zheng, H., He, P., Chen, W., Zhou, M.: Truncated diffusion probabilistic models and diffusion-based adversarial auto-encoders. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=HDxgaKk956l"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73030-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T17:10:54Z","timestamp":1732554654000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73030-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,24]]},"ISBN":["9783031730290","9783031730306"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73030-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,24]]},"assertion":[{"value":"24 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}