{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:03:34Z","timestamp":1777655014425,"version":"3.51.4"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031736674","type":"print"},{"value":"9783031736681","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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\/978-3-031-73668-1_27","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:04:01Z","timestamp":1733018641000},"page":"461-477","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Switch Diffusion Transformer: Synergizing Denoising Tasks with\u00a0Sparse Mixture-of-Experts"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1930-2266","authenticated-orcid":false,"given":"Byeongjun","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5470-042X","authenticated-orcid":false,"given":"Hyojun","family":"Go","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9106-2922","authenticated-orcid":false,"given":"Jin-Young","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4451-9675","authenticated-orcid":false,"given":"Sangmin","family":"Woo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4400-847X","authenticated-orcid":false,"given":"Seokil","family":"Ham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9323-8488","authenticated-orcid":false,"given":"Changick","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,1]]},"reference":[{"key":"27_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":"27_CR2","doi-asserted-by":"crossref","unstructured":"Bao, F., et al.: All are worth words: a vit backbone for diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22669\u201322679 (2023)","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"27_CR4","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":"27_CR5","unstructured":"Clark, A., et\u00a0al.: Unified scaling laws for routed language models. In: International Conference on Machine Learning, pp. 4057\u20134086. PMLR (2022)"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"27_CR7","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"27_CR8","first-page":"5232","volume":"23","author":"W Fedus","year":"2022","unstructured":"Fedus, W., Zoph, B., Shazeer, N.: Switch transformers: scaling to trillion parameter models with simple and efficient sparsity. J. Mach. Learn. Res. 23(1), 5232\u20135270 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"27_CR9","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":"27_CR10","doi-asserted-by":"crossref","unstructured":"Gao, S., Zhou, P., Cheng, M.M., Yan, S.: Masked diffusion transformer is a strong image synthesizer. arXiv preprint arXiv:2303.14389 (2023)","DOI":"10.1109\/ICCV51070.2023.02117"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Go, H., et al.: Towards practical plug-and-play diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1962\u20131971 (2023)","DOI":"10.1109\/CVPR52729.2023.00195"},{"key":"27_CR12","unstructured":"Go, H., Lee, Y., Lee, S., Oh, S., Moon, H., Choi, S.: Addressing negative transfer in diffusion models. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"27_CR13","unstructured":"Goyal, P., et al.: Accurate, large minibatch sgd: training imagenet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Hang, T., et al.: Efficient diffusion training via min-snr weighting strategy. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7441\u20137451 (2023)","DOI":"10.1109\/ICCV51070.2023.00684"},{"key":"27_CR15","first-page":"27953","volume":"35","author":"W Harvey","year":"2022","unstructured":"Harvey, W., Naderiparizi, S., Masrani, V., Weilbach, C., Wood, F.: Flexible diffusion modeling of long videos. Adv. Neural. Inf. Process. Syst. 35, 27953\u201327965 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR16","first-page":"29335","volume":"34","author":"H Hazimeh","year":"2021","unstructured":"Hazimeh, H., et al.: Dselect-k: differentiable selection in the mixture of experts with applications to multi-task learning. Adv. Neural. Inf. Process. Syst. 34, 29335\u201329347 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR17","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"27_CR18","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR19","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2021). https:\/\/openreview.net\/forum?id=qw8AKxfYbI"},{"key":"27_CR20","unstructured":"Jabri, A., Fleet, D., Chen, T.: Scalable adaptive computation for iterative generation. arXiv preprint arXiv:2212.11972 (2022)"},{"issue":"1","key":"27_CR21","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79\u201387 (1991)","journal-title":"Neural Comput."},{"key":"27_CR22","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":"27_CR23","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Laine, S., Lehtinen, J., Aila, T.: Improved precision and recall metric for assessing generative models. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"27_CR24","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":"27_CR25","unstructured":"Lepikhin, D., et al.: Gshard: scaling giant models with conditional computation and automatic sharding. arXiv preprint arXiv:2006.16668 (2020)"},{"key":"27_CR26","unstructured":"Lewis, M., Bhosale, S., Dettmers, T., Goyal, N., Zettlemoyer, L.: Base layers: simplifying training of large, sparse models. In: International Conference on Machine Learning, pp. 6265\u20136274. PMLR (2021)"},{"key":"27_CR27","unstructured":"Liu, Y., et al.: Syncdreamer: generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)"},{"key":"27_CR28","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"27_CR29","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"27_CR30","unstructured":"Park, B., Woo, S., Go, H., Kim, J.Y., Kim, C.: Denoising task routing for diffusion models. arXiv preprint arXiv:2310.07138 (2023)"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. arXiv preprint arXiv:2212.09748 (2022)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"27_CR32","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"27_CR33","first-page":"8583","volume":"34","author":"C Riquelme","year":"2021","unstructured":"Riquelme, C., et al.: Scaling vision with sparse mixture of experts. Adv. Neural. Inf. Process. Syst. 34, 8583\u20138595 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR34","first-page":"17555","volume":"34","author":"S Roller","year":"2021","unstructured":"Roller, S., Sukhbaatar, S., Weston, J., et al.: Hash layers for large sparse models. Adv. Neural. Inf. Process. Syst. 34, 17555\u201317566 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR35","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":"27_CR36","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. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"27_CR37","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"27_CR38","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)"},{"key":"27_CR39","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, B., Go, H., Kim, J.Y., Kim, C.: Harmonyview: harmonizing consistency and diversity in one-image-to-3d. arXiv preprint arXiv:2312.15980 (2023)","DOI":"10.1109\/CVPR52733.2024.01006"},{"key":"27_CR41","unstructured":"Wu, L., Liu, M., Chen, Y., Chen, D., Dai, X., Yuan, L.: Residual mixture of experts. arXiv preprint arXiv:2204.09636 (2022)"},{"key":"27_CR42","unstructured":"Xue, Z., et al.: Raphael: text-to-image generation via large mixture of diffusion paths. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"27_CR43","unstructured":"Yang, X., Shih, S.M., Fu, Y., Zhao, X., Ji, S.: Your vit is secretly a hybrid discriminative-generative diffusion model. arXiv preprint arXiv:2208.07791 (2022)"},{"key":"27_CR44","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":"27_CR45","first-page":"7103","volume":"35","author":"Y Zhou","year":"2022","unstructured":"Zhou, Y., et al.: Mixture-of-experts with expert choice routing. Adv. Neural. Inf. Process. Syst. 35, 7103\u20137114 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR46","unstructured":"Zoph, B., et al.: St-moe: designing stable and transferable sparse expert models. arXiv preprint arXiv:2202.08906 (2022)"}],"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\/978-3-031-73668-1_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:13:53Z","timestamp":1733019233000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73668-1_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"ISBN":["9783031736674","9783031736681"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73668-1_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,1]]},"assertion":[{"value":"1 December 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"}}]}}