{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T17:42:14Z","timestamp":1782322934661,"version":"3.54.5"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729850","type":"print"},{"value":"9783031729867","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:00:00Z","timestamp":1730505600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:00:00Z","timestamp":1730505600000},"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\/978-3-031-72986-7_5","type":"book-chapter","created":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T05:06:23Z","timestamp":1730437583000},"page":"73-90","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["AdaDiff: Accelerating Diffusion Models Through Step-Wise Adaptive Computation"],"prefix":"10.1007","author":[{"given":"Shengkun","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1548-0727","authenticated-orcid":false,"given":"Yaqing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0891-1231","authenticated-orcid":false,"given":"Caiwen","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7195-5774","authenticated-orcid":false,"given":"Yao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1456-9658","authenticated-orcid":false,"given":"Dongkuan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,2]]},"reference":[{"key":"5_CR1","first-page":"17981","volume":"34","author":"J Austin","year":"2021","unstructured":"Austin, J., Johnson, D.D., Ho, J., Tarlow, D., van den Berg, R.: Structured denoising diffusion models in discrete state-spaces. Adv. Neural. Inf. Process. Syst. 34, 17981\u201317993 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR2","unstructured":"Balaji, Y., et\u00a0al.: ediffi: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Bao, F., Li, C., Cao, Y., Zhu, J.: All are worth words: a vit backbone for score-based diffusion models. arXiv preprint arXiv:2209.12152 (2022)","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"5_CR4","unstructured":"Bao, F., Li, C., Zhu, J., Zhang, B.: Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models. arXiv preprint arXiv:2201.06503 (2022)"},{"key":"5_CR5","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale gan training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: attention-based semantic guidance for text-to-image diffusion models. arXiv preprint arXiv:2301.13826 (2023)","DOI":"10.1145\/3592116"},{"key":"5_CR7","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":"5_CR8","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."},{"key":"5_CR9","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"5_CR10","unstructured":"Fang, G., Ma, X., Wang, X.: Structural pruning for diffusion models. arXiv preprint arXiv:2305.10924 (2023)"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Hang, T., et al.: Efficient diffusion training via min-snr weighting strategy. arXiv preprint arXiv:2303.09556 (2023)","DOI":"10.1109\/ICCV51070.2023.00684"},{"key":"5_CR12","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":"5_CR13","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. arXiv preprint arXiv:2204.03458 (2022)"},{"key":"5_CR14","unstructured":"Jolicoeur-Martineau, A., Li, K., Pich\u00e9-Taillefer, R., Kachman, T., Mitliagkas, I.: Gotta go fast when generating data with score-based models. arXiv preprint arXiv:2105.14080 (2021)"},{"key":"5_CR15","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. arXiv preprint arXiv:2206.00364 (2022)"},{"key":"5_CR16","unstructured":"Kim, D., Shin, S., Song, K., Kang, W., Moon, I.C.: Soft ltraining technique of score-based diffusion model for high precision score estimation. arXiv preprint arXiv:2106.05527 (2021)"},{"key":"5_CR17","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Li, M., Lin, J., Meng, C., Ermon, S., Han, S., Zhu, J.Y.: Efficient spatially sparse inference for conditional gans and diffusion models. arXiv preprint arXiv:2211.02048 (2022)","DOI":"10.1109\/TPAMI.2023.3316020"},{"key":"5_CR19","first-page":"4328","volume":"35","author":"X Li","year":"2022","unstructured":"Li, X., Thickstun, J., Gulrajani, I., Liang, P.S., Hashimoto, T.B.: Diffusion-lm improves controllable text generation. Adv. Neural. Inf. Process. Syst. 35, 4328\u20134343 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Q-diffusion: quantizing diffusion models. arXiv preprint arXiv:2302.04304 (2023)","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"5_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"5_CR23","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"5_CR24","unstructured":"Lu, C., Zheng, K., Bao, F., Chen, J., Li, C., Zhu, J.: Maximum likelihood training for score-based diffusion odes by high order denoising score matching. In: International Conference on Machine Learning, pp. 14429\u201314460. PMLR (2022)"},{"key":"5_CR25","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. arXiv preprint arXiv:2206.00927 (2022)"},{"key":"5_CR26","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: Dpm-solver++: fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095 (2022)"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: Repaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"5_CR28","unstructured":"Luhman, E., Luhman, T.: Knowledge distillation in iterative generative models for improved sampling speed. arXiv preprint arXiv:2101.02388 (2021)"},{"key":"5_CR29","unstructured":"Lyu, Z., Xu, X., Yang, C., Lin, D., Dai, B.: Accelerating diffusion models via early stop of the diffusion process. arXiv preprint arXiv:2205.12524 (2022)"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Meng, C., Gao, R., Kingma, D.P., Ermon, S., Ho, J., Salimans, T.: On distillation of guided diffusion models. arXiv preprint arXiv:2210.03142 (2022)","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"5_CR31","unstructured":"Moon, T., Choi, M., Yun, E., Yoon, J., Lee, G., Lee, J.: Early exiting for accelerated inference in diffusion models. In: ICML 2023 Workshop on Structured Probabilistic Inference $$\\{$$$$\\backslash $$ &$$\\}$$ Generative Modeling (2023)"},{"key":"5_CR32","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":"5_CR33","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"5_CR34","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":"5_CR35","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":"5_CR36","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR37","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. arXiv preprint arXiv:2202.00512 (2022)"},{"key":"5_CR38","unstructured":"San-Roman, R., Nachmani, E., Wolf, L.: Noise estimation for generative diffusion models. arXiv preprint arXiv:2104.02600 (2021)"},{"key":"5_CR39","first-page":"17456","volume":"35","author":"T Schuster","year":"2022","unstructured":"Schuster, T., et al.: Confident adaptive language modeling. Adv. Neural. Inf. Process. Syst. 35, 17456\u201317472 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Sehwag, V., Hazirbas, C., Gordo, A., Ozgenel, F., Canton, C.: Generating high fidelity data from low-density regions using diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11492\u201311501 (2022)","DOI":"10.1109\/CVPR52688.2022.01120"},{"key":"5_CR41","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"5_CR42","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. Adv. Neural Inf. Processi. Syst. 32 (2019)"},{"key":"5_CR43","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Tang, S., et al.: You need multiple exiting: dynamic early exiting for accelerating unified vision language model. arXiv preprint arXiv:2211.11152 (2022)","DOI":"10.1109\/CVPR52729.2023.01038"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Teerapittayanon, S., McDanel, B., Kung, H.T.: Branchynet: fast inference via early exiting from deep neural networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 2464\u20132469. IEEE (2016)","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"5_CR46","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)"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Xin, J., Tang, R., Lee, J., Yu, Y., Lin, J.: Deebert: dynamic early exiting for accelerating bert inference. arXiv preprint arXiv:2004.12993 (2020)","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"5_CR48","doi-asserted-by":"crossref","unstructured":"Xin, J., Tang, R., Yu, Y., Lin, J.: Berxit: early exiting for bert with better fine-tuning and extension to regression. In: Proceedings of the 16th conference of the European chapter of the association for computational linguistics: Main Volume, pp. 91\u2013104 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.8"},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: Attngan: fine-grained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1316\u20131324 (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"5_CR50","unstructured":"Zhou, Y., et al.: Lafite: towards language-free training for text-to-image generation. arXiv preprint arXiv:2111.13792 (2021)"},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, M., Pan, P., Chen, W., Yang, Y.: Dm-gan: dynamic memory generative adversarial networks for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5802\u20135810 (2019)","DOI":"10.1109\/CVPR.2019.00595"}],"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\/978-3-031-72986-7_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T05:07:01Z","timestamp":1730437621000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72986-7_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,2]]},"ISBN":["9783031729850","9783031729867"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72986-7_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,2]]},"assertion":[{"value":"2 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"}}]}}