{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:07:30Z","timestamp":1742940450950,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819784868"},{"type":"electronic","value":"9789819784875"}],"license":[{"start":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T00:00:00Z","timestamp":1730678400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T00:00:00Z","timestamp":1730678400000},"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\/978-981-97-8487-5_16","type":"book-chapter","created":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T07:02:39Z","timestamp":1730617359000},"page":"222-235","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multistage Compression Optimization Strategies for Accelerating Diffusion Models"],"prefix":"10.1007","author":[{"given":"Weiquan","family":"Huang","sequence":"first","affiliation":[]},{"given":"Qiang","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,4]]},"reference":[{"key":"16_CR1","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":"16_CR2","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents (2022). arXiv:2204.061251(2), 3"},{"issue":"11","key":"16_CR3","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"16_CR4","first-page":"23593","volume":"35","author":"B Kawar","year":"2022","unstructured":"Kawar, B., Elad, M., Ermon, S., Song, J.: Denoising diffusion restoration models. Adv. Neural. Inf. Process. Syst. 35, 23593\u201323606 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"16_CR5","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":"16_CR6","unstructured":"Popov, V., Vovk, I., Gogoryan, V., Sadekova, T., Kudinov, M.: Grad-tts: a diffusion probabilistic model for text-to-speech. In: International Conference on Machine Learning, pp. 8599\u20138608. PMLR (2021)"},{"key":"16_CR7","unstructured":"Ho, J., Chan, W., Saharia, C., Whang, J., Gao, R., Gritsenko, A., Kingma, D.P., Poole, B., Norouzi, M., Fleet, D.J., et\u00a0al.: Imagen video: high definition video generation with diffusion models (2022). arXiv:2210.02303"},{"key":"16_CR8","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale (2020). arXiv:2010.11929"},{"key":"16_CR9","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Kong, Z., Dong, P., Ma, X., Meng, X., Niu, W., Sun, M., Shen, X., Yuan, G., Ren, B., Tang, H., et\u00a0al.: Spvit: Enabling faster vision transformers via latency-aware soft token pruning. In: European Conference on Computer Vision, pp. 620\u2013640. Springer (2022)","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"16_CR11","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your vit but faster (2022). arXiv:2210.09461"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Meng, C., Rombach, R., Gao, R., Kingma, D., Ermon, S., Ho, J., Salimans, T.: 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":"16_CR13","unstructured":"Fang, G., Ma, X., Wang, X.: Structural pruning for diffusion models. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"16_CR14","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"},{"issue":"4","key":"16_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3626235","volume":"56","author":"L Yang","year":"2023","unstructured":"Yang, L., Zhang, Z., Song, Y., Hong, S., Xu, R., Zhao, Y., Zhang, W., Cui, B., Yang, M.H.: Diffusion models: a comprehensive survey of methods and applications. ACM Comput. Surv. 56(4), 1\u201339 (2023)","journal-title":"ACM Comput. Surv."},{"key":"16_CR16","first-page":"5775","volume":"35","author":"C Lu","year":"2022","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. Adv. Neural. Inf. Process. Syst. 35, 5775\u20135787 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR17","unstructured":"He, Y., Liu, L., Liu, J., Wu, W., Zhou, H., Zhuang, B.: Ptqd: accurate post-training quantization for diffusion models. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Xu, J., De\u00a0Mello, S., Liu, S., Byeon, W., Breuel, T., Kautz, J., Wang, X.: Groupvit: Semantic segmentation emerges from text supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18134\u201318144 (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"16_CR19","first-page":"12786","volume":"34","author":"M Ryoo","year":"2021","unstructured":"Ryoo, M., Piergiovanni, A., Arnab, A., Dehghani, M., Angelova, A.: Tokenlearner: adaptive space-time tokenization for videos. Adv. Neural. Inf. Process. Syst. 34, 12786\u201312797 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Pan, Z., Zhuang, B., He, H., Liu, J., Cai, J.: Less is more: Pay less attention in vision transformers. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2035\u20132043 (2022)","DOI":"10.1609\/aaai.v36i2.20099"},{"key":"16_CR21","unstructured":"Marin, D., Chang, J.H.R., Ranjan, A., Prabhu, A., Rastegari, M., Tuzel, O.: Token pooling in vision transformers (2021). arXiv:2110.03860"},{"key":"16_CR22","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":"16_CR23","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models (2020). arXiv:2010.02502"},{"key":"16_CR24","unstructured":"Lyu, Z., Xu, X., Yang, C., Lin, D., Dai, B.: Accelerating diffusion models via early stop of the diffusion process (2022). arXiv:2205.12524"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Ma, X., Fang, G., Wang, X.: Deepcache: accelerating diffusion models for free (2023). arXiv:2312.00858","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"16_CR26","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., Rombach, R.: Sdxl: improving latent diffusion models for high-resolution image synthesis (2023). arXiv:2307.01952"},{"key":"16_CR27","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. In: The Annual Conference on Neural Information Processing Systems (NeurIPS) (2009)"},{"key":"16_CR28","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":"16_CR29","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"16_CR30","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":"16_CR31","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: Clipscore: a reference-free evaluation metric for image captioning (2021). arXiv:2104.08718","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"16_CR32","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. Adv. Neural Inf. Pocess. Syst. 29 (2016)"},{"key":"16_CR33","unstructured":"Liu, L., Ren, Y., Lin, Z., Zhao, Z.: Pseudo numerical methods for diffusion models on manifolds (2022). arXiv:2202.09778"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8487-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T07:07:29Z","timestamp":1730617649000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8487-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,4]]},"ISBN":["9789819784868","9789819784875"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8487-5_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,4]]},"assertion":[{"value":"4 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}