{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T18:45:25Z","timestamp":1768329925599,"version":"3.49.0"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729065","type":"print"},{"value":"9783031729072","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-72907-2_2","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:22:17Z","timestamp":1730301737000},"page":"20-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Few-Shot Image Generation by\u00a0Conditional Relaxing Diffusion Inversion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9128-1775","authenticated-orcid":false,"given":"Yu","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8156-2299","authenticated-orcid":false,"given":"Shaogang","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Abdal, R., Qin, Y., Wonka, P.: Image2StyleGAN: how to embed images into the StyleGAN latent space? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4432\u20134441 (2019)","DOI":"10.1109\/ICCV.2019.00453"},{"key":"2_CR2","unstructured":"Abdollahzadeh, M., Malekzadeh, T., Teo, C.T., Chandrasegaran, K., Liu, G., Cheung, N.M.: A survey on generative modeling with limited data, few shots, and zero shot. arXiv preprint arXiv:2307.14397 (2023)"},{"issue":"3","key":"2_CR3","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1016\/0304-4149(82)90051-5","volume":"12","author":"BD Anderson","year":"1982","unstructured":"Anderson, B.D.: Reverse-time diffusion equation models. Stochast. Process. Appl. 12(3), 313\u2013326 (1982)","journal-title":"Stochast. Process. Appl."},{"key":"2_CR4","unstructured":"Baranchuk, D., Rubachev, I., Voynov, A., Khrulkov, V., Babenko, A.: Label-efficient semantic segmentation with diffusion models. arXiv preprint arXiv:2112.03126 (2021)"},{"key":"2_CR5","unstructured":"Bartunov, S., Vetrov, D.: Few-shot generative modelling with generative matching networks. In: International Conference on Artificial Intelligence and Statistics, pp. 670\u2013678. PMLR (2018)"},{"key":"2_CR6","unstructured":"Clou\u00e2tre, L., Demers, M.: FIGR: few-shot image generation with reptile. arXiv preprint arXiv:1901.02199 (2019)"},{"key":"2_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":"496","key":"2_CR8","doi-asserted-by":"publisher","first-page":"1602","DOI":"10.1198\/jasa.2011.tm11181","volume":"106","author":"B Efron","year":"2011","unstructured":"Efron, B.: Tweedie\u2019s formula and selection bias. J. Am. Stat. Assoc. 106(496), 1602\u20131614 (2011)","journal-title":"J. Am. Stat. Assoc."},{"key":"2_CR9","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"key":"2_CR10","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Haussmann, U.G., Pardoux, E.: Time reversal of diffusions. Ann. Probab. 1188\u20131205 (1986)","DOI":"10.1214\/aop\/1176992362"},{"key":"2_CR12","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":"2_CR13","unstructured":"Higgins, I., et al.: Beta-VAE: learning basic visual concepts with a constrained variational framework. In: International Conference on Learning Representations (2016)"},{"key":"2_CR14","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":"2_CR15","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Hu, T., et al.: Phasic content fusing diffusion model with directional distribution consistency for few-shot model adaption. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2406\u20132415 (2023)","DOI":"10.1109\/ICCV51070.2023.00228"},{"key":"2_CR17","first-page":"12104","volume":"33","author":"T Karras","year":"2020","unstructured":"Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data. Adv. Neural. Inf. Process. Syst. 33, 12104\u201312114 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR18","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":"2_CR19","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE\/CVF Conference on Computer Vision And Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"2_CR20","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"issue":"13","key":"2_CR21","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521\u20133526 (2017)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"2_CR22","unstructured":"Kong, Z., Ping, W., Huang, J., Zhao, K., Catanzaro, B.: DiffWave: a versatile diffusion model for audio synthesis. arXiv preprint arXiv:2009.09761 (2020)"},{"key":"2_CR23","unstructured":"Kwon, M., Jeong, J., Uh, Y.: Diffusion models already have a semantic latent space. arXiv preprint arXiv:2210.10960 (2022)"},{"key":"2_CR24","unstructured":"Li, C.L., Zaheer, M., Zhang, Y., Poczos, B., Salakhutdinov, R.: Point cloud GAN. arXiv preprint arXiv:1810.05795 (2018)"},{"key":"2_CR25","unstructured":"Li, Y., Zhang, R., Lu, J., Shechtman, E.: Few-shot image generation with elastic weight consolidation. arXiv preprint arXiv:2012.02780 (2020)"},{"key":"2_CR26","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.jmp.2017.05.006","volume":"80","author":"A Ly","year":"2017","unstructured":"Ly, A., Marsman, M., Verhagen, J., Grasman, R.P., Wagenmakers, E.J.: A tutorial on fisher information. J. Math. Psychol. 80, 40\u201355 (2017)","journal-title":"J. Math. Psychol."},{"key":"2_CR27","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"2_CR28","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)"},{"key":"2_CR29","unstructured":"Mo, S., Cho, M., Shin, J.: Freeze the discriminator: a simple baseline for fine-tuning GANs. arXiv preprint arXiv:2002.10964 (2020)"},{"key":"2_CR30","unstructured":"Mondal, A.K., Tiwary, P., Singla, P., Prathosh, A.: Few-shot cross-domain image generation via inference-time latent-code learning. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Noguchi, A., Harada, T.: Image generation from small datasets via batch statistics adaptation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2750\u20132758 (2019)","DOI":"10.1109\/ICCV.2019.00284"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Ojha, U., et al.: Few-shot image generation via cross-domain correspondence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10743\u201310752 (2021)","DOI":"10.1109\/CVPR46437.2021.01060"},{"key":"2_CR33","unstructured":"Oord, A.V.D., et al.: WaveNet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)"},{"key":"2_CR34","unstructured":"Pandey, K., Mukherjee, A., Rai, P., Kumar, A.: DiffuseVAE: efficient, controllable and high-fidelity generation from low-dimensional latents. arXiv preprint arXiv:2201.00308 (2022)"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Preechakul, K., Chatthee, N., Wizadwongsa, S., Suwajanakorn, S.: Diffusion autoencoders: toward a meaningful and decodable representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10619\u201310629 (2022)","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"2_CR36","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"2_CR37","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)"},{"key":"2_CR38","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"2_CR39","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":"2_CR40","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"2_CR41","unstructured":"Sadat, S., Buhmann, J., Bradely, D., Hilliges, O., Weber, R.M.: CADS: unleashing the diversity of diffusion models through condition-annealed sampling. arXiv preprint arXiv:2310.17347 (2023)"},{"key":"2_CR42","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":"2_CR43","doi-asserted-by":"crossref","unstructured":"Saito, M., Matsumoto, E., Saito, S.: Temporal generative adversarial nets with singular value clipping. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2830\u20132839 (2017)","DOI":"10.1109\/ICCV.2017.308"},{"key":"2_CR44","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"2_CR45","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":"2_CR46","unstructured":"Song, Y., Keller, A., Sebe, N., Welling, M.: Flow factorized representation learning. Adv. Neural. Inf. Process. Syst. 36 (2024)"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Stein, C.M.: Estimation of the mean of a multivariate normal distribution. Ann. Stat. 1135\u20131151 (1981)","DOI":"10.1214\/aos\/1176345632"},{"key":"2_CR48","unstructured":"Taigman, Y., Polyak, A., Wolf, L.: Unsupervised cross-domain image generation. arXiv preprint arXiv:1611.02200 (2016)"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Wallace, B., Gokul, A., Naik, N.: EDICT: exact diffusion inversion via coupled transformations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22532\u201322541 (2023)","DOI":"10.1109\/CVPR52729.2023.02158"},{"issue":"11","key":"2_CR50","doi-asserted-by":"publisher","first-page":"1955","DOI":"10.1109\/TPAMI.2008.222","volume":"31","author":"X Wang","year":"2008","unstructured":"Wang, X., Tang, X.: Face photo-sketch synthesis and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(11), 1955\u20131967 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Wang, Y., Gonzalez-Garcia, A., Berga, D., Herranz, L., Khan, F.S., Weijer, J.V.D.: MineGAN: effective knowledge transfer from GANs to target domains with few images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9332\u20139341 (2020)","DOI":"10.1109\/CVPR42600.2020.00935"},{"key":"2_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wu, C., Herranz, L., Van\u00a0de Weijer, J., Gonzalez-Garcia, A., Raducanu, B.: Transferring gans: generating images from limited data. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 218\u2013234 (2018)","DOI":"10.1007\/978-3-030-01231-1_14"},{"issue":"4","key":"2_CR53","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR54","doi-asserted-by":"crossref","unstructured":"Xiang, W., Yang, H., Huang, D., Wang, Y.: Denoising diffusion autoencoders are unified self-supervised learners. arXiv preprint arXiv:2303.09769 (2023)","DOI":"10.1109\/ICCV51070.2023.01448"},{"key":"2_CR55","doi-asserted-by":"crossref","unstructured":"Xiao, J., Li, L., Wang, C., Zha, Z.J., Huang, Q.: Few shot generative model adaption via relaxed spatial structural alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11204\u201311213 (2022)","DOI":"10.1109\/CVPR52688.2022.01092"},{"key":"2_CR56","doi-asserted-by":"crossref","unstructured":"Yang, G., Huang, X., Hao, Z., Liu, M.Y., Belongie, S., Hariharan, B.: PointFlow: 3D point cloud generation with continuous normalizing flows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4541\u20134550 (2019)","DOI":"10.1109\/ICCV.2019.00464"},{"key":"2_CR57","unstructured":"Yang, Y., Wang, R., Qian, Z., Zhu, Y., Wu, Y.: Diffusion in diffusion: cyclic one-way diffusion for text-vision-conditioned generation. arXiv preprint arXiv:2306.08247 (2023)"},{"issue":"4","key":"2_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3322984","volume":"38","author":"J Yaniv","year":"2019","unstructured":"Yaniv, J., Newman, Y., Shamir, A.: The face of art: landmark detection and geometric style in portraits. ACM Trans. Graph. (TOG) 38(4), 1\u201315 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2_CR59","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":"2_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"2_CR61","first-page":"19427","volume":"35","author":"Y Zhao","year":"2022","unstructured":"Zhao, Y., Chandrasegaran, K., Abdollahzadeh, M., Cheung, N.M.M.: Few-shot image generation via adaptation-aware kernel modulation. Adv. Neural. Inf. Process. Syst. 35, 19427\u201319440 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR62","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: Exploring incompatible knowledge transfer in few-shot image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7380\u20137391 (2023)","DOI":"10.1109\/CVPR52729.2023.00713"},{"key":"2_CR63","unstructured":"Zhu, J., Ma, H., Chen, J., Yuan, J.: Few-shot image generation with diffusion models. arXiv preprint arXiv:2211.03264 (2022)"},{"key":"2_CR64","unstructured":"Zhu, Y., Wu, Y., Deng, Z., Russakovsky, O., Yan, Y.: Boundary guided mixing trajectory for semantic control with diffusion models. arXiv preprint arXiv:2302.08357 (2023)"}],"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\/978-3-031-72907-2_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:23:26Z","timestamp":1730301806000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72907-2_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031729065","9783031729072"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72907-2_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 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"}}]}}