{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:16:21Z","timestamp":1791303381247,"version":"4.1.0"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031731129","type":"print"},{"value":"9783031731136","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-73113-6_24","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T08:48:51Z","timestamp":1732092531000},"page":"414-430","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Self-Guided Generation of\u00a0Minority Samples Using Diffusion Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1133-0027","authenticated-orcid":false,"given":"Soobin","family":"Um","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9763-9609","authenticated-orcid":false,"given":"Jong Chul","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Amini, A., Soleimany, A.P., Schwarting, W., Bhatia, S.N., Rus, D.: Uncovering and mitigating algorithmic bias through learned latent structure. In: Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society, pp. 289\u2013295 (2019)","DOI":"10.1145\/3306618.3314243"},{"key":"24_CR2","unstructured":"Arvinte, M., Cornelius, C., Martin, J., Himayat, N.: Investigating the adversarial robustness of density estimation using the probability flow ODE. arXiv preprint arXiv:2310.07084 (2023)"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Breunig, M.M., Kriegel, H.P., Ng, R.T., Sander, J.: LOF: identifying density-based local outliers. In: Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, pp. 93\u2013104 (2000)","DOI":"10.1145\/342009.335388"},{"key":"24_CR4","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"24_CR6","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":"24_CR7","unstructured":"Chung, H., Kim, J., Mccann, M.T., Klasky, M.L., Ye, J.C.: Diffusion posterior sampling for general noisy inverse problems. arXiv preprint arXiv:2209.14687 (2022)"},{"key":"24_CR8","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":"24_CR9","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":"24_CR10","unstructured":"Du, X., Sun, Y., Zhu, X., Li, Y.: Dream the impossible: outlier imagination with diffusion models. In: Advances in Neural Information Processing Systems (2023)"},{"key":"24_CR11","unstructured":"Du, X., Wang, Z., Cai, M., Li, Y.: Vos: Learning what you don\u2019t know by virtual outlier synthesis. arXiv preprint arXiv:2202.01197 (2022)"},{"key":"24_CR12","unstructured":"Epstein, D., Jabri, A., Poole, B., Efros, A.A., Holynski, A.: Diffusion self-guidance for controllable image generation. arXiv preprint arXiv:2306.00986 (2023)"},{"key":"24_CR13","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"24_CR14","first-page":"4218","volume":"34","author":"S Gowal","year":"2021","unstructured":"Gowal, S., Rebuffi, S.A., Wiles, O., Stimberg, F., Calian, D.A., Mann, T.A.: Improving robustness using generated data. Adv. Neural. Inf. Process. Syst. 34, 4218\u20134233 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR15","unstructured":"Han, J., Choi, H., Choi, Y., Kim, J., Ha, J.W., Choi, J.: Rarity score: a new metric to evaluate the uncommonness of synthesized images. arXiv preprint arXiv:2206.08549 (2022)"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15262\u201315271 (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"24_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":"24_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":"24_CR19","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Hong, S., Lee, G., Jang, W., Kim, S.: Improving sample quality of diffusion models using self-attention guidance. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7462\u20137471 (2023)","DOI":"10.1109\/ICCV51070.2023.00686"},{"issue":"7","key":"24_CR21","doi-asserted-by":"publisher","first-page":"5145","DOI":"10.1007\/s00521-021-06163-8","volume":"35","author":"G Huang","year":"2023","unstructured":"Huang, G., Jafari, A.H.: Enhanced balancing GAN: minority-class image generation. Neural Comput. Appl. 35(7), 5145\u20135154 (2023)","journal-title":"Neural Comput. Appl."},{"key":"24_CR22","first-page":"26565","volume":"35","author":"T Karras","year":"2022","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. Adv. Neural. Inf. Process. Syst. 35, 26565\u201326577 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR23","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":"24_CR24","unstructured":"Kim, D., Shin, S., Song, K., Kang, W., Moon, I.C.: Soft truncation: a universal training technique of score-based diffusion model for high precision score estimation. arXiv preprint arXiv:2106.05527 (2021)"},{"key":"24_CR25","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":"24_CR26","doi-asserted-by":"crossref","unstructured":"Lin, Z., et\u00a0al.: RareGAN: generating samples for rare classes. arXiv preprint arXiv:2203.10674 (2022)","DOI":"10.1609\/aaai.v36i7.20715"},{"key":"24_CR27","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":"24_CR28","unstructured":"Nash, C., Menick, J., Dieleman, S., Battaglia, P.W.: Generating images with sparse representations. arXiv preprint arXiv:2103.03841 (2021)"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Parmar, G., Zhang, R., Zhu, J.Y.: On aliased resizing and surprising subtleties in GAN evaluation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11410\u201311420 (2022)","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"24_CR30","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":"24_CR31","doi-asserted-by":"crossref","unstructured":"Qin, Y., Zheng, H., Yao, J., Zhou, M., Zhang, Y.: Class-balancing diffusion models. arXiv preprint arXiv:2305.00562 (2023)","DOI":"10.1109\/CVPR52729.2023.01768"},{"key":"24_CR32","unstructured":"Ravuri, S., Vinyals, O.: Classification accuracy score for conditional generative models. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"24_CR33","doi-asserted-by":"publisher","unstructured":"Robbins, H.E.: An empirical Bayes approach to statistics. In: Kotz, S., Johnson, N.L. (eds.) Breakthroughs in Statistics. Springer Series in Statistics. Springer, New York, NY (1992). https:\/\/doi.org\/10.1007\/978-1-4612-0919-5_26","DOI":"10.1007\/978-1-4612-0919-5_26"},{"key":"24_CR34","unstructured":"Roh, Y., Nie, W., Huang, D.A., Whang, S.E., Vahdat, A., Anandkumar, A.: Dr-Fairness: dynamic data ratio adjustment for fair training on real and generated data. Trans. Mach. Learn. Res. (2023)"},{"key":"24_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":"24_CR36","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":"24_CR37","unstructured":"Samuel, D., Ben-Ari, R., Raviv, S., Darshan, N., Chechik, G.: It is all about where you start: text-to-image generation with seed selection. arXiv preprint arXiv:2304.14530 (2023)"},{"key":"24_CR38","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":"24_CR39","unstructured":"Serr\u00e0, J., \u00c1lvarez, D., G\u00f3mez, V., Slizovskaia, O., N\u00fa\u00f1ez, J.F., Luque, J.: Input complexity and out-of-distribution detection with likelihood-based generative models. arXiv preprint arXiv:1909.11480 (2019)"},{"key":"24_CR40","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":"24_CR41","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"24_CR42","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":"24_CR43","unstructured":"Um, S., Ye, J.C.: Don\u2019t play favorites: minority guidance for diffusion models. arXiv preprint arXiv:2301.12334 (2023)"},{"issue":"7","key":"24_CR44","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1162\/NECO_a_00142","volume":"23","author":"P Vincent","year":"2011","unstructured":"Vincent, P.: A connection between score matching and denoising autoencoders. Neural Comput. 23(7), 1661\u20131674 (2011)","journal-title":"Neural Comput."},{"key":"24_CR45","unstructured":"Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., 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":"24_CR46","doi-asserted-by":"publisher","unstructured":"Yu, N., Li, K., Zhou, P., Malik, J., Davis, L., Fritz, M.: Inclusive GAN: improving data and minority coverage in generative models. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) Computer Vision \u2013 ECCV 2020. ECCV 2020. LNCS, vol. 12367. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_23","DOI":"10.1007\/978-3-030-58542-6_23"},{"key":"24_CR47","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"24_CR48","unstructured":"Zhao, B., Bilen, H.: Synthesizing informative training samples with GAN. arXiv preprint arXiv:2204.07513 (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\/978-3-031-73113-6_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T10:14:44Z","timestamp":1732097684000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73113-6_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031731129","9783031731136"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73113-6_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 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"}}]}}