{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T21:59:16Z","timestamp":1778536756137,"version":"3.51.4"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732089","type":"print"},{"value":"9783031732096","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73209-6_15","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:02:57Z","timestamp":1730386977000},"page":"252-268","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["DataDream: Few-Shot Guided Dataset Generation"],"prefix":"10.1007","author":[{"given":"Jae Myung","family":"Kim","sequence":"first","affiliation":[]},{"given":"Jessica","family":"Bader","sequence":"additional","affiliation":[]},{"given":"Stephan","family":"Alaniz","sequence":"additional","affiliation":[]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[]},{"given":"Zeynep","family":"Akata","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"15_CR1","unstructured":"Alemohammad, S., et al.: Self-consuming generative models go mad. In: ICLR (2023)"},{"key":"15_CR2","unstructured":"Azizi, S., Kornblith, S., Saharia, C., Norouzi, M., Fleet, D.J.: Synthetic data from diffusion models improves imagenet classification. arXiv preprint arXiv:2304.08466 (2023)"},{"key":"15_CR3","unstructured":"Bansal, H., Grover, A.: Leaving reality to imagination: robust classification via generated datasets. arXiv preprint arXiv:2302.02503 (2023)"},{"key":"15_CR4","unstructured":"Betker, J., et\u00a0al.: Improving image generation with better captions. Comput. Sci. 2(3), 8 (2023). https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf"},{"key":"15_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29"},{"key":"15_CR6","unstructured":"Burg, M.F., et al.: Image retrieval outperforms diffusion models on data augmentation. In: TMLR (2023)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Choi, J., Kim, S., Jeong, Y., Gwon, Y., Yoon, S.: ILVR: conditioning method for denoising diffusion probabilistic models. arXiv preprint arXiv:2108.02938 (2021)","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., , Vedaldi, A.: Describing textures in the wild. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"15_CR9","unstructured":"da\u00a0Costa, V.G.T., Dall\u2019Asen, N., Wang, Y., Sebe, N., Ricci, E.: Diversified in-domain synthesis with efficient fine-tuning for few-shot classification (2023)"},{"key":"15_CR10","unstructured":"Dunlap, L., Umino, A., Zhang, H., Yang, J., Gonzalez, J.E., Darrell, T.: Diversify your vision datasets with automatic diffusion-based augmentation (2023)"},{"key":"15_CR11","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: ICLR (2022)"},{"key":"15_CR12","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"15_CR13","unstructured":"Hammoud, H.A.A.K., Itani, H., Pizzati, F., Torr, P., Bibi, A., Ghanem, B.: Synthclip: are we ready for a fully synthetic clip training? arXiv preprint arXiv:2402.01832 (2024)"},{"key":"15_CR14","unstructured":"He, R., et al.: Is synthetic data from generative models ready for image recognition? In: ICLR (2023)"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Helber, P., Bischke, B., Dengel, A., Borth, D.: EuroSAT: a novel dataset and deep learning benchmark for land use and land cover classification. In: AEROS (2019)","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"15_CR16","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. In: Advances in neural Information Processing Systems, vol. 30 (2017)"},{"key":"15_CR17","unstructured":"Hu, E.J., et\u00a0al.: Lora: low-rank adaptation of large language models. In: ICLR (2021)"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Jia, M., et al.: Visual prompt tuning. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"15_CR19","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: ICCV workshop, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"15_CR21","doi-asserted-by":"publisher","unstructured":"Li, F.F., Andreeto, M., Ranzato, M., Perona, P.: Caltech 101, April 2022. https:\/\/doi.org\/10.22002\/D1.20086","DOI":"10.22002\/D1.20086"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Lin, S., Wang, K., Zeng, X., Zhao, R.: Explore the power of synthetic data on few-shot object detection. In: CVPR (2023)","DOI":"10.1109\/CVPRW59228.2023.00071"},{"key":"15_CR23","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: More control for free! image synthesis with semantic diffusion guidance. In: WACV (2023)","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"15_CR25","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2018)"},{"key":"15_CR26","unstructured":"Maji, S., Kannala, J., Rahtu, E., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. Technical Report (2013)"},{"key":"15_CR27","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: Indian Conference on Computer Vision, Graphics and Image Processing, December 2008","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.V.: Cats and dogs. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"15_CR30","unstructured":"Pernias, P., Rampas, D., Richter, M.L., Pal, C., Aubreville, M.: W\u00fcrstchen: an efficient architecture for large-scale text-to-image diffusion models. In: ICLR (2023)"},{"key":"15_CR31","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. In: ICLR (2023)"},{"key":"15_CR32","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"15_CR33","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.061251(2), 3 (2022)"},{"key":"15_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: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"15_CR35","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: CVPR, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"15_CR36","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"15_CR37","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Sariyildiz, M.B., Alahari, K., Larlus, D., Kalantidis, Y.: Fake it till you make it: learning transferable representations from synthetic imagenet clones. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00774"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Shipard, J., Wiliem, A., Thanh, K.N., Xiang, W., Fookes, C.: Diversity is definitely needed: Improving model-agnostic zero-shot classification via stable diffusion (2023)","DOI":"10.1109\/CVPRW59228.2023.00084"},{"key":"15_CR40","unstructured":"Tian, Y., Fan, L., Isola, P., Chang, H., Krishnan, D.: Stablerep: synthetic images from text-to-image models make strong visual representation learners. In: NeurIPS (2024)"},{"key":"15_CR41","unstructured":"Wang, Z., Liang, J., Sheng, L., He, R., Wang, Z., Tan, T.: A hard-to-beat baseline for training-free CLIP-based adaptation. In: ICLR (2024)"},{"key":"15_CR42","doi-asserted-by":"crossref","unstructured":"Wortsman, M., et\u00a0al.: Robust fine-tuning of zero-shot models. In: CVPR, pp. 7959\u20137971 (2022)","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: CVPR, pp. 3485\u20133492. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"15_CR44","unstructured":"Yu, Z., Zhu, C., Culatana, S., Krishnamoorthi, R., Xiao, F., Lee, Y.J.: Diversify, don\u2019t fine-tune: Scaling up visual recognition training with synthetic images. arXiv preprint arXiv:2312.02253 (2023)"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"15_CR46","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: ICLR (2018)"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. In: IJCV (2022)","DOI":"10.1007\/s11263-022-01653-1"},{"key":"15_CR48","unstructured":"Zhou, Y., Sahak, H., Ba, J.: Training on thin air: improve image classification with generated data. arXiv preprint arXiv:2305.15316 (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\/978-3-031-73209-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T12:20:56Z","timestamp":1744114856000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73209-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732089","9783031732096"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73209-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}