{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:10:37Z","timestamp":1765357837219,"version":"3.44.0"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031851803"},{"type":"electronic","value":"9783031851810"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-85181-0_10","type":"book-chapter","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T06:58:29Z","timestamp":1745305109000},"page":"148-163","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DIAGen: Semantically Diverse Image Augmentation with\u00a0Generative Models for\u00a0Few-Shot Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7061-9210","authenticated-orcid":false,"given":"Tobias","family":"Lingenberg","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2179-4901","authenticated-orcid":false,"given":"Markus","family":"Reuter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3721-5602","authenticated-orcid":false,"given":"Gopika","family":"Sudhakaran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1965-8286","authenticated-orcid":false,"given":"Dominik","family":"Gojny","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9002-9832","authenticated-orcid":false,"given":"Stefan","family":"Roth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8644-1074","authenticated-orcid":false,"given":"Simone","family":"Schaub-Meyer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,23]]},"reference":[{"key":"10_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 Technical report. arXiv:2303.08774 [cs.CL] (2023)"},{"key":"10_CR2","unstructured":"Alaa, A., Van\u00a0Breugel, B., Saveliev, E.S., van\u00a0der Schaar, M.: How faithful is your synthetic data? sample-level metrics for evaluating and auditing generative models. In: ICML, pp. 290\u2013306 (2022)"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Antoniou, A., Storkey, A., Edwards, H.: Data augmentation generative adversarial networks. arXiv:1711.04340 [stat.ML] (2017)","DOI":"10.1007\/978-3-030-01424-7_58"},{"key":"10_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-030-01270-0_28","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Beery","year":"2018","unstructured":"Beery, S., Van Horn, G., Perona, P.: Recognition in terra incognita. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 472\u2013489. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_28"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Besnier, V., Jain, H., Bursuc, A., Cord, M., P\u00e9rez, P.: This dataset does not exist: training models from generated images. In: ICASSP, pp.\u00a01\u20135 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053146"},{"key":"10_CR6","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. NeurIPS 34, 8780\u20138794 (2021)","journal-title":"NeurIPS"},{"key":"10_CR7","unstructured":"Friedman, D., Dieng, A.B.: The vendi score: a diversity evaluation metric for machine learning. TMLR (2023)"},{"key":"10_CR8","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: ICLR (2023)"},{"key":"10_CR9","unstructured":"Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: ICML, pp. 1321\u20131330 (2017)"},{"key":"10_CR10","unstructured":"He, R., et al.: Is synthetic data from generative models ready for image recognition? In: ICLR (2023)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Henriksson, J., Berger, C., Ursing, S.: Understanding the impact of edge cases from occluded pedestrians for ML systems. In: SEAA, pp. 316\u2013325 (2021)","DOI":"10.1109\/SEAA53835.2021.00048"},{"key":"10_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. NeurIPS 30 (2017)"},{"key":"10_CR13","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. NeurIPS 33, 6840\u20136851 (2020)","journal-title":"NeurIPS"},{"issue":"47","key":"10_CR14","first-page":"1","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. JMLR 23(47), 1\u201333 (2022)","journal-title":"JMLR"},{"key":"10_CR15","unstructured":"Jahanian, A., Puig, X., Tian, Y., Isola, P.: Generative models as a data source for multiview representation learning. In: ICLR (2022)"},{"issue":"1","key":"10_CR16","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1109\/TPAMI.2022.3153611","volume":"45","author":"S Jiang","year":"2022","unstructured":"Jiang, S., Zhu, Y., Liu, C., Song, X., Li, X., Min, W.: Dataset bias in few-shot image recognition. TPAMI 45(1), 229\u2013246 (2022)","journal-title":"TPAMI"},{"key":"10_CR17","unstructured":"Kattakinda, P., Feizi, S.: Focus: familiar objects in common and uncommon settings. In: ICML, pp. 10825\u201310847 (2022)"},{"key":"10_CR18","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Laine, S., Lehtinen, J., Aila, T.: Improved precision and recall metric for assessing generative models. NeurIPS 32 (2019)"},{"key":"10_CR19","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":"10_CR20","unstructured":"Liu, J., et al.: Towards out-of-distribution generalization: A survey. arXiv:2108.13624 [cs.LG] (2021)"},{"issue":"11","key":"10_CR21","doi-asserted-by":"publisher","first-page":"310","DOI":"10.3390\/jimaging8110310","volume":"8","author":"K Man","year":"2022","unstructured":"Man, K., Chahl, J.: A review of synthetic image data and its use in computer vision. J. Imaging 8(11), 310 (2022)","journal-title":"J. Imaging"},{"key":"10_CR22","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: ICLR (2022)"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Miko\u0142ajczyk, A., Grochowski, M.: Data augmentation for improving deep learning in image classification problem. In: IIPhDW, pp. 117\u2013122 (2018)","DOI":"10.1109\/IIPHDW.2018.8388338"},{"key":"10_CR24","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. NeurIPS 26 (2013)"},{"key":"10_CR25","unstructured":"Murphy, K.P.: Probabilistic machine learning: Advanced topics. MIT press (2023)"},{"key":"10_CR26","unstructured":"Naeem, M.F., Oh, S.J., Uh, Y., Choi, Y., Yoo, J.: Reliable fidelity and diversity metrics for generative models. In: ICML, pp. 7176\u20137185 (2020)"},{"key":"10_CR27","unstructured":"Nagarajan, V., Andreassen, A., Neyshabur, B.: Understanding the failure modes of out-of-distribution generalization. In: ICLR (2021)"},{"key":"10_CR28","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: ICML, pp. 8162\u20138171 (2021)"},{"key":"10_CR29","unstructured":"Perez, L., Wang, J.: The effectiveness of data augmentation in image classification using deep learning. arXiv:1712.04621 [cs.CV] (2017)"},{"key":"10_CR30","unstructured":"Ravuri, S., Vinyals, O.: Classification accuracy score for conditional generative models. NeurIPS 32 (2019)"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Rebbapragada, U., Brodley, C.E.: Class noise mitigation through instance weighting. In: ECML, pp. 708\u2013715 (2007)","DOI":"10.1007\/978-3-540-74958-5_71"},{"key":"10_CR32","unstructured":"Ren, J., et al.: Out-of-distribution detection and selective generation for conditional language models. In: ICLR (2023)"},{"key":"10_CR33","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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: Image-to-image diffusion models. In: ACM SIGGRAPH, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"10_CR35","unstructured":"Sajjadi, M.S., Bachem, O., Lucic, M., Bousquet, O., Gelly, S.: Assessing generative models via precision and recall. NeurIPS 31 (2018)"},{"key":"10_CR36","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. NeurIPS 29 (2016)"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Shijie, J., Ping, W., Peiyi, J., Siping, H.: Research on data augmentation for image classification based on convolution neural networks. In: CAC, pp. 4165\u20134170 (2017)","DOI":"10.1109\/CAC.2017.8243510"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Singh, K., Navaratnam, T., Holmer, J., Schaub-Meyer, S., Roth, S.: Is synthetic data all we need? benchmarking the robustness of models trained with synthetic images. In: CVPR Workshops (2024)","DOI":"10.1109\/CVPRW63382.2024.00257"},{"key":"10_CR39","unstructured":"Stein, G., et al.: Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models. NeurIPS 36 (2024)"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Sudhakaran, G., Dhami, D.S., Kersting, K., Roth, S.: Vision relation transformer for unbiased scene graph generation. In: ICCV, pp. 21882\u201321893 (2023)","DOI":"10.1109\/ICCV51070.2023.02000"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Sushko, V., Sch\u00f6nfeld, E., Zhang, D., Gall, J., Schiele, B., Khoreva, A.: Oasis: only adversarial supervision for semantic image synthesis. Inter. J. Comput. Vis. 2903\u20132923 (2022)","DOI":"10.1007\/s11263-022-01673-x"},{"key":"10_CR42","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR, pp.\u00a01\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., Zhang, H.: Unbiased scene graph generation from biased training. In: CVPR, pp. 3716\u20133725 (2020)","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"10_CR44","doi-asserted-by":"crossref","unstructured":"Tong, J., Dai, L.: Out-of-distribution with text-to-image diffusion models. In: PRCV, pp. 276\u2013288 (2023)","DOI":"10.1007\/978-981-99-8552-4_22"},{"key":"10_CR45","unstructured":"Touvron, H., et\u00a0al.: Llama: Open and efficient foundation language models. arXiv2302.13971[cs.CL] (2023)"},{"key":"10_CR46","unstructured":"Trabucco, B., Doherty, K., Gurinas, M., Salakhutdinov, R.: Effective data augmentation with diffusion models. In: ICLR Workshop: Mathematical and Empirical Understanding of Foundation Models (2024)"},{"key":"10_CR47","unstructured":"Wang, J., et\u00a0al.: On the robustness of ChatGPT: an adversarial and out-of-distribution perspective. In: ICLR Workshop: Trustworthy and Reliable Large-Scale Machine Learning Models (2023)"},{"key":"10_CR48","doi-asserted-by":"crossref","unstructured":"Wang, L., Zhang, S., Han, Z., Feng, Y., Wei, J., Mei, S.: Diversity measurement-based meta-learning for few-shot object detection of remote sensing images. In: IGARSS, pp. 3087\u20133090 (2022)","DOI":"10.1109\/IGARSS46834.2022.9884721"},{"key":"10_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/978-3-030-32239-7_43","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"Y Xue","year":"2019","unstructured":"Xue, Y., et al.: Synthetic augmentation and feature-based filtering for improved cervical histopathology image classification. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11764, pp. 387\u2013396. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32239-7_43"},{"key":"10_CR50","unstructured":"Yang, J., Zhou, K., Li, Y., Liu, Z.: Generalized out-of-distribution detection: A survey. arXiv:2110.11334 [cs.CV] (2021)"},{"key":"10_CR51","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: Out-of-distribution generalization in text classification: past, present, and future. arXiv:2305.14104 [cs.CL] (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.276"},{"key":"10_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: DatasetGAN: efficient labeled data factory with minimal human effort. In: CVPR, pp. 10145\u201310155 (2021)","DOI":"10.1109\/CVPR46437.2021.01001"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-85181-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T13:14:45Z","timestamp":1758633285000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-85181-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031851803","9783031851810"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-85181-0_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"23 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}