{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T05:31:33Z","timestamp":1782970293900,"version":"3.54.5"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T00:00:00Z","timestamp":1750636800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T00:00:00Z","timestamp":1750636800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306046"],"award-info":[{"award-number":["62306046"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s11263-025-02436-0","type":"journal-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T10:26:01Z","timestamp":1750674361000},"page":"5435-5454","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Image Captions are Natural Prompts for Training Data Synthesis"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7810-9346","authenticated-orcid":false,"given":"Shiye","family":"Lei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,23]]},"reference":[{"key":"2436_CR1","unstructured":"Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. In: International conference on machine learning, pp. 214\u2013223. PMLR"},{"key":"2436_CR2","unstructured":"Azizi, S., Kornblith, S., Saharia, C., Norouzi, M., & Fleet, D.J. (2023). Synthetic data from diffusion models improves imagenet classification. Transactions on Machine Learning Research"},{"key":"2436_CR3","unstructured":"Bansal, H., & Grover, A. (2023). Leaving reality to imagination: Robust classification via generated datasets. In: ICLR 2023 workshop on trustworthy and reliable large-scale machine learning models. https:\/\/openreview.net\/forum?id=LjGqAFP6rA"},{"issue":"10s","key":"2436_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3502287","volume":"54","author":"MA Bansal","year":"2022","unstructured":"Bansal, M. A., Sharma, D. R., & Kathuria, D. M. (2022). A systematic review on data scarcity problem in deep learning: Solution and applications. ACM Computing Surveys (CSUR), 54(10s), 1\u201329.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"2436_CR5","unstructured":"Brock, A., Donahue, J., & Simonyan, K. (2019). Large scale GAN training for high fidelity natural image synthesis. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=B1xsqj09Fm"},{"key":"2436_CR6","unstructured":"Brock, A., Lim, T., Ritchie, J.M., & Weston, N. (2017). Neural photo editing with introspective adversarial networks. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=HkNKFiGex"},{"key":"2436_CR7","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. In: Proceedings of the international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2436_CR8","unstructured":"Chiang, W.-L., Li, Z., Lin, Z., Sheng, Y., Wu, Z., Zhang, H., Zheng, L., Zhuang, S., Zhuang, Y., Gonzalez, J.E., Stoica, I., & Xing, E.P. (2023). Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"2436_CR9","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., & Le, Q.V. (2020). Randaugment: Practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp. 702\u2013703","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"2436_CR10","unstructured":"Dhariwal, P., & Nichol, A.Q. (2021). Diffusion models beat GANs on image synthesis. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (Eds.) Advances in neural information processing systems. https:\/\/openreview.net\/forum?id=AAWuCvzaVt"},{"key":"2436_CR11","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"2436_CR12","unstructured":"Dunlap, L., Umino, A., Zhang, H., Yang, J., Gonzalez, J.E., & Darrell, T. (2023). Diversify your vision datasets with automatic diffusion-based augmentation. In: Thirty-seventh conference on neural information processing systems. https:\/\/openreview.net\/forum?id=9wrYfqdrwk"},{"key":"2436_CR13","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. In: Advances in neural information processing systems, vol. 27. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2014\/file\/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf"},{"key":"2436_CR14","unstructured":"Hammoud, H.A.A.K., Itani, H., Pizzati, F., Bibi, A., & Ghanem, B. (2024). SynthCLIP: Are we ready for a fully synthetic CLIP training? In: Synthetic data for computer vision workshop @ CVPR 2024. https:\/\/openreview.net\/forum?id=oKwYycMSrf"},{"key":"2436_CR15","unstructured":"Hao, Y., Chi, Z., Dong, L., & Wei, F. (2023). Optimizing prompts for text-to-image generation. In: Thirty-seventh conference on neural information processing systems. https:\/\/openreview.net\/forum?id=BsZNWXD3a1"},{"key":"2436_CR16","unstructured":"He, R., Sun, S., Yu, X., Xue, C., Zhang, W., Torr, P., Bai, S., & QI, X. (2023). Is synthetic data from generative models ready for image recognition? In: The eleventh international conference on learning representations. https:\/\/openreview.net\/forum?id=nUmCcZ5RKF"},{"key":"2436_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2436_CR18","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Basart, S., Mu, N., Kadavath, S., Wang, F., Dorundo, E., Desai, R., Zhu, T., Parajuli, S., Guo, M., & et al. (2021). The many faces of robustness: A critical analysis of out-of-distribution generalization. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 8340\u20138349","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"2436_CR19","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., & Song, D. (2021). Natural adversarial examples. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 15262\u201315271","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"2436_CR20","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33, 6840\u20136851.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2436_CR21","unstructured":"Howard, J. (2019). Imagenette: A smaller subset of 10 easily classified classes from Imagenet. GitHub. https:\/\/github.com\/fastai\/imagenette"},{"key":"2436_CR22","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A.A. (2017). Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1125\u20131134","DOI":"10.1109\/CVPR.2017.632"},{"key":"2436_CR23","unstructured":"Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2018). Progressive growing of GANs for improved quality, stability, and variation. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=Hk99zCeAb"},{"issue":"13","key":"2436_CR24","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A. A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al. (2017). Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences, 114(13), 3521\u20133526.","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2436_CR25","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.-J., Shamma, D. A., et al. (2017). Visual genome: Connecting language and vision using crowdsourced dense image annotations. International Journal of Computer Vision, 123, 32\u201373.","journal-title":"International Journal of Computer Vision"},{"key":"2436_CR26","unstructured":"Kumar, A. (2022). The illustrated image captioning using transformers. ankur3107.github.io"},{"key":"2436_CR27","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., & Zhu, J.-Y. (2023). Multi-concept customization of text-to-image diffusion. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 1931\u20131941","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"2436_CR28","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., Husz\u00e1r, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., & et al. (2017). Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4681\u20134690","DOI":"10.1109\/CVPR.2017.19"},{"key":"2436_CR29","unstructured":"Lei, S. (2021). Understanding deep learning via large-scale systematic experiments. Master\u2019s thesis, The University of Syndey"},{"key":"2436_CR30","unstructured":"Lei, S., He, F., Yuan, Y., & Tao, D. (2023). Understanding deep learning via decision boundary. In: IEEE Transactions on Neural Networks and Learning Systems, pp. 1\u201312. 10.1109\/TNNLS.2023.3326654"},{"key":"2436_CR31","unstructured":"Li, J., Li, D., Savarese, S., & Hoi, S. (2023). Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: International conference on machine learning (pp. 19730\u201319742). PMLR"},{"key":"2436_CR32","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C.L. (2014). 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","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2436_CR33","doi-asserted-by":"crossref","unstructured":"Miyato, T., Kataoka, T., Koyama, M., & Yoshida, Y. (2018). Spectral normalization for generative adversarial networks. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=B1QRgziT-","DOI":"10.1007\/978-3-030-03243-2_860-1"},{"key":"2436_CR34","unstructured":"Nash, C., Menick, J., Dieleman, S., & Battaglia, P. (2021). Generating images with sparse representations. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th international conference on machine learning. Proceedings of machine learning research, vol. 139, pp. 7958\u20137968. https:\/\/proceedings.mlr.press\/v139\/nash21a.html"},{"key":"2436_CR35","unstructured":"Nichol, A.Q., & Dhariwal, P. (2021). Improved denoising diffusion probabilistic models. In: International conference on machine learning, pp. 8162\u20138171. PMLR"},{"key":"2436_CR36","unstructured":"Nichol, A.Q., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., Mcgrew, B., Sutskever, I., & Chen, M. (2022). GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models. In: Proceedings of the 39th international conference on machine learning. Proceedings of machine learning research, vol. 162, pp. 16784\u201316804. https:\/\/proceedings.mlr.press\/v162\/nichol22a.html"},{"key":"2436_CR37","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022). Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125"},{"key":"2436_CR38","unstructured":"Ravuri, S., & Vinyals, O. (2019). Classification accuracy score for conditional generative models. Advances in neural information processing systems 32"},{"key":"2436_CR39","unstructured":"Ravuri, S., & Vinyals, O. (2019). Seeing is not necessarily believing: Limitations of BigGANs for data augmentation. https:\/\/openreview.net\/forum?id=rJMw747l_4"},{"key":"2436_CR40","unstructured":"Razavi, A., Oord, A., & Vinyals, O. (2019). Generating diverse high-fidelity images with vq-vae-2. Advances in neural information processing systems 32"},{"key":"2436_CR41","unstructured":"Recht, B., Roelofs, R., Schmidt, L., & Shankar, V. (2019). Do imagenet classifiers generalize to imagenet? In: International conference on machine learning, pp. 5389\u20135400. PMLR"},{"key":"2436_CR42","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., & Lee, H. (2016). Generative adversarial text to image synthesis. In: International conference on machine learning, pp. 1060\u20131069. PMLR"},{"key":"2436_CR43","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins, H., & Monro, S. (1951). A stochastic approximation method. The Annals of Mathematical Statistics, 22, 400\u2013407.","journal-title":"The Annals of Mathematical Statistics"},{"key":"2436_CR44","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10684\u201310695","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2436_CR45","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115, 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"2436_CR46","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E. L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., et al. (2022). Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, 35, 36479\u201336494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2436_CR47","doi-asserted-by":"crossref","unstructured":"Sar\u0131y\u0131ld\u0131z, M.B., Alahari, K., Larlus, D., & Kalantidis, Y. Fake it till you make it: Learning transferable representations from synthetic imagenet clones. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 8011\u20138021","DOI":"10.1109\/CVPR52729.2023.00774"},{"key":"2436_CR48","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C.W., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., Schramowski, P., Kundurthy, S.R., Crowson, K., Schmidt, L., Kaczmarczyk, R., & Jitsev, J. (2022). LAION-5b: An open large-scale dataset for training next generation image-text models. In: Thirty-sixth conference on neural information processing systems datasets and benchmarks track. https:\/\/openreview.net\/forum?id=M3Y74vmsMcY"},{"key":"2436_CR49","unstructured":"Shin, J., Kang, M., & Park, J. (2023). Fill-up: Balancing long-tailed data with generative models. arXiv preprint arXiv:2306.07200"},{"key":"2436_CR50","doi-asserted-by":"crossref","unstructured":"Shokri, R., & Shmatikov, V. (2015). Privacy-preserving deep learning. In: Proceedings of the 22nd ACM SIGSAC conference on computer and communications security, pp. 1310\u20131321","DOI":"10.1145\/2810103.2813687"},{"key":"2436_CR51","doi-asserted-by":"crossref","unstructured":"Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017). Membership inference attacks against machine learning models. In: 2017 IEEE symposium on security and privacy (SP), pp. 3\u201318. IEEE","DOI":"10.1109\/SP.2017.41"},{"key":"2436_CR52","unstructured":"Smith, J.S., Hsu, Y.-C., Zhang, L., Hua, T., Kira, Z., Shen, Y., & Jin, H. (2024). Continual diffusion: Continual customization of text-to-image diffusion with c-loRA. Transactions on Machine Learning Research"},{"key":"2436_CR53","doi-asserted-by":"crossref","unstructured":"Tian, Y., Fan, L., Chen, K., Katabi, D., Krishnan, D., & Isola, P. (2024). Learning vision from models rivals learning vision from data. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 15887\u201315898","DOI":"10.1109\/CVPR52733.2024.01504"},{"key":"2436_CR54","unstructured":"Tian, Y., Fan, L., Isola, P., Chang, H., & Krishnan, D. (2023). Stablerep: Synthetic images from text-to-image models make strong visual representation learners. In: Thirty-seventh conference on neural information processing systems. https:\/\/openreview.net\/forum?id=xpjsOQtKqx"},{"key":"2436_CR55","doi-asserted-by":"crossref","unstructured":"Tian, Y., Krishnan, D., & Isola, P. (2020). Contrastive multiview coding. In: Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XI 16, pp. 776\u2013794. Springer","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"2436_CR56","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., & J\u00e9gou, H. (2022). Deit III: Revenge of the vit. In: European conference on computer vision, pp. 516\u2013533. Springer","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"2436_CR57","unstructured":"Trabucco, B., Doherty, K., Gurinas, M.A., & Salakhutdinov, R. (2024). Effective data augmentation with diffusion models. In: The twelfth international conference on learning representations. https:\/\/openreview.net\/forum?id=ZWzUA9zeAg"},{"key":"2436_CR58","unstructured":"Wang, H., Ge, S., Lipton, Z., & Xing, E.P. (2019). Learning robust global representations by penalizing local predictive power. Advances in Neural Information Processing Systems 32"},{"key":"2436_CR59","unstructured":"Wightman, R., Touvron, H., & Jegou, H. (2021). Resnet strikes back: An improved training procedure in timm. In: NeurIPS 2021 workshop on ImageNet: past, present, and future. https:\/\/openreview.net\/forum?id=NG6MJnVl6M5"},{"issue":"4","key":"2436_CR60","first-page":"1","volume":"37","author":"Y Xie","year":"2018","unstructured":"Xie, Y., Franz, E., Chu, M., & Thuerey, N. (2018). Tempogan: A temporally coherent, volumetric Gan for super-resolution fluid flow. ACM Transactions on Graphics (TOG), 37(4), 1\u201315.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2436_CR61","doi-asserted-by":"crossref","unstructured":"Yeom, S., Giacomelli, I., Fredrikson, M., & Jha, S. (2018). Privacy risk in machine learning: Analyzing the connection to overfitting. In: 2018 IEEE 31st computer security foundations symposium (CSF), pp. 268\u2013282. IEEE","DOI":"10.1109\/CSF.2018.00027"},{"key":"2436_CR62","unstructured":"You, Y., Li, J., Reddi, S., Hseu, J., Kumar, S., Bhojanapalli, S., Song, X., Demmel, J., Keutzer, K., & Hsieh, C.-J. (2020). Large batch optimization for deep learning: Training bert in 76 minutes. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=Syx4wnEtvH"},{"key":"2436_CR63","unstructured":"Yuan, J., Pinto, F., Davies, A., & Torr, P. (2024). Not just pretty pictures: Toward interventional data augmentation using text-to-image generators. In: ICML 2024 workshop on foundation models in the wild. https:\/\/openreview.net\/forum?id=9Gja3UYcVg"},{"key":"2436_CR64","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., & Yoo, Y. (2019). Cutmix: Regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 6023\u20136032","DOI":"10.1109\/ICCV.2019.00612"},{"key":"2436_CR65","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., & Komodakis, N. (2016). Wide residual networks. In: British machine vision conference","DOI":"10.5244\/C.30.87"},{"key":"2436_CR66","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., & Lopez-Paz, D. (2018). Mixup: Beyond empirical risk minimization. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=r1Ddp1-Rb"},{"key":"2436_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., & Metaxas, D.N. (2017). Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp. 5907\u20135915","DOI":"10.1109\/ICCV.2017.629"},{"key":"2436_CR68","unstructured":"Zhang, C., Zhang, C., Zhang, M., & Kweon, I.S. (2023). Text-to-image diffusion model in generative AI: A survey. arXiv preprint arXiv:2303.07909"},{"key":"2436_CR69","unstructured":"Zhou, Y., Sahak, H., & Ba, J. (2023). Training on thin air: Improve image classification with generated data. arXiv preprint arXiv:2305.15316"},{"key":"2436_CR70","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., Park, T., Isola, P., & Efros, A.A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp. 2223\u20132232","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02436-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02436-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02436-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T21:35:41Z","timestamp":1757194541000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02436-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":70,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["2436"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02436-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,23]]},"assertion":[{"value":"20 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate:"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication:"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Materials availability"}}]}}