{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:34:25Z","timestamp":1742913265096,"version":"3.40.3"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781827"},{"type":"electronic","value":"9783031781834"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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\/978-3-031-78183-4_27","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T12:00:37Z","timestamp":1733227237000},"page":"423-438","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Using Generated Privileged Information by Text-to-Image Diffusion Models"],"prefix":"10.1007","author":[{"given":"Rafael-Edy","family":"Menadil","sequence":"first","affiliation":[]},{"given":"Mariana-Iuliana","family":"Georgescu","sequence":"additional","affiliation":[]},{"given":"Radu Tudor","family":"Ionescu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Alehdaghi, M., Josi, A., Cruz, R.M.O., Granger, E.: Visible-Infrared Person Re-Identification Using Privileged Intermediate Information. In: Proceedings of ECCVW. pp. 720\u2013737 (2022)","DOI":"10.1007\/978-3-031-25072-9_48"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Antoniou, A., Storkey, A., Edwards, H.: Augmenting image classifiers using data augmentation generative adversarial networks. In: Proceedings of ICANN. pp. 594\u2013603 (2018)","DOI":"10.1007\/978-3-030-01424-7_58"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: Proceedings of CVPR. pp. 18208\u201318218 (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"27_CR4","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":"27_CR5","unstructured":"Ba, J., Caruana, R.: Do deep nets really need to be deep? In: Proceedings of NIPS. pp. 2654\u20132662 (2014)"},{"issue":"9","key":"27_CR6","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","volume":"45","author":"FA Croitoru","year":"2023","unstructured":"Croitoru, F.A., Hondru, V., Ionescu, R.T., Shah, M.: Diffusion models in vision: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(9), 10850\u201310869 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.: RandAugment: Practical Automated Data Augmentation with a Reduced Search Space. In: Proceedings of NeurIPS. vol.\u00a033, pp. 18613\u201318624 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"27_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, L.K.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In: Proceedings of NAACL-HLT. pp. 4171\u20134186 (2019)"},{"key":"27_CR9","unstructured":"DeVries, T., Taylor, G.W.: Improved Regularization of Convolutional Neural Networks with Cutout. arXiv preprint arXiv:1708.04552 (2017)"},{"key":"27_CR10","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Proceedings of NeurIPS. vol.\u00a034, pp. 8780\u20138794 (2021)"},{"key":"27_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.: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In: Proceedings of ICLR (2021)"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Feng, Y., Wang, H., Hu, R., Yi, D.T.: Triplet distillation for deep face recognition. In: Proceedings of ICIP. pp. 808\u2013812 (2020)","DOI":"10.1109\/ICIP40778.2020.9190651"},{"key":"27_CR13","doi-asserted-by":"publisher","first-page":"264","DOI":"10.2307\/747998","volume":"28","author":"LB Gambrell","year":"1993","unstructured":"Gambrell, L.B., Jawitz, P.B.: Mental Imagery, Text Illustrations, and Children\u2019s Story Comprehension and Recall. Read. Res. Q. 28, 264\u2013276 (1993)","journal-title":"Read. Res. Q."},{"key":"27_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101534","volume":"58","author":"Z Gao","year":"2019","unstructured":"Gao, Z., Wu, S., Liu, Z., Luo, J., Zhang, H., Gong, M., Li, S.: Learning the implicit strain reconstruction in ultrasound elastography using privileged information. Med. Image Anal. 58, 101534 (2019)","journal-title":"Med. Image Anal."},{"issue":"10","key":"27_CR15","doi-asserted-by":"publisher","first-page":"2581","DOI":"10.1109\/TPAMI.2019.2929038","volume":"42","author":"NC Garcia","year":"2019","unstructured":"Garcia, N.C., Morerio, P., Murino, V.: Learning with privileged information via adversarial discriminative modality distillation. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2581\u20132593 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"27_CR16","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/s00138-021-01270-x","volume":"33","author":"MI Georgescu","year":"2022","unstructured":"Georgescu, M.I., Du\u0163\u01ce, G.E., Ionescu, R.T.: Teacher-student training and triplet loss to reduce the effect of drastic face occlusion: Application to emotion recognition, gender identification and age estimation. Mach. Vis. Appl. 33(1), 12 (2022)","journal-title":"Mach. Vis. Appl."},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Georgescu, M.I., Ionescu, R.T.: Teacher-student training and triplet loss for facial expression recognition under occlusion. In: Proceedings of ICPR. pp. 2288\u20132295 (2021)","DOI":"10.1109\/ICPR48806.2021.9412493"},{"key":"27_CR18","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of AISTATS. pp. 249\u2013256 (2010)"},{"key":"27_CR19","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Proceedings of NIPS. vol.\u00a027, pp. 2672\u20132680 (2014)"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Gu, S., Chen, D., Bao, J., Wen, F., Zhang, B., Chen, D., Yuan, L., Guo, B.: Vector quantized diffusion model for text-to-image synthesis. In: Proceedings of CVPR. pp. 10696\u201310706 (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"27_CR21","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the Knowledge in a Neural Network. In: Proceedings of NIPS Deep Learning and Representation Learning Workshop (2014)"},{"key":"27_CR22","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Proceedings of NeurIPS. vol.\u00a033, pp. 6840\u20136851 (2020)"},{"key":"27_CR23","unstructured":"Jung, B., Johansson, F.D.: Efficient learning of nonlinear prediction models with time-series privileged information. In: Proceedings of NeurIPS. vol.\u00a035, pp. 19048\u201319060 (2022)"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Lang, K.: NewsWeeder: Learning to Filter Netnews. In: Proceedings of ICML. pp. 331\u2013339 (1995)","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Lee, W., Lee, J., Kim, D., Ham, B.: Learning with privileged information for efficient image super-resolution. In: Proceedings of ECCV. pp. 465\u2013482 (2020)","DOI":"10.1007\/978-3-030-58586-0_28"},{"key":"27_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106927","volume":"159","author":"Z Liu","year":"2023","unstructured":"Liu, Z., Wei, J., Li, R., Zhou, J.: Learning multi-modal brain tumor segmentation from privileged semi-paired MRI images with curriculum disentanglement learning. Comput. Biol. Med. 159, 106927 (2023)","journal-title":"Comput. Biol. Med."},{"key":"27_CR27","unstructured":"Lopez-Paz, D., Bottou, L., Sch\u00f6lkopf, B., Vapnik, V.: Unifying distillation and privileged information. In: Proceedings of ICLR (2016)"},{"key":"27_CR28","unstructured":"Loshchilov, I., Hutter, F.: Decoupled Weight Decay Regularization. In: Proceedings of ICLR (2019)"},{"key":"27_CR29","unstructured":"Maas, A.L., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning Word Vectors for Sentiment Analysis. In: Proceedings of ACL. pp. 142\u2013150 (2011)"},{"key":"27_CR30","unstructured":"Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., Chen, M.: GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In: Proceedings of ICML. pp. 16784\u201316804 (2021)"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., Cho, M.: Relational Knowledge Distillation. In: Proceedings of CVPR. pp. 3962\u20133971 (2019)","DOI":"10.1109\/CVPR.2019.00409"},{"key":"27_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.specom.2019.08.006","volume":"114","author":"Y Qian","year":"2019","unstructured":"Qian, Y., Hu, H., Tan, T.: Data augmentation using generative adversarial networks for robust speech recognition. Speech Commun. 114, 1\u20139 (2019)","journal-title":"Speech Commun."},{"key":"27_CR33","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning Transferable Visual Models From Natural Language Supervision. In: Proceedings of ICML. pp. 8748\u20138763 (2021)"},{"key":"27_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: Proceedings of CVPR. pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"27_CR35","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E., Ghasemipour, S.K.S., Ayan, B.K., Mahdavi, S.S., Lopes, R.G., et\u00a0al.: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. In: Proceedings of NeurIPS. vol.\u00a035, pp. 36479\u201336494 (2022)"},{"issue":"1","key":"27_CR36","doi-asserted-by":"publisher","first-page":"16884","DOI":"10.1038\/s41598-019-52737-x","volume":"9","author":"V Sandfort","year":"2019","unstructured":"Sandfort, V., Yan, K., Pickhardt, P.J., Summers, R.M.: Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks. Sci. Rep. 9(1), 16884 (2019)","journal-title":"Sci. Rep."},{"key":"27_CR37","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. In: Proceedings of EMC$$^2$$ (2019)"},{"key":"27_CR38","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et\u00a0al.: LAION-5B: An open large-scale dataset for training next generation image-text models. In: Proceedings of NeurIPS. vol.\u00a035, pp. 25278\u201325294 (2022)"},{"key":"27_CR39","unstructured":"Shivashankar, C., Miller, S.: Semantic Data Augmentation with Generative Models. In: Proceedings of CVPRW. pp. 863\u2013873 (2023)"},{"key":"27_CR40","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using non-equilibrium thermodynamics. In: Proceedings of ICML. pp. 2256\u20132265 (2015)"},{"key":"27_CR41","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Proceedings of NeurIPS. vol.\u00a032, pp. 11918\u201311930 (2019)"},{"issue":"5\u20136","key":"27_CR42","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.neunet.2009.06.042","volume":"22","author":"V Vapnik","year":"2009","unstructured":"Vapnik, V., Vashist, A.: A new learning paradigm: Learning using privileged information. Neural Netw. 22(5\u20136), 544\u2013557 (2009)","journal-title":"Neural Netw."},{"key":"27_CR43","unstructured":"Yang, J., Li, B., Yang, F., Zeng, A., Zhang, L., Zhang, R.: Boosting human-object interaction detection with text-to-image diffusion model. arXiv preprint arXiv:2305.12252 (2023)"},{"key":"27_CR44","doi-asserted-by":"crossref","unstructured":"Yim, J., Joo, D., Bae, J., Kim, J.: A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning. In: Proceedings of CVPR. pp. 7130\u20137138 (2017)","DOI":"10.1109\/CVPR.2017.754"},{"key":"27_CR45","doi-asserted-by":"crossref","unstructured":"Yimam, S.M., \u0160tajner, S., Riedl, M., Biemann, C.: Multilingual and Cross-Lingual Complex Word Identification. In: Proceedings of RANLP. pp. 813\u2013822 (2017)","DOI":"10.26615\/978-954-452-049-6_104"},{"key":"27_CR46","doi-asserted-by":"crossref","unstructured":"You, S., Xu, C., Xu, C., Tao, D.: Learning from multiple teacher networks. In: Proceedings of KDD. pp. 1285\u20131294 (2017)","DOI":"10.1145\/3097983.3098135"},{"key":"27_CR47","doi-asserted-by":"crossref","unstructured":"Yu, L., Yazici, V.O., Liu, X., van\u00a0de Weijer, J., Cheng, Y., Ramisa, A.: Learning Metrics from Teachers: Compact Networks for Image Embedding. In: Proceedings of CVPR. pp. 2907\u20132916 (2019)","DOI":"10.1109\/CVPR.2019.00302"},{"key":"27_CR48","doi-asserted-by":"crossref","unstructured":"Yuan, S., Stenger, B., Kim, T.K.: RGB-based 3D hand pose estimation via privileged learning with depth images. arXiv preprint arXiv:1811.07376 (2018)","DOI":"10.1109\/ICCVW.2019.00348"},{"key":"27_CR49","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond Empirical Risk Minimization. In: Proceedings of ICLR (2018)"},{"key":"27_CR50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108741","volume":"129","author":"P Zhao","year":"2022","unstructured":"Zhao, P., Xie, L., Wang, J., Zhang, Y., Tian, Q.: Progressive privileged knowledge distillation for online action detection. Pattern Recogn. 129, 108741 (2022)","journal-title":"Pattern Recogn."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78183-4_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T12:13:59Z","timestamp":1733228039000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78183-4_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031781827","9783031781834"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78183-4_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}