{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T04:10:51Z","timestamp":1745554251614,"version":"3.40.4"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031882227","type":"print"},{"value":"9783031882234","type":"electronic"}],"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\/978-3-031-88223-4_17","type":"book-chapter","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T03:44:40Z","timestamp":1745466280000},"page":"226-243","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Synthetic Image Detection Using Mixture of\u00a0Knowledge Distillation from\u00a0Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Hessen","family":"Bougueffa Eutamene","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wassim","family":"Hamidouche","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mamadou","family":"Keita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdelmalik","family":"Taleb-Ahmed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdenour","family":"Hadid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"17_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Binh, L.M., Woo, S.: ADD: frequency attention and multi-view based knowledge distillation to detect low-quality compressed deepfake images In:. The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22) (2022). https:\/\/arxiv.org\/abs\/2408.03888","DOI":"10.1609\/aaai.v36i1.19886"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: COCO-stuff: thing and stuff classes in context. In: CVPR (2018). https:\/\/github.com\/nightrome\/cocostuff","DOI":"10.1109\/CVPR.2018.00132"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Coccomini, D.A., Esuli, A., Falchi, F., Gennaro, C., Amato, G.: Detecting images generated by diffusers. arXiv preprint arXiv:2303.05275 (2023)","DOI":"10.7717\/peerj-cs.2127"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Cozzolino, D., Poggi, G., Corvi, R., Nie\u00dfner, M., Verdoliva, L.: Raising the bar of AI-generated image detection with CLIP. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4356\u20134366 (2024)","DOI":"10.1109\/CVPRW63382.2024.00439"},{"key":"17_CR7","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"17_CR8","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":"17_CR9","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Everingham, M., Gool, L.V., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge (2010). http:\/\/host.robots.ox.ac.uk\/pascal\/VOC\/","DOI":"10.1007\/s11263-009-0275-4"},{"key":"17_CR11","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR13","unstructured":"Hugo, T., Cord, M., Matthijs, D., Francisco, M., Alexandre, S., Herve, J.: Training data-efficient image transformers & distillation through attention. In: ICML (2021)"},{"key":"17_CR14","unstructured":"Keita, M., Hamidouche, W., Bougueffa, H., Hadid, A., Taleb-Ahmed, A.: Harnessing the power of large vision language models for synthetic image detection. arXiv preprint arXiv:2404.02726 (2024)"},{"key":"17_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"17_CR16","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"17_CR17","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: 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 (2023)"},{"key":"17_CR18","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"17_CR19","unstructured":"Lin, S., et al.: Knowledge distillation via the target-aware transformer. arXiv preprint arXiv:2205.10793 (2022), https:\/\/arxiv.org\/abs\/2205.10793"},{"key":"17_CR20","unstructured":"Lin, T.Y., et al.: Microsoft COCO: Common objects in context (2017). https:\/\/cocodataset.org\/#home"},{"key":"17_CR21","unstructured":"Lu, Z., Huang, D., Bai, L., Liu, X., Qu, J., Ouyang, W.: Seeing is not always believing: A quantitative study on human perception of AI-generated images. arXiv preprint arXiv:2304.13023 (2023)"},{"key":"17_CR22","unstructured":"Nichol, A., et al.: GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"17_CR23","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"17_CR24","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"17_CR25","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents (2022)"},{"key":"17_CR26","unstructured":"Ricker, J., Damm, S., Holz, T., Fischer, A.: Towards the detection of diffusion model deepfakes. arXiv preprint arXiv:2210.14571 (2022)"},{"key":"17_CR27","unstructured":"Ricker, J., Damm, S., Holz, T., Fischer, A.: Towards the detection of diffusion model deepfakes. arXiv preprint arXiv:2210.14571 (2022)"},{"key":"17_CR28","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":"17_CR29","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding (2022)"},{"key":"17_CR30","doi-asserted-by":"publisher","first-page":"8620","DOI":"10.1109\/TMM.2023.3238554","volume":"25","author":"H Tan","year":"2023","unstructured":"Tan, H., Yin, B., Wei, K., Liu, X., Li, X.: ALR-GAN: adaptive layout refinement for text-to-image synthesis. IEEE Trans. Multimedia 25, 8620\u20138631 (2023). https:\/\/doi.org\/10.1109\/TMM.2023.3238554","journal-title":"IEEE Trans. Multimedia"},{"key":"17_CR31","unstructured":"Wang, Y., Hao, Y., Cong, A.X.: Harnessing machine learning for discerning AI-generated synthetic images. arXiv preprint arXiv:2401.07358 (2024)"},{"key":"17_CR32","unstructured":"Wang, Z., Yu, J., Yu, A.W., Dai, Z., Tsvetkov, Y., Cao, Y.: SimVLM: Simple visual language model pretraining with weak supervision. arXiv preprint arXiv:2108.10904 (2021)"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Xi, Z., Huang, W., Wei, K., Luo, W., Zheng, P.: AI-generated image detection using a cross-attention enhanced dual-stream network. In: 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1463\u20131470. IEEE (2023)","DOI":"10.1109\/APSIPAASC58517.2023.10317126"},{"issue":"3","key":"17_CR34","doi-asserted-by":"publisher","first-page":"3121","DOI":"10.1109\/TPAMI.2022.3181070","volume":"45","author":"W Xia","year":"2022","unstructured":"Xia, W., Zhang, Y., Yang, Y., Xue, J.H., Zhou, B., Yang, M.H.: Gan inversion: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3121\u20133138 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR35","unstructured":"Yan, S., et al.: A sanity check for AI-generated image detection. arXiv preprint arXiv:2406.19435 (2024)"},{"issue":"4","key":"17_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3626235","volume":"56","author":"L Yang","year":"2023","unstructured":"Yang, L., et al.: Diffusion models: a comprehensive survey of methods and applications. ACM Comput. Surv. 56(4), 1\u201339 (2023)","journal-title":"ACM Comput. Surv."},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Focal and global knowledge distillation for detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4643\u20134652 (2022)","DOI":"10.1109\/CVPR52688.2022.00460"},{"key":"17_CR38","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":"17_CR39","doi-asserted-by":"crossref","unstructured":"Zar\u00e1ndy, \u00c1., Rekeczky, C., Szolgay, P., Chua, L.O.: Overview of CNN research: 25 years history and the current trends. In: 2015 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 401\u2013404. IEEE (2015)","DOI":"10.1109\/ISCAS.2015.7168655"},{"key":"17_CR40","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: A survey. arXiv preprint arXiv:2304.00685 (2023)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition. ICPR 2024 International Workshops and Challenges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-88223-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T03:45:08Z","timestamp":1745466308000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-88223-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031882227","9783031882234"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-88223-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 April 2025","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"}}]}}