{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T13:40:29Z","timestamp":1743342029294,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819626434","type":"print"},{"value":"9789819626441","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\/978-981-96-2644-1_15","type":"book-chapter","created":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T13:23:57Z","timestamp":1743341037000},"page":"211-227","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HYPNOS: Highly Precise Foreground-Focused Diffusion Finetuning for\u00a0Inanimate Objects"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1206-9579","authenticated-orcid":false,"given":"Oliverio Theophilus","family":"Nathanael","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5146-8648","authenticated-orcid":false,"given":"Jonathan Samuel","family":"Lumentut","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1272-7272","authenticated-orcid":false,"given":"Nicholas Hans","family":"Muliawan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3065-5040","authenticated-orcid":false,"given":"Edbert Valencio","family":"Angky","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0850-601X","authenticated-orcid":false,"given":"Felix Indra","family":"Kurniadi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6051-4279","authenticated-orcid":false,"given":"Alfi Yusrotis","family":"Zakiyyah","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9486-6432","authenticated-orcid":false,"given":"Jeklin","family":"Harefa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,28]]},"reference":[{"key":"15_CR1","unstructured":"Blattmann, A., et\u00a0al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Chauhan, V.K., Zhou, J., Lu, P., Molaei, S., Clifton, D.A.: A brief review of hypernetworks in deep learning. arXiv preprint arXiv:2306.06955 (2023)","DOI":"10.1007\/s10462-024-10862-8"},{"key":"15_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"15_CR5","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\,\\times \\,$$16 words: transformers for image recognition at scale (2021)"},{"key":"15_CR6","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"key":"15_CR7","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_CR8","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR9","unstructured":"Hu, E.J., et al.: LoRa: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Kingma, D.P., Welling, M., et\u00a0al.: An introduction to variational autoencoders. Found. Trends\u00ae Mach. Learn. 12(4), 307\u2013392 (2019)","DOI":"10.1561\/2200000056"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Lee, M.S., Shin, W., Han, S.W.: Tracer: extreme attention guided salient object tracing network (student abstract). In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, pp. 12993\u201312994 (2022)","DOI":"10.1609\/aaai.v36i11.21633"},{"key":"15_CR12","unstructured":"Lu, L., Zhang, B., Niu, L.: DreamCom: finetuning text-guided inpainting model for image composition. arXiv preprint arXiv:2309.15508 (2023)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Motamed, S., Paudel, D.P., Van\u00a0Gool, L.: Lego: learning to disentangle and invert concepts beyond object appearance in text-to-image diffusion models. arXiv preprint arXiv:2311.13833 (2023)","DOI":"10.1007\/978-3-031-72633-0_7"},{"key":"15_CR14","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_CR15","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"15_CR16","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"15_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404","volume":"106","author":"X Qin","year":"2020","unstructured":"Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O.R., Jagersand, M.: U2-Net: going deeper with nested u-structure for salient object detection. Pattern Recogn. 106, 107404 (2020)","journal-title":"Pattern Recogn."},{"key":"15_CR18","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"140","key":"15_CR19","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"15_CR20","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 (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"15_CR21","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Ruiz, N., et al.: HyperDreamBooth: hypernetworks for fast personalization of text-to-image models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6527\u20136536 (2024)","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"15_CR23","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Sauer, A., Lorenz, D., Blattmann, A., Rombach, R.: Adversarial diffusion distillation. arXiv preprint arXiv:2311.17042 (2023)","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Schwartz, I., Sn\u00e6bjarnarson, V., Chefer, H., Belongie, S., Wolf, L., Benaim, S.: Discriminative class tokens for text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22725\u201322735 (2023)","DOI":"10.1109\/ICCV51070.2023.02077"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Shi, Z., Zhou, X., Qiu, X., Zhu, X.: Improving image captioning with better use of captions. arXiv preprint arXiv:2006.11807 (2020)","DOI":"10.18653\/v1\/2020.acl-main.664"},{"key":"15_CR27","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"15_CR28","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"15_CR29","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"15_CR30","first-page":"16782","volume":"35","author":"Y Xu","year":"2022","unstructured":"Xu, Y., Liu, Z., Tegmark, M., Jaakkola, T.: Poisson flow generative models. Adv. Neural. Inf. Process. Syst. 35, 16782\u201316795 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR31","unstructured":"Xu, Y., Liu, Z., Tian, Y., Tong, S., Tegmark, M., Jaakkola, T.: PFGM++: unlocking the potential of physics-inspired generative models. In: International Conference on Machine Learning, pp. 38566\u201338591. PMLR (2023)"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2644-1_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T13:24:18Z","timestamp":1743341058000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2644-1_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819626434","9789819626441"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2644-1_15","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":"28 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}