{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:34:37Z","timestamp":1772822077034,"version":"3.50.1"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729393","type":"print"},{"value":"9783031729409","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T00:00:00Z","timestamp":1731801600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T00:00:00Z","timestamp":1731801600000},"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\/978-3-031-72940-9_22","type":"book-chapter","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T20:41:03Z","timestamp":1731789663000},"page":"384-400","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["AlignDiff: Aligning Diffusion Models for\u00a0General Few-Shot Segmentation"],"prefix":"10.1007","author":[{"given":"Ri-Zhao","family":"Qiu","sequence":"first","affiliation":[]},{"given":"Yu-Xiong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Kris","family":"Hauser","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,17]]},"reference":[{"key":"22_CR1","unstructured":"Cermelli, F., Mancini, M., Xian, Y., Akata, Z., Caputo, B.: Prototype-based incremental few-shot semantic segmentation. In: BMVC (2021)"},{"key":"22_CR2","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"22_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"22_CR4","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: NeurIPS (2021)"},{"key":"22_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1007\/978-3-031-19800-7_41","volume-title":"Computer Vision - ECCV 2022","author":"Q Fan","year":"2022","unstructured":"Fan, Q., Pei, W., Tai, Y.W., Tang, C.K.: Self-support few-shot semantic segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13679, pp. 701\u2013719. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19800-7_41"},{"key":"22_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":"22_CR7","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"22_CR8","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"22_CR9","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"22_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-031-19818-2_7","volume-title":"Computer Vision - ECCV 2022","author":"S Hong","year":"2022","unstructured":"Hong, S., Cho, S., Nam, J., Lin, S., Kim, S.: Cost aggregation with 4d convolutional swin transformer for few-shot segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13689, pp. 108\u2013126. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_7"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Hu, T., et al.: Anomalydiffusion: few-shot anomaly image generation with diffusion model. In: Proceedings of the AAAI Conference on Artificial Intelligence (2024)","DOI":"10.1609\/aaai.v38i8.28696"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Li, X., Wei, T., Chen, Y.P., Tai, Y.W., Tang, C.K.: FSS-1000: a 1000-class dataset for few-shot segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GliGEN: open-set grounded text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"22_CR14","unstructured":"Li, Z., Zhou, Q., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Guiding text-to-image diffusion model towards grounded generation. arXiv preprint arXiv:2301.05221 (2023)"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, N., Cao, Q., Yao, X., Han, J., Shao, L.: Learning non-target knowledge for few-shot semantic segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01128"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Min, J., Kang, D., Cho, M.: Hypercorrelation squeeze for few-shot segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"22_CR18","unstructured":"Myers-Dean, J., Zhao, Y., Price, B., Cohen, S., Gurari, D.: Generalized few-shot semantic segmentation: all you need is fine-tuning. arXiv preprint arXiv:2112.10982 (2021)"},{"key":"22_CR19","unstructured":"Nguyen, Q., Vu, T., Tran, A., Nguyen, K.: Dataset diffusion: diffusion-based synthetic data generation for pixel-level semantic segmentation. In: NeurIPS (2023)"},{"key":"22_CR20","unstructured":"Qiu, R.Z., Chen, P., Sun, W., Wang, Y.X., Hauser, K.: GAPS: few-shot incremental semantic segmentation via guided copy-paste synthesis. In: CVPRW (2023)"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Qiu, R.Z., Sun, Y., Marques, J.M.C., Hauser, K.: Real-time semantic 3D reconstruction for high-touch surface recognition for robotic disinfection. In: IROS (2022)","DOI":"10.1109\/IROS47612.2022.9981300"},{"key":"22_CR22","unstructured":"Qiu, R.: Towards real-time robotics perception with continual adaptation. Ph.D. thesis, University of Illinois at Urbana-Champaign (2023)"},{"key":"22_CR23","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 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"22_CR24","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"22_CR25","unstructured":"Saharia, C., et\u00a0al.: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. In: NeurIPS (2022)"},{"key":"22_CR26","unstructured":"Schuhmann, C., et\u00a0al.: Laion-5b: an open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:2210.08402 (2022)"},{"key":"22_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/978-3-031-20044-1_9","volume-title":"Computer Vision - ECCV 2022","author":"X Shi","year":"2022","unstructured":"Shi, X., et al.: Dense cross-query-and-support attention weighted mask aggregation for few-shot segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13680, pp. 151\u2013168. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20044-1_9"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Tian, Z., et al.: Generalized few-shot semantic segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01127"},{"key":"22_CR29","unstructured":"Tian, Z., Zhao, H., Shu, M., Yang, Z., Li, R., Jia, J.: Prior guided feature enrichment network for few-shot segmentation. TPAMI (2020)"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Wang, K., Liew, J.H., Zou, Y., Zhou, D., Feng, J.: Panet: few-shot image semantic segmentation with prototype alignment. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00929"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Wu, W., Zhao, Y., Shou, M.Z., Zhou, H., Shen, C.: Diffumask: synthesizing images with pixel-level annotations for semantic segmentation using diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Xu, Q., Zhao, W., Lin, G., Long, C.: Self-calibrated cross attention network for few-shot segmentation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00067"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Yang, L., Zhuo, W., Qi, L., Shi, Y., Gao, Y.: Mining latent classes for few-shot segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00860"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Zhi, S., Laidlow, T., Leutenegger, S., Davison, A.J.: In-place scene labelling and understanding with implicit scene representation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01554"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72940-9_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T21:35:16Z","timestamp":1731792916000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72940-9_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,17]]},"ISBN":["9783031729393","9783031729409"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72940-9_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,17]]},"assertion":[{"value":"17 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}