{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:25:06Z","timestamp":1767324306889,"version":"3.48.0"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032128393","type":"print"},{"value":"9783032128409","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-12840-9_18","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:22:39Z","timestamp":1767324159000},"page":"267-283","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Masked Attention Transformer for\u00a0Few-Shot Classification and\u00a0Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5322-9130","authenticated-orcid":false,"given":"Dustin","family":"Carri\u00f3n-Ojeda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9002-9832","authenticated-orcid":false,"given":"Stefan","family":"Roth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8644-1074","authenticated-orcid":false,"given":"Simone","family":"Schaub-Meyer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"18_CR1","unstructured":"Aggarwal, P., Deshpande, A., Narasimhan, K.R.: SemSup-XC: semantic supervision for zero and few-shot extreme classification. In: ICML, vol.\u00a0202, pp. 228\u2013247 (2023)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Alfassy, A., et al.: LaSO: label-set operations networks for multi-label few-shot learning. In: CVPR, pp. 6548\u20136557 (2019)","DOI":"10.1109\/CVPR.2019.00671"},{"key":"18_CR3","unstructured":"Allen, K.R., Shelhamer, E., Shin, H., Tenenbaum, J.B.: Infinite mixture prototypes for few-shot learning. In: ICML, vol.\u00a097, pp. 232\u2013241 (2019)"},{"key":"18_CR4","unstructured":"Antoniou, A., Edwards, H., Storkey, A.J.: How to train your MAML. In: ICLR (2019)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"18_CR6","unstructured":"Carri\u00f3n-Ojeda, D., Alam, M., Escalera, S., et\u00a0al.: NeurIPS\u201922 cross-domain MetaDL challenge: results and lessons learned. In: NeurIPS Competition Track, vol.\u00a0220, pp. 50\u201372 (2022)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., Dong, Y., Lu, Z., Yu, Y., Han, J.: Pixel matching network for cross-domain few-shot segmentation. In: WACV, pp. 978\u2013987 (2024)","DOI":"10.1109\/WACV57701.2024.00102"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: CVPR, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The Cityscapes dataset for semantic urban scene understanding. In: CVPR, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"18_CR10","unstructured":"Dhillon, G.S., Chaudhari, P., Ravichandran, A., Soatto, S.: A baseline for few-shot image classification. In: ICLR (2020)"},{"key":"18_CR11","unstructured":"Dong, N., Xing, E.P.: Few-shot semantic segmentation with prototype learning. In: BMVC (2018)"},{"key":"18_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Fan, X., Wang, X., Gao, J., Wang, J., Luo, Z., Liu, R.: Bi-level learning of task-specific decoders for joint registration and one-shot medical image segmentation. In: CVPR, pp. 11726\u201311735 (2024)","DOI":"10.1109\/CVPR52733.2024.01114"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Fang, Z., Wang, X., Li, H., Liu, J., Hu, Q., Xiao, J.: FastRecon: few-shot industrial anomaly detection via fast feature reconstruction. In: ICCV, pp. 17481\u201317490 (2023)","DOI":"10.1109\/ICCV51070.2023.01603"},{"key":"18_CR15","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, vol.\u00a070, pp. 1126\u20131135 (2017)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Gong, X., Xia, X., Zhu, W., Zhang, B., Doermann, D., Zhuo, L.: Deformable Gabor feature networks for biomedical image classification. In: WACV, pp. 4004\u20134012 (2021)","DOI":"10.1109\/WACV48630.2021.00405"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Hao, F., He, F., Liu, L., Wu, F., Tao, D., Cheng, J.: Class-aware patch embedding adaptation for few-shot image classification. In: ICCV, pp. 18905\u201318915 (2023)","DOI":"10.1109\/ICCV51070.2023.01733"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Herzog, J.: Adapt before comparison: a new perspective on cross-domain few-shot segmentation. In: CVPR, pp. 23605\u201323615 (2024)","DOI":"10.1109\/CVPR52733.2024.02228"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Kang, D., Cho, M.: Integrative few-shot learning for classification and segmentation. In: CVPR, pp. 9979\u20139990 (2022)","DOI":"10.1109\/CVPR52688.2022.00974"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Kang, D., Koniusz, P., Cho, M., Murray, N.: Distilling self-supervised vision transformers for weakly-supervised few-shot classification & segmentation. In: CVPR, pp. 19627\u201319638 (2023)","DOI":"10.1109\/CVPR52729.2023.01880"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Kang, D., Kwon, H., Min, J., Cho, M.: Relational embedding for few-shot classification. In: ICCV, pp. 8822\u20138833 (2021)","DOI":"10.1109\/ICCV48922.2021.00870"},{"key":"18_CR22","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"18_CR23","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV, pp. 4015\u20134026 (2023)"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Li, W.H., Liu, X., Bilen, H.: Cross-domain few-shot learning with task-specific adapters. In: CVPR, pp. 7161\u20137170 (2022)","DOI":"10.1109\/CVPR52688.2022.00702"},{"key":"18_CR25","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Liu, J., Bao, Y., Xie, G.S., Xiong, H., Sonke, J.J., Gavves, E.: Dynamic prototype convolution network for few-shot semantic segmentation. In: CVPR, pp. 11553\u201311562 (2022)","DOI":"10.1109\/CVPR52688.2022.01126"},{"key":"18_CR27","unstructured":"Liu, Y., Zhu, M., Li, H., Chen, H., Wang, X., Shen, C.: Matcher: segment anything with one shot using all-purpose feature matching. In: ICLR (2024)"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Ma, T., Sun, Y., Yang, Z., Yang, Y.: ProD: prompting-to-disentangle domain knowledge for cross-domain few-shot image classification. In: CVPR, pp. 19754\u201319763 (2023)","DOI":"10.1109\/CVPR52729.2023.01892"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Min, J., Kang, D., Cho, M.: Hypercorrelation squeeze for few-shot segmentation. In: ICCV, pp. 6941\u20136952 (2021)","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Moon, S., et al.: MSI: maximize support-set information for few-shot segmentation. In: ICCV, pp. 19266\u201319276 (2023)","DOI":"10.1109\/ICCV51070.2023.01765"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Nguyen, K., Todorovic, S.: Feature weighting and boosting for few-shot segmentation. In: ICCV, pp. 622\u2013631 (2019)","DOI":"10.1109\/ICCV.2019.00071"},{"key":"18_CR32","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., et\u00a0al.: DINOv2: learning robust visual features without supervision. Trans. Mach. Learn. Res. (2024)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Peng, B., et al.: Hierarchical dense correlation distillation for few-shot segmentation. In: CVPR, pp. 23641\u201323651 (2023)","DOI":"10.1109\/CVPR52729.2023.02264"},{"key":"18_CR34","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, vol.\u00a0139, pp. 8748\u20138763 (2021)"},{"key":"18_CR35","unstructured":"Raghu, A., Raghu, M., Bengio, S., Vinyals, O.: Rapid learning or feature reuse? Towards understanding the effectiveness of MAML. In: ICLR (2020)"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Shaban, A., Bansal, S., Liu, Z., Essa, I., Boots, B.: One-shot learning for semantic segmentation. In: BMVC (2017)","DOI":"10.5244\/C.31.167"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Silva-Rodr\u00edguez, J., Hajimiri, S., Ben\u00a0Ayed, I., Dolz, J.: A closer look at the few-shot adaptation of large vision-language models. In: CVPR, pp. 23681\u201323690 (2024)","DOI":"10.1109\/CVPR52733.2024.02235"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Simon, C., Koniusz, P., Harandi, M.: Meta-learning for multi-label few-shot classification. In: WACV, pp. 346\u2013355 (2022)","DOI":"10.1109\/WACV51458.2022.00042"},{"key":"18_CR39","unstructured":"Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: NIPS, pp. 4077\u20134087 (2017)"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Sun, Q., Liu, Y., Chua, T.S., Schiele, B.: Meta-transfer learning for few-shot learning. In: CVPR, pp. 403\u2013412 (2019)","DOI":"10.1109\/CVPR.2019.00049"},{"key":"18_CR41","unstructured":"Team, G.G.: Gemini: a family of highly capable multimodal models. arXiv:2312.11805 [cs.CL] (2023)"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Tian, P., Wu, Z., Qi, L., Wang, L., Shi, Y., Gao, Y.: Differentiable meta-learning model for few-shot semantic segmentation. In: AAAI, pp. 12087\u201312094 (2020)","DOI":"10.1609\/aaai.v34i07.6887"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J.B., Isola, P.: Rethinking few-shot image classification: a good embedding is all you need? In: ECCV, vol. 12359, pp. 266\u2013282 (2020)","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Tian, Z., et al.: Generalized few-shot semantic segmentation. In: CVPR, pp. 11563\u201311572 (2022)","DOI":"10.1109\/CVPR52688.2022.01127"},{"issue":"2","key":"18_CR45","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1109\/TPAMI.2020.3013717","volume":"44","author":"Z Tian","year":"2022","unstructured":"Tian, Z., Zhao, H., Shu, M., Yang, Z., Li, R., Jia, J.: Prior guided feature enrichment network for few-shot segmentation. IEEE T. Pattern Anal. Mach. Intell. 44(2), 1050\u20131065 (2022)","journal-title":"IEEE T. Pattern Anal. Mach. Intell."},{"key":"18_CR46","unstructured":"Ullah, I., et al.: Meta-album: multi-domain meta-dataset for few-shot image classification. In: NeurIPS, vol.\u00a035, pp. 3232\u20133247 (2022)"},{"key":"18_CR47","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"18_CR48","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: NIPS, pp. 3630\u20133638 (2016)"},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, B., Pang, J., Chen, H., Liu, W.: Rethinking prior information generation with CLIP for few-shot segmentation. In: CVPR, pp. 3941\u20133951 (2024)","DOI":"10.1109\/CVPR52733.2024.00378"},{"key":"18_CR50","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, pp. 9196\u20139205 (2019)","DOI":"10.1109\/ICCV.2019.00929"},{"key":"18_CR51","unstructured":"Wang, Y., Luo, N., Zhang, T.: Focus on query: adversarial mining transformer for few-shot segmentation. In: NeurIPS, vol.\u00a036, pp. 31524\u201331542 (2023)"},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Wu, A., Han, Y., Zhu, L., Yang, Y.: Universal-prototype enhancing for few-shot object detection. In: ICCV, pp. 9567\u20139576 (2021)","DOI":"10.1109\/ICCV48922.2021.00943"},{"key":"18_CR53","doi-asserted-by":"crossref","unstructured":"Xie, G.S., Xiong, H., Liu, J., Yao, Y., Shao, L.: Few-shot semantic segmentation with cyclic memory network. In: ICCV, pp. 7293\u20137302 (2021)","DOI":"10.1109\/ICCV48922.2021.00720"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Xu, Q., Zhao, W., Lin, G., Long, C.: Self-calibrated cross attention network for few-shot segmentation. In: ICCV, pp. 655\u2013665 (2023)","DOI":"10.1109\/ICCV51070.2023.00067"},{"key":"18_CR55","doi-asserted-by":"crossref","unstructured":"Yang, Y., Chen, Q., Feng, Y., Huang, T.: MIANet: aggregating unbiased instance and general information for few-shot semantic segmentation. In: CVPR, pp. 7131\u20137140 (2023)","DOI":"10.1109\/CVPR52729.2023.00689"},{"key":"18_CR56","doi-asserted-by":"crossref","unstructured":"Ye, C., Zhu, H., Liao, Y., Zhang, Y., Chen, T., Fan, J.: What makes for effective few-shot point cloud classification? In: WACV, pp. 1829\u20131838 (2022)","DOI":"10.1109\/WACV51458.2022.00034"},{"key":"18_CR57","unstructured":"Zhang, A., Gao, G., Jiao, J., Liu, C., Wei, Y.: Bridge the points: graph-based few-shot segment anything semantically. In: NeurIPS (2024)"},{"key":"18_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, B., Xiao, J., Qin, T.: Self-guided and cross-guided learning for few-shot segmentation. In: CVPR, pp. 8312\u20138321 (2021)","DOI":"10.1109\/CVPR46437.2021.00821"},{"issue":"12","key":"18_CR59","doi-asserted-by":"publisher","first-page":"8586","DOI":"10.1109\/TCSVT.2022.3193612","volume":"32","author":"M Zhang","year":"2022","unstructured":"Zhang, M., Shi, M., Li, L.: MFNet: multiclass few-shot segmentation network with pixel-wise metric learning. IEEE T. Circuits Syst. Video Tech. 32(12), 8586\u20138598 (2022)","journal-title":"IEEE T. Circuits Syst. Video Tech."},{"key":"18_CR60","doi-asserted-by":"crossref","unstructured":"Zhou, F., Wang, P., Zhang, L., Wei, W., Zhang, Y.: Revisiting prototypical network for cross domain few-shot learning. In: CVPR, pp. 20061\u201320070 (2023)","DOI":"10.1109\/CVPR52729.2023.01921"},{"key":"18_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Xu, H.M., Shu, Y., Liu, L.: Unlocking the potential of pre-trained vision transformers for few-shot semantic segmentation through relationship descriptors. In: CVPR, pp. 3817\u20133827 (2024)","DOI":"10.1109\/CVPR52733.2024.00366"},{"key":"18_CR62","doi-asserted-by":"crossref","unstructured":"Zhu, L., Chen, T., Ji, D., Ye, J., Liu, J.: LLaFS: when large language models meet few-shot segmentation. In: CVPR, pp. 3065\u20133075 (2024)","DOI":"10.1109\/CVPR52733.2024.00296"},{"key":"18_CR63","doi-asserted-by":"crossref","unstructured":"Zhu, L., Chen, T., Yin, J., See, S., Liu, J.: Addressing background context bias in few-shot segmentation through iterative modulation. In: CVPR, pp. 3370\u20133379 (2024)","DOI":"10.1109\/CVPR52733.2024.00324"},{"key":"18_CR64","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: Not all features matter: enhancing few-shot clip with adaptive prior refinement. In: ICCV, pp. 2605\u20132615 (2023)","DOI":"10.1109\/ICCV51070.2023.00246"},{"key":"18_CR65","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Wang, S., Xin, T., Zhang, H.: Few-shot medical image segmentation via a region-enhanced prototypical transformer. In: MICCAI, pp. 271\u2013280 (2023)","DOI":"10.1007\/978-3-031-43901-8_26"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-12840-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:22:43Z","timestamp":1767324163000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-12840-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032128393","9783032128409"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-12840-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"DAGM German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Freiburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"47","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dagm-gcpr.de\/year\/2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}