{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T05:19:34Z","timestamp":1743052774408,"version":"3.40.3"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729669"},{"type":"electronic","value":"9783031729676"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-3-031-72967-6_17","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:05:00Z","timestamp":1730574300000},"page":"303-320","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic-Guided Robustness Tuning for\u00a0Few-Shot Transfer Across Extreme Domain Shift"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4378-0556","authenticated-orcid":false,"given":"Kangyu","family":"Xiao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1822-3731","authenticated-orcid":false,"given":"Zilei","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2906-8514","authenticated-orcid":false,"given":"Junjie","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"17_CR1","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_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":"17_CR3","unstructured":"Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., Huang, J.B.: A closer look at few-shot classification. arXiv preprint arXiv:1904.04232 (2019)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Chen, W., Si, C., Zhang, Z., Wang, L., Wang, Z., Tan, T.: Semantic prompt for few-shot image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23581\u201323591 (2023)","DOI":"10.1109\/CVPR52729.2023.02258"},{"key":"17_CR5","unstructured":"Codella, N., et al.: Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (ISIC). arXiv preprint arXiv:1902.03368 (2019)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 702\u2013703 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Das, R., Wang, Y.X., Moura, J.M.: On the importance of distractors for few-shot classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9030\u20139040 (2021)","DOI":"10.1109\/ICCV48922.2021.00890"},{"key":"17_CR8","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":"17_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"17_CR10","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126\u20131135. PMLR (2017)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Fu, Y., Fu, Y., Jiang, Y.G.: Meta-fdmixup: cross-domain few-shot learning guided by labeled target data. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 5326\u20135334 (2021)","DOI":"10.1145\/3474085.3475655"},{"key":"17_CR12","unstructured":"Fu, Y., Xie, Y., Fu, Y., Chen, J., Jiang, Y.G.: Wave-san: wavelet based style augmentation network for cross-domain few-shot learning. arXiv preprint arXiv:2203.07656 (2022)"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Fu, Y., Xie, Y., Fu, Y., Jiang, Y.-G.: StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24575\u201324584 (2023)","DOI":"10.1109\/CVPR52729.2023.02354"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Gao, P., et al.: Clip-adapter: better vision-language models with feature adapters. Int. J. Comput. Vision 1\u201315 (2023)","DOI":"10.1007\/s11263-023-01891-x"},{"key":"17_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1007\/978-3-030-58583-9_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Guo","year":"2020","unstructured":"Guo, Y., et al.: A broader study of cross-domain few-shot learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 124\u2013141. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58583-9_8"},{"key":"17_CR16","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"},{"issue":"7","key":"17_CR17","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","volume":"12","author":"P Helber","year":"2019","unstructured":"Helber, P., Bischke, B., Dengel, A., Borth, D.: Eurosat: a novel dataset and deep learning benchmark for land use and land cover classification. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 12(7), 2217\u20132226 (2019)","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"17_CR18","unstructured":"Hendrycks, D., Mu, N., Cubuk, E.D., Zoph, B., Gilmer, J., Lakshminarayanan, B.: Augmix: a simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:1912.02781 (2019)"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Hong, T., Guo, X., Ma, J.: Itmix: image-text mix augmentation for transferring clip to image classification. In: 2022 16th IEEE International Conference on Signal Processing (ICSP), vol.\u00a01, pp. 129\u2013133. IEEE (2022)","DOI":"10.1109\/ICSP56322.2022.9965292"},{"key":"17_CR20","unstructured":"Hou, R., Chang, H., Ma, B., Shan, S., Chen, X.: Cross attention network for few-shot classification. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"17_CR21","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799. PMLR (2019)"},{"key":"17_CR22","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"17_CR23","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-031-20044-1_2","volume-title":"European Conference on Computer Vision","author":"Y Hu","year":"2022","unstructured":"Hu, Y., Ma, A.J.: Adversarial feature augmentation for cross-domain few-shot classification. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13680, pp. 20\u201337. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20044-1_2"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhou, A., Ling, Z., Cai, M., Wang, H., Lee, Y.J.: A sentence speaks a thousand images: domain generalization through distilling clip with language guidance. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11685\u201311695 (2023)","DOI":"10.1109\/ICCV51070.2023.01073"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Jang, J., Kong, C., Jeon, D., Kim, S., Kwak, N.: Unifying vision-language representation space with single-tower transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 980\u2013988 (2023)","DOI":"10.1609\/aaai.v37i1.25178"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: Maple: multi-modal prompt learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19113\u201319122 (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Wasim, S.T., Naseer, M., Khan, S., Yang, M.H., Khan, F.S.: Self-regulating prompts: foundational model adaptation without forgetting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15190\u201315200 (2023)","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"17_CR28","unstructured":"Kim, J.H., Choo, W., Song, H.O.: Puzzle mix: exploiting saliency and local statistics for optimal mixup. In: International Conference on Machine Learning, pp. 5275\u20135285. PMLR (2020)"},{"key":"17_CR29","unstructured":"Kurakin, A., et al.: Remixmatch: semi-supervised learning with distribution matching and augmentation anchoring (2020)"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, Z., Gao, Y., Hu, X.: Exploring high-quality target domain information for unsupervised domain adaptive semantic segmentation. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5237\u20135245 (2022)","DOI":"10.1145\/3503161.3548114"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, Z., Hu, X.: Learning intact features by erasing-inpainting for few-shot classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 8401\u20138409 (2021)","DOI":"10.1609\/aaai.v35i9.17021"},{"key":"17_CR32","unstructured":"Li, J., Zhang, Y., Wang, Z., Tu, K., Hou, S.: Probabilistic contrastive learning for domain adaptation. arXiv preprint arXiv:2111.06021 (2021)"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Liang, H., Zhang, Q., Dai, P., Lu, J.: Boosting the generalization capability in cross-domain few-shot learning via noise-enhanced supervised autoencoder. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9424\u20139434 (2021)","DOI":"10.1109\/ICCV48922.2021.00929"},{"key":"17_CR34","unstructured":"Liu, B., Zhao, Z., Li, Z., Jiang, J., Guo, Y., Ye, J.: Feature transformation ensemble model with batch spectral regularization for cross-domain few-shot classification. arXiv preprint arXiv:2005.08463 (2020)"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Learning a few-shot embedding model with contrastive learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 8635\u20138643 (2021)","DOI":"10.1609\/aaai.v35i10.17047"},{"key":"17_CR36","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"17_CR37","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.3389\/fpls.2016.01419","volume":"7","author":"SP Mohanty","year":"2016","unstructured":"Mohanty, S.P., Hughes, D.P., Salath\u00e9, M.: Using deep learning for image-based plant disease detection. Front. Plant Sci. 7, 1419 (2016)","journal-title":"Front. Plant Sci."},{"key":"17_CR38","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"issue":"10","key":"17_CR39","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2009","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2009)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"17_CR40","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"17_CR41","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR42","unstructured":"So, J., Oh, C., Shin, M., Song, K.: Multi-modal mixup for robust fine-tuning. arXiv preprint arXiv:2203.03897, vol. 3 (2022)"},{"key":"17_CR43","unstructured":"Song, K., Ma, H., Zou, B., Zhang, H., Huang, W.: FD-align: feature discrimination alignment for fine-tuning pre-trained models in few-shot learning. arXiv preprint arXiv:2310.15105 (2023)"},{"key":"17_CR44","unstructured":"Verma, V., et al.: Manifold mixup: better representations by interpolating hidden states. In: International Conference on Machine Learning, pp. 6438\u20136447. PMLR (2019)"},{"key":"17_CR45","doi-asserted-by":"crossref","unstructured":"Wang, H., Deng, Z.H.: Cross-domain few-shot classification via adversarial task augmentation. arXiv preprint arXiv:2104.14385 (2021)","DOI":"10.24963\/ijcai.2021\/149"},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: Chestx-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2097\u20132106 (2017)","DOI":"10.1109\/CVPR.2017.369"},{"key":"17_CR47","unstructured":"Wang, Z., Liang, J., He, R., Xu, N., Wang, Z., Tan, T.: Improving zero-shot generalization for clip with synthesized prompts. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3032\u20133042 (2023)"},{"key":"17_CR48","unstructured":"Wang, Z., Liang, J., Sheng, L., He, R., Wang, Z., Tan, T.: A hard-to-beat baseline for training-free clip-based adaptation. arXiv preprint arXiv:2402.04087 (2024)"},{"key":"17_CR49","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, J., Ni, B., Li, T., Wang, C., Tian, Q., Zhang, W.: Adversarial domain adaptation with domain mixup. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 6502\u20136509 (2020)","DOI":"10.1609\/aaai.v34i04.6123"},{"key":"17_CR50","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"17_CR51","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)"},{"key":"17_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Prompt, generate, then cache: cascade of foundation models makes strong few-shot learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15211\u201315222 (2023)","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"17_CR53","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1007\/978-3-031-19833-5_29","volume-title":"European Conference on Computer Vision","author":"R Zhang","year":"2022","unstructured":"Zhang, R., et al.: Tip-adapter: training-free adaption of clip for few-shot classification. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13695, pp. 493\u2013510. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_29"},{"key":"17_CR54","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"17_CR55","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"17_CR56","doi-asserted-by":"crossref","unstructured":"Zhuo, L., Fu, Y., Chen, J., Cao, Y., Jiang, Y.G.: TGDM: target guided dynamic mixup for cross-domain few-shot learning. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 6368\u20136376 (2022)","DOI":"10.1145\/3503161.3548052"}],"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\/978-3-031-72967-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:15:58Z","timestamp":1730574958000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72967-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031729669","9783031729676"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72967-6_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 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"}}]}}