{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T14:16:22Z","timestamp":1775312182265,"version":"3.50.1"},"reference-count":32,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T00:00:00Z","timestamp":1716940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSFC General Program","award":["62176215"],"award-info":[{"award-number":["62176215"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Few-shot learning, especially few-shot image classification (FSIC), endeavors to recognize new categories using only a handful of labeled images by transferring knowledge from a model trained on base categories. Despite numerous efforts to address the challenge of deficient transferability caused by the distribution shift between the base and new classes, the fundamental principles remain a subject of debate. In this paper, we elucidate why a decline in performance occurs and what information is transferred during the testing phase, examining it from a frequency spectrum perspective. Specifically, we adopt causality on the frequency space for FSIC. With our causal assumption, non-causal frequencies (e.g., background knowledge) act as confounders between causal frequencies (e.g., object information) and predictions. Our experimental results reveal that different frequency components represent distinct semantics, and non-causal frequencies adversely affect transferability, resulting in suboptimal performance. Subsequently, we suggest a straightforward but potent approach, namely the Frequency Spectrum Mask (FRSM), to weight the frequency and mitigate the impact of non-causal frequencies. Extensive experiments demonstrate that the proposed FRSM method significantly enhanced the transferability of the FSIC model across nine testing datasets.<\/jats:p>","DOI":"10.3390\/e26060473","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T08:15:54Z","timestamp":1717056954000},"page":"473","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Revisiting the Transferability of Few-Shot Image Classification: A Frequency Spectrum Perspective"],"prefix":"10.3390","volume":"26","author":[{"given":"Min","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science & Technology, Zhejiang University, Hangzhou 310027, China"},{"name":"School of Engineer, Westlake Univercity, Hangzhou 310030, China"}]},{"given":"Zhitao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Engineer, Westlake Univercity, Hangzhou 310030, China"}]},{"given":"Donglin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Engineer, Westlake Univercity, Hangzhou 310030, China"}]}],"member":"1968","published-online":{"date-parts":[[2024,5,29]]},"reference":[{"key":"ref_1","first-page":"1","article-title":"Generalizing from a few examples: A survey on few-shot learning","volume":"53","author":"Wang","year":"2020","journal-title":"ACM Comput. Surv."},{"key":"ref_2","unstructured":"Thrun, S., and Pratt, L. (2012). Learning to Learn, Springer Science & Business Media."},{"key":"ref_3","unstructured":"Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., and Huang, J.B. (2019, January 6\u20139). A closer look at few-shot classification. Proceedings of the International Conference on Learning Representations, ICLR, New Orleans, LA, USA."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, Z., Xu, H., Darrell, T., and Wang, X. (2021, January 10\u201317). Meta-baseline: Exploring simple meta-learning for few-shot learning. Proceedings of the International Conference on Computer Vision, ICCV, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00893"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J.B., and Isola, P. Rethinking few-shot image classification: A good embedding is all you need? In Proceedings of the European Conference on Computer Vision, ECCV, Glasgow, UK, 23\u201328 August 2020.","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A comprehensive survey on transfer learning","volume":"109","author":"Zhuang","year":"2020","journal-title":"Proc. IEEE"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1186\/s40537-016-0043-6","article-title":"A survey of transfer learning","volume":"3","author":"Weiss","year":"2016","journal-title":"J. Big Data"},{"key":"ref_9","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., and Wierstra, D. (2016, January 5\u201310). Matching networks for one shot learning. Proceedings of the Advances in Neural Information Processing Systems, NeurIPS, Barcelona, Spain."},{"key":"ref_10","unstructured":"Snell, J., Swersky, K., and Zemel, R.S. (2017, January 4\u20139). Prototypical networks for few-shot learning. Proceedings of the NeurIPS, Long Beach, CA, USA."},{"key":"ref_11","unstructured":"Finn, C., Abbeel, P., and Levine, S. (2017, January 6\u201311). Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. Proceedings of the ICML, Sydney, Australia."},{"key":"ref_12","unstructured":"Rusu, A.A., Rao, D., Sygnowski, J., Vinyals, O., Pascanu, R., Osindero, S., and Hadsell, R. (2019, January 6\u20139). Meta-Learning with Latent Embedding Optimization. Proceedings of the International Conference on Learning Representations, ICLR, New Orleans, LA, USA."},{"key":"ref_13","unstructured":"Raghu, A., Raghu, M., Bengio, S., and Vinyals, O. (2020, January 30). Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML. Proceedings of the International Conference on Learning Representations, ICLR, Addis Ababa, Ethiopia."},{"key":"ref_14","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref_15","unstructured":"Tseng, H.Y., Lee, H.Y., Huang, J.B., and Yang, M.-H. (2020, January 30). Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation. Proceedings of the International Conference on Learning Representations, ICLR, Addis Ababa, Ethiopia."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wang, H., and Deng, Z.H. (2021, January 19\u201327). Cross-Domain Few-Shot Classification via Adversarial Task Augmentation. Proceedings of the International Joint Conference on Artificial Intelligence, IJCAI, Montreal, QC, Canada.","DOI":"10.24963\/ijcai.2021\/149"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sun, J., Lapuschkin, S., Samek, W., Zhao, Y., Cheung, N.M., and Binder, A. (2021, January 10\u201315). Explanation-guided training for cross-domain few-shot classification. Proceedings of the International Conference on Pattern Recognition, ICPR, Milan, Italy.","DOI":"10.1109\/ICPR48806.2021.9412941"},{"key":"ref_18","unstructured":"Oh, J., Kim, S., Ho, N., Kim, J.H., Song, H., and Yun, S.Y. (December, January 28). Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty. Proceedings of the Advances in Neural Information Processing Systems, NeurIPS, New Orleans, LA, USA."},{"key":"ref_19","unstructured":"Islam, A., Chen, C.F.R., Panda, R., Karlinsky, L., Feris, R., and Radke, R.J. (2021, January 6\u201314). Dynamic distillation network for cross-domain few-shot recognition with unlabeled data. Proceedings of the Advances in Neural Information Processing Systems, NeurIPS, Virtual."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Long, Y., Zhang, Q., Zeng, B., Gao, L., Liu, X., Zhang, J., and Song, J. (2022, January 23\u201327). Frequency domain model augmentation for adversarial attack. Proceedings of the European Conference on Computer Vision, ECCV, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-19772-7_32"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Xu, K., Qin, M., Sun, F., Wang, Y., Chen, Y.K., and Ren, F. (2020, January 13\u201319). Learning in the frequency domain. Proceedings of the Computer Vision and Pattern Recognition, CVPR, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00181"},{"key":"ref_22","unstructured":"Yue, Z., Zhang, H., Sun, Q., and Hua, X.S. (2020, January 6\u201312). Interventional few-shot learning. Proceedings of the Advances in Neural Information Processing Systems, NeurIPS, Virtual."},{"key":"ref_23","unstructured":"Rajasegaran, J., Khan, S., Hayat, M., Khan, F.S., and Shah, M. (2021, January 22\u201325). Self-supervised knowledge distillation for few-shot learning. Proceedings of the British Machine Vision Conference, BMVC, Virtual."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., and Hospedales, T.M. (2018, January 18\u201322). Learning to compare: Relation network for few-shot learning. Proceedings of the Computer Vision and Pattern Recognition, CVPR, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref_25","unstructured":"Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., and Brendel, W. (2019, January 6\u20139). ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. Proceedings of the International Conference on Learning Representations, ICLR, New Orleans, LA, USA."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Xu, Q., Zhang, R., Zhang, Y., Wang, Y., and Tian, Q. (2021, January 20\u201325). A Fourier-based Framework for Domain Generalization. Proceedings of the Computer Vision and Pattern Recognition, CVPR, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01415"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Huang, J., Guan, D., Xiao, A., and Lu, S. (2021, January 20\u201325). Fsdr: Frequency space domain randomization for domain generalization. Proceedings of the Computer Vision and Pattern Recognition, CVPR, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00682"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Guo, Y., Codella, N.C., Karlinsky, L., Codella, J.V., Smith, J.R., Saenko, K., Rosing, T., and Feris, R. (2020, January 23\u201328). A Broader Study of Cross-Domain Few-Shot Learning. Proceedings of the European Conference on Computer Vision, ECCV, Glasgow, UK.","DOI":"10.1007\/978-3-030-58583-9_8"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"14938","DOI":"10.1109\/TPAMI.2023.3312125","article-title":"Libfewshot: A comprehensive library for few-shot learning","volume":"45","author":"Li","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1979","DOI":"10.1109\/TMM.2022.3141886","article-title":"Graph complemented latent representation for few-shot image classification","volume":"25","author":"Zhong","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"8225","DOI":"10.1109\/TMM.2022.3233442","article-title":"Graph neural networks with triple attention for few-shot learning","volume":"25","author":"Cheng","year":"2023","journal-title":"IEEE Trans. Multimed."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/26\/6\/473\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:50:37Z","timestamp":1760107837000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/26\/6\/473"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,29]]},"references-count":32,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["e26060473"],"URL":"https:\/\/doi.org\/10.3390\/e26060473","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,29]]}}}