{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:49:44Z","timestamp":1772207384896,"version":"3.50.1"},"reference-count":42,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2022,5,27]],"date-time":"2022-05-27T00:00:00Z","timestamp":1653609600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11971296"],"award-info":[{"award-number":["11971296"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Cross Domain Few-Shot Learning (CDFSL) has attracted the attention of many scholars since it is closer to reality. The domain shift between the source domain and the target domain is a crucial problem for CDFSL. The essence of domain shift is the marginal distribution difference between two domains which is implicit and unknown. So the empirical marginal distribution measurement is proposed, that is, WDMDS (Wasserstein Distance for Measuring Domain Shift) and MMDMDS (Maximum Mean Discrepancy for Measuring Domain Shift). Besides this, pre-training a feature extractor and fine-tuning a classifier are used in order to have a good generalization in CDFSL. Since the feature obtained by the feature extractor is high-dimensional and left-biased, the adaptive feature distribution transformation is proposed, to make the feature distribution of each sample be approximately Gaussian distribution. This approximate symmetric distribution improves image classification accuracy by 3% on average. In addition, the applicability of different classifiers for CDFSL is investigated, and the classification model should be selected based on the empirical marginal distribution difference between the two domains. The Task Adaptive Cross Domain Few-Shot Learning (TACDFSL) is proposed based on the above ideas. TACDFSL improves image classification accuracy by 3\u20139%.<\/jats:p>","DOI":"10.3390\/sym14061097","type":"journal-article","created":{"date-parts":[[2022,5,31]],"date-time":"2022-05-31T02:30:06Z","timestamp":1653964206000},"page":"1097","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["TACDFSL: Task Adaptive Cross Domain Few-Shot Learning"],"prefix":"10.3390","volume":"14","author":[{"given":"Qi","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Mathematics, College of Sciences, Shanghai University, Shanghai 200444, China"}]},{"given":"Yingluo","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Mathematics, College of Sciences, Shanghai University, Shanghai 200444, China"}]},{"given":"Zhijie","family":"Wen","sequence":"additional","affiliation":[{"name":"Department of Mathematics, College of Sciences, Shanghai University, Shanghai 200444, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,5,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Fan, Z., Yu, J.G., and Liang, Z. (2020, January 13\u201319). Fgn: Fully guided network for few-shot instance segmentation. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00919"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ganea, D.A., Boom, B., and Poppe, R. (2021, January 20\u201325). Incremental few-shot instance segmentation. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00124"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Simon, C., Koniusz, P., and Nock, R. (2020, January 13\u201319). Adaptive subspaces for few-shot learning. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00419"},{"key":"ref_4","unstructured":"Jeong, T., and Kim, H. (2020, January 6\u201312). OOD-MAML: Meta-learning for few-shot out-of-distribution detection and classification. Proceedings of the 2020 Conference on Neural Information Processing Systems, Online."},{"key":"ref_5","unstructured":"Zhao, Y., Wang, L., and Tian, Y. (2021, January 18\u201324). Few-shot neural architecture search. Proceedings of the 2021 International Conference on Machine Learning, Online."},{"key":"ref_6","unstructured":"Vinyals, O., Blundell, C., and Lillicrap, T. (2016, January 5\u201310). Matching networks for one shot learning. Proceedings of the Annual Conference on Neural Information Processing Systems, Barcelona, Spain."},{"key":"ref_7","unstructured":"Snell, J., Swersky, K., and Zemel, R. (2017, January 4\u20139). Prototypical networks for few-shot learning. Proceedings of the Annual Conference on Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., and Zhang, L. (2018, January 18\u201323). Learning to compare: Relation network for few-shot learning. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref_9","unstructured":"Garcia, V., and Bruna, J. (May, January 30). Few-shot learning with graph neural networks. Proceedings of the 6th International Conference on Learning Representation, Vancouver, BC, Canada."},{"key":"ref_10","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 2017 International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhong, X., Gu, C., and Huang, W. (2021, January 10\u201315). Complementing representation deficiency in few-shot image classification: A meta-learning approach. Proceedings of the 25th International Conference on Pattern Recognition, Milan, Italy.","DOI":"10.1109\/ICPR48806.2021.9412416"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Rajasegaran, J., Khan, S., and Hayat, M. (2020, January 13\u201319). An incremental task-agnostic meta-learning approach. Proceedings of the 2020 Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01360"},{"key":"ref_13","unstructured":"Sugandh, U., Khari, M., and Nigam, S. (2022). The integration of blockchain and IoT edge devices for smart agriculture: The challenges and use cases. Adv. Comput."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sugandh, U., Khari, M., and Nigam, S. (2022). How Blockchain Technology Can Transfigure the Indian Agriculture Sector: A Review. Handbook of Green Computing and Blockchain Technologies, CRC Press.","DOI":"10.1201\/9781003107507-6"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Srivastava, S., Khari, M., Crespo, R.G., Chaudhary, G., and Arora, P. (2021). Concepts and Real-Time Applications of Deep Learning, Springer International Publishing.","DOI":"10.1007\/978-3-030-76167-7"},{"key":"ref_16","unstructured":"Tseng, H.Y., and Lee, H.Y. (2020, January 26\u201330). Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation. Proceedings of the 8th International Conference on Learning Representations, Addis Ababa, Ethiopia."},{"key":"ref_17","unstructured":"Wah, C., Branson, S., and Welinder, P. (2011). The Caltech-UCSD Birds-200-2011 Dataset, California Institute of Technology."},{"key":"ref_18","unstructured":"Chen, W.Y., Liu, Y.C., and Kira, Z. (2019, January 6\u20139). A closer look at few-shot classification. Proceedings of the 7th International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Guo, Y., Codella, N.C., and Karlinsky, L. (2020, January 23\u201328). A broader study of cross-domain few-shot learning. Proceedings of the 2020 European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58583-9_8"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., and Socher, R. (2009, January 20\u201325). A large-scale hierarchical image database. Proceedings of the 2009 Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.3389\/fpls.2016.01419","article-title":"Using deep learning for image-based plant disease detection","volume":"7","author":"Mohanty","year":"2016","journal-title":"Front. Plant Sci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","article-title":"Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification","volume":"12","author":"Helber","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2018.161","article-title":"The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions","volume":"5","author":"Tschandl","year":"2018","journal-title":"Sci. Data"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., and LU, L. (2017, January 21\u201326). Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. Proceedings of the 2017 Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref_25","unstructured":"Rusu, A.A., Rao, D., and Sygnowski, J. (2019, January 6\u20139). Meta-learning with latent embedding optimization. Proceedings of the 7th International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_26","unstructured":"Vuorio, R., Sun, S.H., and Hu, H. (2019, January 8\u201314). Multimodal model-agnostic meta-learning via task-aware modulation. Proceedings of the 2019 Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_27","unstructured":"Tseng, H.Y., De, M.S., and Tremblay, J. (2020, January 7\u201310). Few-shot viewpoint estimation. Proceedings of the 31st British Machine Vision Virtual Conference, Online."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wang, Y.X., Girshick, R., and Hebert, M. (2018, January 18\u201322). Low-shot learning from imaginary data. Proceedings of the 2018 Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00760"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Alfassy, A., Karlinsky, L., and Aides, A. (2019, January 16\u201320). Laso: Label-set operations networks for multi-label few-shot learning. Proceedings of the 2019 Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00671"},{"key":"ref_30","unstructured":"Mangla, P., Kumari, N., and Sinha, A. (2022, January 4\u20138). Charting the right manifold: Manifold mixup for few-shot learning. Proceedings of the 2022 Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Hu, Y., Gripon, V., and Pateux, S. (2021, January 3\u20137). Leveraging the feature distribution in transfer-based few-shot learning. Proceedings of the 2021 International Conference on Learning Representations, Vienna, Austria.","DOI":"10.1007\/978-3-030-86340-1_39"},{"key":"ref_32","unstructured":"Yang, S., Liu, L., and Xu, M. (2021, January 3\u20137). Free lunch for few-shot learning: Distribution calibration. Proceedings of the 2021 International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_33","unstructured":"Phoo, C.P., and Hariharan, B. (2021, January 3\u20137). Self-training for few-shot transfer across extreme task differences. Proceedings of the 2021 International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Wang, A., Liu, C., and Xue, D. (2021). Hyperspectral Image Classification Based on Cross-Scene Adaptive Learning. Symmetry, 13.","DOI":"10.3390\/sym13101878"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Hsu, H.K., Yao, C.H., and Tsai, Y.H. (2020, January 2\u20135). Progressive domain adaptation for object detection. Proceedings of the 2020 Winter Conference on Applications of Computer Vision, Snowmass Village, CO, USA.","DOI":"10.1109\/WACV45572.2020.9093358"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wang, F., Chai, G., and Li, Q. (2022). An Efficient Deep Unsupervised Domain Adaptation for Unknown Malware Detection. Symmetry, 14.","DOI":"10.3390\/sym14020296"},{"key":"ref_37","unstructured":"Fickinger, A., Cohen, S., and Russell, S. (2022, January 25\u201329). Cross-Domain Imitation Learning via Optimal Transport. Proceedings of the 2022 International Conference on Learning Representations, Online."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1023\/A:1026543900054","article-title":"The earth mover\u2019s distance as a metric for image retrieval","volume":"40","author":"Rubner","year":"2000","journal-title":"Int. J. Comput. Vis."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"e49","DOI":"10.1093\/bioinformatics\/btl242","article-title":"Integrating structured biological data by kernel maximum mean discrepancy","volume":"22","author":"Borgwardt","year":"2006","journal-title":"Bioinformatics"},{"key":"ref_40","unstructured":"Gretton, A., Sejdinovic, D., and Strathmann, H. (2021, January 3\u20138). Optimal kernel choice for large-scale two-sample tests. Proceedings of the 2012 Annual Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1109\/TPAMI.2011.114","article-title":"Domain transfer multiple kernel learning","volume":"34","author":"Duan","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1111\/j.2517-6161.1964.tb00553.x","article-title":"An analysis of transformations","volume":"26","author":"Box","year":"1964","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/6\/1097\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:19:29Z","timestamp":1760138369000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/6\/1097"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,27]]},"references-count":42,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2022,6]]}},"alternative-id":["sym14061097"],"URL":"https:\/\/doi.org\/10.3390\/sym14061097","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,27]]}}}