{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T11:17:12Z","timestamp":1770290232121,"version":"3.49.0"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>The objective of few-shot fine-grained learning is to identify subclasses within a primary class using a limited number of labeled samples. However, many current methodologies rely on the metric of singular feature, which is either global or local. In fine-grained image classification tasks, where the inter-class distance is small and the intra-class distance is big, relying on a singular similarity measurement can lead to the omission of either inter-class or intra-class information. We delve into inter-class information through global measures and tap into intra-class information via local measures. In this study, we introduce the Feature Fusion Similarity Network (FFSNet). This model employs global measures to accentuate the differences between classes, while utilizing local measures to consolidate intra-class data. Such an approach enables the model to learn features characterized by enlarge inter-class distances and reduce intra-class distances, even with a limited dataset of fine-grained images. Consequently, this greatly enhances the model's generalization capabilities. Our experimental results demonstrated that the proposed paradigm stands its ground against state-of-the-art models across multiple established fine-grained image benchmark datasets.<\/jats:p>","DOI":"10.3389\/fnbot.2023.1301192","type":"journal-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T03:15:40Z","timestamp":1699845340000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Feature fusion network based on few-shot fine-grained classification"],"prefix":"10.3389","volume":"17","author":[{"given":"Yajie","family":"Yang","sequence":"first","affiliation":[]},{"given":"Yuxuan","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Li","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Haitao","family":"Fu","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Chenlei","family":"Jin","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,11,9]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"4683","DOI":"10.1109\/TIP.2020.2973812","article-title":"The devil is in the channels: mutual-channel loss for fine-grained image classification","volume":"29","author":"Chang","year":"2020","journal-title":"IEEE Trans. Image Process"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1904.04232","article-title":"A closer look at few-shot classification","author":"Chen","year":"2020","journal-title":"arXiv"},{"key":"B3","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"\u201cImageNet: a large-scale hierarchical image database,\u201d","volume-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","author":"Deng","year":"2009"},{"key":"B4","doi-asserted-by":"crossref","first-page":"3722","DOI":"10.1109\/ICCV.2019.00382","article-title":"\u201cDiversity with cooperation: ensemble methods for few-shot classification,\u201d","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Dvornik","year":"2019"},{"key":"B5","article-title":"\u201cModel-agnostic meta-learning for fast adaptation of deep networks,\u201d","author":"Finn","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"B6","doi-asserted-by":"crossref","first-page":"4476","DOI":"10.1109\/CVPR.2017.476","article-title":"\u201cLook closer to see better: recurrent attention convolutional neural network for fine-grained image recognition,\u201d","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Fu","year":"2017"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.04043","article-title":"Few-shot learning with graph neural networks","author":"Garcia","year":"2018","journal-title":"arXiv"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.07108","article-title":"Recent advances in convolutional neural networks","author":"Gu","year":"2017","journal-title":"arXiv"},{"key":"B9","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"\u201cDeep residual learning for image recognition,\u201d","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He","year":"2016"},{"key":"B10","volume-title":"Meta-Learning in Computational Intelligence, Volume 358 of Studies in Computational Intelligence","author":"Jankowski","year":"2011"},{"key":"B11","article-title":"\u201cNovel dataset for fine-grained image categorization,\u201d","author":"Khosla","year":"2013","journal-title":"CVPR Workshop on Fine-Grained Visual Categorization"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","article-title":"ADAM: a method for stochastic optimization","author":"Kingma","year":"2017","journal-title":"arXiv"},{"key":"B13","doi-asserted-by":"crossref","first-page":"554","DOI":"10.1109\/ICCVW.2013.77","article-title":"\u201c3D object representations for fine-grained categorization,\u201d","volume-title":"2013 IEEE International Conference on Computer Vision Workshops","author":"Krause","year":"2013"},{"key":"B14","first-page":"2526","article-title":"\u201cOne-shot learning by inverting a compositional causal process,\u201d","author":"Lake","year":"2017","journal-title":"Advances in Neural Information Processing Systems 26 (NIPS 2013)"},{"key":"B15","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1903.12290","article-title":"Revisiting local descriptor based image-to-class measure for few-shot learning","author":"Li","year":"","journal-title":"arXiv"},{"key":"B17","doi-asserted-by":"publisher","first-page":"8642","DOI":"10.1609\/aaai.v33i01.33018642","article-title":"Distribution consistency based covariance metric networks for few-shot learning","volume":"33","author":"Li","year":"","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.10953","article-title":"A concise review of recent few-shot meta-learning methods","author":"Li","year":"2020","journal-title":"arXiv"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1109\/TIP.2020.3043128","article-title":"BSNet: bi-similarity network for few-shot fine-grained image classification","volume":"30","author":"Li","year":"2021","journal-title":"IEEE Trans. Image Process"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1707.09835","article-title":"Meta-SGD: learning to learn quickly for few-shot learning","author":"Li","year":"2017","journal-title":"arXiv"},{"key":"B21","doi-asserted-by":"crossref","first-page":"9250","DOI":"10.1109\/CVPR.2019.00948","article-title":"\u201cDense classification and implanting for few-shot learning,\u201d","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lifchitz","year":"2019"},{"key":"B22","doi-asserted-by":"crossref","first-page":"1449","DOI":"10.1109\/ICCV.2015.170","article-title":"\u201cBilinear CNN models for fine-grained visual recognition,\u201d","volume-title":"2015 IEEE International Conference on Computer Vision (ICCV)","author":"Lin","year":"2015"},{"key":"B23","doi-asserted-by":"publisher","first-page":"2749","DOI":"10.1109\/TMM.2019.2962310","article-title":"Partition-aware adaptive switching neural networks for post-processing in HEVC","volume":"22","author":"Lin","year":"2020","journal-title":"IEEE Trans. Multimedia"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2438","DOI":"10.1109\/TIP.2017.2683063","article-title":"Learning correspondence structures for person re-identification","volume":"26","author":"Lin","year":"","journal-title":"IEEE Trans. Image Process"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1109\/TPAMI.2016.2608884","article-title":"A tube-and-droplet-based approach for representing and analyzing motion trajectories","volume":"39","author":"Lin","year":"","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B26","doi-asserted-by":"publisher","first-page":"3224","DOI":"10.1109\/TVT.2019.2899972","article-title":"Fine-grained vehicle classification with channel max pooling modified CNNs","volume":"68","author":"Ma","year":"2019","journal-title":"IEEE Trans. Veh. Technol"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1306.5151","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1803.02999","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018","journal-title":"arXiv"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.12348","article-title":"A task-aware dual similarity network for fine-grained few-shot learning","author":"Qi","year":"2022","journal-title":"arXiv"},{"key":"B30","article-title":"\u201cOptimization as a model for few-shot learning,\u201d","author":"Ravi","year":"2017","journal-title":"ICLR"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1807.05960","article-title":"Meta-learning with latent embedding optimization","author":"Rusu","year":"2019","journal-title":"arXiv"},{"key":"B32","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2017.74","article-title":"\u201cGrad-CAM: visual explanations from deep networks via gradient-based localization,\u201d","volume-title":"2017 IEEE International Conference on Computer Vision (ICCV)","author":"Selvaraju","year":"2017"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2101.02141","article-title":"Integrated generalized zero-shot learning for fine-grained classification","author":"Shermin","year":"2021","journal-title":"arXiv"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.1556","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"arXiv"},{"key":"B35","article-title":"\u201cPrototypical networks for few-shot learning,\u201d","author":"Snell","year":"2017","journal-title":"Advances in Neural Information Processing Systems, Vol. 30"},{"key":"B36","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1109\/CVPR.2018.00131","article-title":"\u201cLearning to compare: relation network for few-shot learning,\u201d","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Sung","year":"2018"},{"key":"B37","article-title":"\u201cMatching networks for one shot learning,\u201d","author":"Vinyals","year":"2016","journal-title":"Advances in Neural Information Processing Systems, Vol. 29"},{"key":"B38","author":"Wah","year":"2011","journal-title":"The Caltech-UCSD Birds-200-2011 Dataset"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2109.05719","article-title":"Fine-grained few shot learning with foreground object transformation","author":"Wang","year":"2021","journal-title":"arXiv"},{"key":"B40","doi-asserted-by":"publisher","first-page":"6116","DOI":"10.1109\/TIP.2019.2924811","article-title":"Piecewise classifier mappings: learning fine-grained learners for novel categories with few examples","volume":"28","author":"Wei","year":"2019","journal-title":"IEEE Trans. Image Process"},{"key":"B41","doi-asserted-by":"publisher","first-page":"2911","DOI":"10.1609\/aaai.v36i3.20196","article-title":"Dual attention networks for few-shot fine-grained recognition","volume":"36","author":"Xu","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B42","doi-asserted-by":"publisher","first-page":"2736","DOI":"10.1109\/TMM.2017.2710803","article-title":"Picking neural activations for fine-grained recognition","volume":"179","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Multimedia"},{"key":"B43","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1109\/TMM.2017.2648498","article-title":"Diversified visual attention networks for fine-grained object classification","volume":"19","author":"Zhao","year":"2017","journal-title":"IEEE Trans. Multimedia"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1301192\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T21:44:55Z","timestamp":1730497495000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1301192\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,9]]},"references-count":43,"alternative-id":["10.3389\/fnbot.2023.1301192"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2023.1301192","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,9]]},"article-number":"1301192"}}