{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T04:34:56Z","timestamp":1783571696510,"version":"3.55.0"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T00:00:00Z","timestamp":1714694400000},"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>To efficiently capture feature information in tasks of fine-grained image classification, this study introduces a new network model for fine-grained image classification, which utilizes a hybrid attention approach. The model is built upon a hybrid attention module (MA), and with the assistance of the attention erasure module (EA), it can adaptively enhance the prominent areas in the image and capture more detailed image information. Specifically, for tasks involving fine-grained image classification, this study designs an attention module capable of applying the attention mechanism to both the channel and spatial dimensions. This highlights the important regions and key feature channels in the image, allowing for the extraction of distinct local features. Furthermore, this study presents an attention erasure module (EA) that can remove significant areas in the image based on the features identified; thus, shifting focus to additional feature details within the image and improving the diversity and completeness of the features. Moreover, this study enhances the pooling layer of ResNet50 to augment the perceptual region and the capability to extract features from the network\u2019s less deep layers. For the objective of fine-grained image classification, this study extracts a variety of features and merges them effectively to create the final feature representation. To assess the effectiveness of the proposed model, experiments were conducted on three publicly available fine-grained image classification datasets: Stanford Cars, FGVC-Aircraft, and CUB-200\u20132011. The method achieved classification accuracies of 92.8, 94.0, and 88.2% on these datasets, respectively. In comparison with existing approaches, the efficiency of this method has significantly improved, demonstrating higher accuracy and robustness.<\/jats:p>","DOI":"10.3389\/fnbot.2024.1391791","type":"journal-article","created":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T13:17:45Z","timestamp":1714742265000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Fine-grained image classification method based on hybrid attention module"],"prefix":"10.3389","volume":"18","author":[{"given":"Weixiang","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,5,3]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"6017","DOI":"10.1109\/TIP.2022.3205215","article-title":"Sr-gnn: spatial relation-aware graph neural network for fine-grained image categorization","volume":"31","author":"Bera","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"ref2","author":"Bojarski","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"241","DOI":"10.3724\/SP.J.1089.2021.18399","article-title":"Saliency enhanced hierarchical bilinear pooling for fine-grained image classification","volume":"33","author":"Chen","year":"2021","journal-title":"J. Comp. Aid. Desig. Comp. Graph."},{"key":"ref4","doi-asserted-by":"crossref","first-page":"6598","DOI":"10.1109\/ICCV.2019.00670","article-title":"Selective sparse sampling for fine-grained image recognition","volume-title":"2019 IEEE\/CVF international conference on computer vision (ICCV)","author":"Ding","year":"2019"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","volume-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"ref6","first-page":"7132","author":"Hu","year":"2018"},{"key":"ref7","article-title":"Spatial transformer networks","volume-title":"NeurIPS","author":"Jaderberg","year":"2015"},{"key":"ref8","article-title":"Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition","volume-title":"CVPR","author":"Jianlong","year":"2017"},{"key":"ref9","author":"Krause","year":"2013"},{"key":"ref10","first-page":"1106","author":"Krizhevsky","year":"2012"},{"key":"ref11","first-page":"1830","article-title":"Deep learning method for fine-grained image categorization","volume":"15","author":"Li","year":"2021","journal-title":"J. Front. Comp. Sci. Technol."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1007\/s00371-020-02052-8","article-title":"Fine-grained visual classification via multilayer bilinear pooling with object localization","volume":"38","author":"Li","year":"2021","journal-title":"Vis. Comput."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.3969\/j.issn.1000-1220.2021.05.030","article-title":"Fine-grained image classification with attention and bilinear networks","volume":"42","author":"Li","year":"2021","journal-title":"J. Chin. Comp. Syst."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1449","DOI":"10.48550\/arXiv.1504.07889","article-title":"Bilinear CNN models for fine-grained visual recognition[C]\/\/proceedings of the IEEE","author":"Lin","year":"2015","journal-title":"Internat. Conf. Comp. Vision"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1666","DOI":"10.1109\/CVPR.2015.7298775","article-title":"Deep lac: deep localization, alignment and classification for fine-grained recognition","volume-title":"2015 IEEE conference on computer vision and pattern recognition (CVPR)","author":"Lin","year":"2015"},{"key":"ref16","volume-title":"Global attention mechanism: Retain information to Enhance Channel-spatial interactions","author":"Liu","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.ins.2021.05.040","article-title":"Dual attention guided multi-scale CNN for fine-grained image classification","volume":"573","author":"Liu","year":"2021","journal-title":"Inf. Sci."},{"key":"ref18","volume-title":"Fine-grained visual classifica-tion of aircraft [OL]","author":"Maji","year":"2013"},{"key":"ref19","volume-title":"BAM: Bottleneck Attention Module","author":"Park","year":"2018"},{"key":"ref20","first-page":"815","article-title":"Facenet: a unified embedding for face recognition and clustering","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Schroff","year":"2015"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1145\/3394171.3413883","article-title":"Beyond the attention: distinguish the discriminative and confusable features for fine-grained image classification","volume-title":"Proceedings of the 28th ACM international conference on multimedia","author":"Shi","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.1556","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"Comp. Sci."},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01270-0_49","article-title":"Multi-attention multi-class constraint for fine-grained image recognition","volume-title":"Proceedings of the 2018 European conference on computer vision","author":"Sun","year":"2018"},{"key":"ref24","first-page":"480","article-title":"Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline)","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Sun","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2014","journal-title":"IEEE Comp. Soci."},{"key":"ref26","author":"Wah","year":"2011"},{"key":"ref27","first-page":"3","article-title":"CBAM: Convolutional block attention module","volume-title":"proceedings of the European conference on computer vision (ECCV)","author":"Woo","year":"2018"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01264-9_26","article-title":"Learning to navigate for fine-grained classification","volume-title":"ECCV","author":"Yang","year":"2018"},{"key":"ref29","first-page":"1","article-title":"Progressive co-attention network for fine-grained visual classification","volume-title":"Proceedings of the international conference on visual communications and image processing","author":"Zhang","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10590-1_54","article-title":"Part-based r-cnns or fine-grained category detection","author":"Zhang","year":"2014","journal-title":"Lect. Notes Comput. Sci"},{"key":"ref31","first-page":"10","article-title":"Complementary attention method for fine-grained image classification","volume":"26","author":"Zhao","year":"2021","journal-title":"J. Image Graph."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"13130","DOI":"10.1609\/aaai.v34i07.7016","article-title":"Learning attentive pairwise interaction for fine-grained classification","volume":"34","author":"Zhuang","year":"2020","journal-title":"Proceed. AAAI Conf. Artif. Intellig."}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1391791\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T13:18:56Z","timestamp":1714742336000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1391791\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,3]]},"references-count":32,"alternative-id":["10.3389\/fnbot.2024.1391791"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2024.1391791","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,3]]},"article-number":"1391791"}}