{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:05:23Z","timestamp":1753891523977,"version":"3.41.2"},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T00:00:00Z","timestamp":1687305600000},"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>Establishing the relationship between a limited number of samples and segmented objects in diverse scenarios is the primary challenge in few-shot segmentation. However, many previous works overlooked the crucial support-query set interaction and the deeper information that needs to be explored. This oversight can lead to model failure when confronted with complex scenarios, such as ambiguous boundaries. To solve this problem, a duplex network that utilizes the suppression and focus concept is proposed to effectively suppress the background and focus on the foreground. Our network includes dynamic convolution to enhance the support-query interaction and a prototype match structure to fully extract information from support and query. The proposed model is called dynamic prototype mixture convolutional networks (DPMC). To minimize the impact of redundant information, we have incorporated a hybrid attentional module called double-layer attention augmented convolutional module (DAAConv) into DPMC. This module enables the network to concentrate more on foreground information. Our experiments on PASCAL-5i and COCO-20i datasets suggested that DPMC and DAAConv outperform traditional prototype-based methods by up to 5\u20138% on average.<\/jats:p>","DOI":"10.3389\/fnbot.2023.1206189","type":"journal-article","created":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T08:06:40Z","timestamp":1687334800000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Few-shot segmentation with duplex network and attention augmented module"],"prefix":"10.3389","volume":"17","author":[{"given":"Sifu","family":"Zeng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yudi","family":"Ruan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,6,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2202.07231","article-title":"Few-shot semantic segmentation via mask aggregation","author":"Ao","year":"2022","journal-title":"arXiv:2202.07231."},{"key":"B2","first-page":"3286","article-title":"\u201cAttention augmented convolutional networks,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Bello","year":"2019"},{"key":"B3","first-page":"13979","article-title":"\u201cFew-shot segmentation without meta-learning: a good transductive inference is all you need?,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Boudiaf","year":"2021"},{"key":"B4","first-page":"357","article-title":"\u201cCrossvit: cross-attention multi-scale vision transformer for image classification,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Chen","year":"2021"},{"key":"B5","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.05587","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"","journal-title":"arXiv:1412.7062."},{"key":"B7","first-page":"3640","article-title":"\u201cAttention to scale: Scale-aware semantic image segmentation,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Chen","year":"2016"},{"key":"B8","first-page":"2393","article-title":"\u201cContext contrasted feature and gated multi-scale aggregation for scene segmentation,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Ding","year":"2018"},{"key":"B9","article-title":"\u201cFew-shot semantic segmentation with prototype learning,\u201d","volume-title":"Proceedings of the British Machine Vision Conference 2018.","author":"Dong","year":"2018"},{"key":"B10","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2009","journal-title":"Int. J. Comput. Vis."},{"key":"B11","first-page":"3146","article-title":"\u201cDual attention network for scene segmentation,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Fu","year":"2019"},{"key":"B12","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/978-3-319-10584-0_20","article-title":"\u201cSimultaneous detection and segmentation,\u201d","volume-title":"Proceedings of the Computer Vision\u2013ECCV 2014: 13th European Conference: Springer","author":"Hariharan","year":"2014"},{"key":"B13","first-page":"4003","article-title":"\u201cStrip pooling: rethinking spatial pooling for scene parsing,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hou","year":"2020"},{"key":"B14","first-page":"7132","article-title":"\u201cSqueeze-and-excitation networks,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Hu","year":"2018"},{"key":"B15","doi-asserted-by":"publisher","first-page":"3037","DOI":"10.1007\/s00500-022-07483-0","article-title":"Image colorization using deep convolutional auto-encoder with multi-skip connections","volume":"27","author":"Jin","year":"2023","journal-title":"Soft Comput."},{"key":"B16","doi-asserted-by":"publisher","first-page":"901018","DOI":"10.3389\/fbioe.2022.901018","article-title":"Prediction of protein secondary structure based on an improved channel attention and multiscale convolution module","volume":"10","author":"Jin","year":"","journal-title":"Front. Bioeng. Biotechnol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"962170","DOI":"10.3389\/fnbot.2022.962170","article-title":"Editorial: recent advances in artificial neural networks and embedded systems for multi-source image fusion","volume":"16","author":"Jin","year":"","journal-title":"Front. Neurorobot."},{"key":"B18","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1049\/ipr2.12668","article-title":"An unsupervised multi-focus image fusion method based on Transformer and U-Net","volume":"17","author":"Jin","year":"","journal-title":"IET Image Process."},{"key":"B19","first-page":"8334","article-title":"\u201cAdaptive prototype learning and allocation for few-shot segmentation,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li","year":"2021"},{"key":"B20","first-page":"9167","article-title":"\u201cExpectation-maximization attention networks for semantic segmentation,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Li","year":"2019"},{"key":"B21","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","article-title":"\u201cMicrosoft coco: common objects in context,\u201d","volume-title":"Proceedings of the Computer Vision-ECCV 2014: 13th European Conference","author":"Lin","year":"2014"},{"key":"B22","first-page":"11553","article-title":"\u201cDynamic prototype convolution network for few-shot semantic segmentation,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Liu","year":"2022"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1520","DOI":"10.48550\/arXiv.1710.01020","article-title":"Learning affinity via spatial propagation networks","volume":"30","author":"Liu","year":"2017","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"B24","doi-asserted-by":"publisher","first-page":"3140","DOI":"10.1007\/s11263-022-01677-7","article-title":"CRCNet: few-shot segmentation with cross-reference and region-global conditional networks","volume":"130","author":"Liu","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"B25","first-page":"10012","article-title":"\u201cSwin transformer: hierarchical vision transformer using shifted windows,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Liu","year":"2021"},{"key":"B26","doi-asserted-by":"publisher","first-page":"3431","DOI":"10.1109\/CVPR.2015.7298965","article-title":"\u201cFully convolutional networks for semantic segmentation,\u201d","author":"Long","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B27","first-page":"8721","article-title":"\u201cSimpler is better: few-shot semantic segmentation with classifier weight transformer,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Lu","year":"2021"},{"key":"B28","first-page":"6941","article-title":"\u201cHypercorrelation squeeze for few-shot segmentation,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Min","year":"2021"},{"key":"B29","first-page":"622","article-title":"\u201cFeature weighting and boosting for few-shot segmentation,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Nguyen","year":"2019"},{"key":"B30","doi-asserted-by":"publisher","first-page":"106083","DOI":"10.1016\/j.compbiomed.2022.106083","article-title":"Attention UW-Net: a fully connected model for automatic segmentation and annotation of chest X-ray","volume":"150","author":"Pal","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"B31","article-title":"\u201cConditional networks for few-shot semantic segmentation,\u201d","volume-title":"Proceedings of the 6th International Conference on Learning Representations.","author":"Rakelly","year":"2018"},{"key":"B32","first-page":"234","article-title":"\u201cU-net: convolutional networks for biomedical image segmentation,\u201d","volume-title":"Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference","author":"Ronneberger","year":"2015"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1709.03410","article-title":"One-shot learning for semantic segmentation","author":"Shaban","year":"2017","journal-title":"arXiv:1709.03410."},{"key":"B34","first-page":"7262","article-title":"\u201cSegmenter: transformer for semantic segmentation,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Strudel","year":"2021"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1109\/TPAMI.2020.3013717","article-title":"Prior guided feature enrichment network for few-shot segmentation","volume":"44","author":"Tian","year":"2020","journal-title":"IEEE Trans. Pattern. Anal. Mach. Intell."},{"key":"B36","doi-asserted-by":"publisher","first-page":"4477","DOI":"10.3390\/s22124477","article-title":"Multiple-attention mechanism network for semantic segmentation","volume":"22","author":"Wang","year":"2022","journal-title":"Sensors"},{"key":"B37","first-page":"9196","article-title":"\u201cPANet: few-shot image semantic segmentation with prototype alignment,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Wang","year":"2019"},{"key":"B38","first-page":"568","article-title":"\u201cPyramid vision transformer: a versatile backbone for dense prediction without convolutions,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Wang","year":"2021"},{"key":"B39","first-page":"7794","article-title":"\u201cNon-local neural networks,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Wang","year":"2018"},{"key":"B40","doi-asserted-by":"publisher","first-page":"102459","DOI":"10.1016\/j.media.2022.102459","article-title":"SSA-Net: Spatial self-attention network for COVID-19 pneumonia infection segmentation with semi-supervised few-shot learning","volume":"79","author":"Wang","year":"2022","journal-title":"Med. Image Anal."},{"key":"B41","first-page":"3","article-title":"\u201cCbam: convolutional block attention module,\u201d","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Woo","year":"2018"},{"key":"B42","doi-asserted-by":"publisher","first-page":"3319","DOI":"10.1007\/s10489-021-02603-z","article-title":"FPANet: feature pyramid aggregation network for real-time semantic segmentation","volume":"52","author":"Wu","year":"2022","journal-title":"Appl. Intell."},{"key":"B43","first-page":"517","article-title":"\u201cLearning meta-class memory for few-shot semantic segmentation,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Wu","year":"2021"},{"key":"B44","doi-asserted-by":"publisher","first-page":"12077","DOI":"10.48550\/arXiv.2105.15203","article-title":"SegFormer: simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"B45","doi-asserted-by":"publisher","first-page":"5475","DOI":"10.1109\/CVPR46437.2021.00543","article-title":"\u201cScale-aware graph neural network for few-shot semantic segmentation\u201d","author":"Xie","year":"2021"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-022-09452-x","article-title":"Medical image segmentation model based on triple gate MultiLayer perceptron","volume":"12","author":"Yan","year":"2022","journal-title":"Sci. Rep."},{"key":"B47","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1007\/978-3-030-58598-3_45","article-title":"\u201cPrototype mixture models for few-shot semantic segmentation,\u201d","volume-title":"Proceeding of the Computer Vision\u2013ECCV 2020: 16th European Conference","author":"Yang","year":"2020"},{"key":"B48","first-page":"8312","article-title":"\u201cSelf-guided and cross-guided learning for few-shot segmentation,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhang","year":"2021"},{"key":"B49","first-page":"5217","article-title":"\u201cCanet: class-agnostic segmentation networks with iterative refinement and attentive few-shot learning,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhang","year":"2019"},{"key":"B50","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1007\/978-3-030-58604-1_20","article-title":"\u201cFeature pyramid transformer,\u201d","volume-title":"Proceedings of the Computer Vision-ECCV 2020: 16th European Conference","author":"Zhang","year":"2020"},{"key":"B51","first-page":"2881","article-title":"\u201cPyramid scene parsing network,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Zhao","year":"2017"},{"key":"B52","first-page":"6881","article-title":"\u201cRethinking semantic segmentation from a sequence-to-sequence perspective with transformers,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zheng","year":"2021"},{"key":"B53","first-page":"6688","article-title":"\u201cAn empirical study of spatial attention mechanisms in deep networks,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Zhu","year":"2019"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1206189\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T08:07:20Z","timestamp":1687334840000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1206189\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,21]]},"references-count":53,"alternative-id":["10.3389\/fnbot.2023.1206189"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2023.1206189","relation":{},"ISSN":["1662-5218"],"issn-type":[{"type":"electronic","value":"1662-5218"}],"subject":[],"published":{"date-parts":[[2023,6,21]]},"article-number":"1206189"}}