{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T18:47:48Z","timestamp":1780598868756,"version":"3.54.1"},"reference-count":59,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T00:00:00Z","timestamp":1698019200000},"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. Comput. Neurosci."],"abstract":"<jats:p>The current semantic segmentation algorithms suffer from encoding feature distortion and small object feature loss. Context information exchange can effectively address the feature distortion problem, but it has the issue of fixed spatial range. Maintaining the input feature resolution can reduce the loss of small object information but would slow down the network\u2019s operation speed. To tackle these problems, we propose a lightweight semantic segmentation network with configurable context and small object attention (CCSONet). CCSONet includes a long-short distance configurable context feature enhancement module (LSCFEM) and a small object attention decoding module (SOADM). The LSCFEM differs from the regular context exchange module by configuring long and short-range relevant features for the current feature, providing a broader and more flexible spatial range. The SOADM enhances the features of small objects by establishing correlations among objects of the same category, avoiding the introduction of redundancy issues caused by high-resolution features. On the Cityscapes and Camvid datasets, our network achieves the accuracy of 76.9 mIoU and 73.1 mIoU, respectively, while maintaining speeds of 87 FPS and 138 FPS. It outperforms other lightweight semantic segmentation algorithms in terms of accuracy.<\/jats:p>","DOI":"10.3389\/fncom.2023.1280640","type":"journal-article","created":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T07:24:45Z","timestamp":1698045885000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Lightweight semantic segmentation network with configurable context and small object attention"],"prefix":"10.3389","volume":"17","author":[{"given":"Chunyu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengdong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinzhao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,10,23]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.patrec.2008.04.005","article-title":"Semantic object classes in video: a high-definition ground truth database","volume":"30","author":"Brostow","year":"2009","journal-title":"Pattern Recogn. Lett."},{"key":"ref2","first-page":"3547","volume-title":"Scene labeling with lstm recurrent neural networks. Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Byeon","year":"2015"},{"key":"ref3","first-page":"3552","volume-title":"Hardnet: a low memory traffic network. Proceedings of the IEEE\/CVF international conference on computer vision","author":"Chao","year":"2019"},{"key":"ref4","first-page":"1","article-title":"Linknet: exploiting encoder representations for efficient semantic segmentation","author":"Chaurasia","year":"2017"},{"key":"ref5","first-page":"4545","volume-title":"Semantic image segmentation with task-specific edge detection using cnns and a discriminatively trained domain transform. Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Chen","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"23194","DOI":"10.1109\/TITS.2022.3194931","article-title":"Light transport induced domain adaptation for semantic segmentation in thermal infrared urban scenes","volume":"23","author":"Chen","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref7","article-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs","author":"Chen","year":"2014","journal-title":"ar Xiv preprint ar Xiv: 1412.7062"},{"key":"ref8","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":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref9","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"ar Xiv preprint ar Xiv: 1706.05587"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"5033","DOI":"10.1007\/s12652-020-02066-z","article-title":"Research of improving semantic image segmentation based on a feature fusion model","volume":"13","author":"Chen","year":"2020","journal-title":"J. Ambient. Intell. Humaniz. Comput."},{"key":"ref11","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","volume-title":"Computer Vision \u2013 ECCV 2018. ECCV 2018. Lecture Notes in Computer Science()","author":"Chen","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"5500","DOI":"10.3390\/s20195500","article-title":"A novel post-processing method based on a weighted composite filter for enhancing semantic segmentation results","volume":"20","author":"Cheng","year":"2020","journal-title":"Sensors"},{"key":"ref13","first-page":"3213","volume-title":"The cityscapes dataset for semantic urban scene understanding. Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Cordts","year":"2016"},{"key":"ref14","first-page":"764","volume-title":"Deformable convolutional networks. Proceedings of the IEEE international conference on computer vision","author":"Dai","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"4350","DOI":"10.1109\/TITS.2019.2939832","article-title":"Restricted deformable convolution-based road scene semantic segmentation using surround view cameras","volume":"21","author":"Deng","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref16","first-page":"1","volume-title":"Multi-scale feature fusion: learning better semantic segmentation for road pothole detection. 2021 IEEE international conference on autonomous systems (ICAS)","author":"Fan","year":"2021"},{"key":"ref17","first-page":"3146","volume-title":"Dual attention network for scene segmentation. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Fu","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"2643","DOI":"10.1109\/TIP.2018.2888701","article-title":"Small object sensitive segmentation of urban street scene with spatial adjacency between object classes","volume":"28","author":"Guo","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"7200","DOI":"10.1109\/TIP.2021.3102509","article-title":"Mgseg: multiple granularity-based real-time semantic segmentation network","volume":"30","author":"He","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"ref21","first-page":"7132","volume-title":"Squeeze-and-excitation networks. Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Hu","year":"2018"},{"key":"ref22","first-page":"4700","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2023.3234257","article-title":"Edge detection guide network for semantic segmentation of remote-sensing images","volume":"20","author":"Jin","year":"2023","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref24","first-page":"1","volume-title":"Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks. Proceedings of the IEEE conference on computer vision and pattern recognition workshops","author":"Kampffmeyer","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"140305","DOI":"10.1007\/s11432-022-3599-y","article-title":"MFVNet: a deep adaptive fusion network with multiple field-of-views for remote sensing image semantic segmentation","volume":"66","author":"Li","year":"2023","journal-title":"SCIENCE CHINA Inf. Sci."},{"key":"ref28","first-page":"1222","volume-title":"Perceptual generative adversarial networks for small object detection. Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Li","year":"2017"},{"key":"ref29","volume-title":"Pyramid attention network for semantic segmentation","author":"Li","year":"2018"},{"key":"ref30","first-page":"9522","volume-title":"Dfanet: deep feature aggregation for real-time semantic segmentation. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Li","year":"2019"},{"key":"ref31","article-title":"Convolutional neural networks with intra-layer recurrent connections for scene labeling","volume":"28","author":"Liang","year":"2015","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"ref32","first-page":"603","article-title":"Multi-scale Context Intertwining for Semantic Segmentation","volume-title":"Computer Vision \u2013 ECCV 2018. ECCV 2018. Lecture Notes in Computer Science()","author":"Lin","year":"2018"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46448-0_2","article-title":"Ssd: single shot multibox detector","volume-title":"Computer Vision \u2013 ECCV 2016. ECCV 2016. Lecture Notes in Computer Science()","author":"Liu","year":"2016"},{"key":"ref35","first-page":"8759","volume-title":"Path aggregation network for instance segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Liu","year":"2018"},{"key":"ref36","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015"},{"key":"ref37","first-page":"77","volume-title":"Optimizing data augmentation for semantic segmentation on small-scale dataset. Proceedings of the 2nd international conference on control and computer vision","author":"Ma","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2021.3097148","article-title":"Fact Seg: foreground activation-driven small object semantic segmentation in large-scale remote sensing imagery","volume":"60","author":"Ma","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref39","first-page":"217","volume-title":"Detecting small signs from large images. 2017 IEEE international conference on information reuse and integration (IRI)","author":"Meng","year":"2017"},{"key":"ref41","article-title":"Enet: a deep neural network architecture for real-time semantic segmentation","author":"Paszke","year":"2016","journal-title":"ar Xiv preprint ar Xiv: 1606.02147"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-Net: convolutional networks for biomedical image segmentation","volume-title":"Medical image computing and computer-assisted intervention \u2013 MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science()","author":"Ronneberger","year":"2015"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"6289","DOI":"10.1109\/TPAMI.2022.3211171","article-title":"Small-object sensitive segmentation using across feature map attention","volume":"45","author":"Sang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"872","DOI":"10.3390\/rs12050872","article-title":"Multi-scale adaptive feature fusion network for semantic segmentation in remote sensing images","volume":"12","author":"Shang","year":"2020","journal-title":"Remote Sens."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"7880","DOI":"10.1109\/TCSVT.2022.3187664","article-title":"Urban LF: a comprehensive light field dataset for semantic segmentation of urban scenes","volume":"32","author":"Sheng","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref48","first-page":"1296","volume-title":"Swiftnet: real-time video object segmentation. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Wang","year":"2021"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","article-title":"Deep high-resolution representation learning for visual recognition","volume":"43","author":"Wang","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref50","first-page":"1860","volume-title":"Lednet: a lightweight encoder-decoder network for real-time semantic segmentation. 2019 IEEE international conference on image processing (ICIP)","author":"Wang","year":"2019"},{"key":"ref51","first-page":"3","volume-title":"Cbam: convolutional block attention module. Proceedings of the European conference on computer vision (ECCV)","author":"Woo","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1016\/j.neunet.2022.10.034","article-title":"BASeg: boundary aware semantic segmentation for autonomous driving","volume":"157","author":"Xiao","year":"2023","journal-title":"Neural Netw."},{"key":"ref53","doi-asserted-by":"publisher","first-page":"71","DOI":"10.3390\/rs13010071","article-title":"HRCNet: high-resolution context extraction network for semantic segmentation of remote sensing images","volume":"13","author":"Xu","year":"2020","journal-title":"Remote Sens."},{"key":"ref54","doi-asserted-by":"publisher","first-page":"5175","DOI":"10.1109\/TIP.2020.2976856","article-title":"Small object augmentation of urban scenes for real-time semantic segmentation","volume":"29","author":"Yang","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref55","first-page":"3684","volume-title":"Denseaspp for semantic segmentation in street scenes. Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Yang","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.10410","article-title":"Radar-camera fusion for object detection and semantic segmentation in autonomous driving: a comprehensive review","author":"Yao","year":"2023","journal-title":"ar Xiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s11263-021-01515-2","article-title":"Bisenet v2: bilateral network with guided aggregation for real-time semantic segmentation","volume":"129","author":"Yu","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"ref58","first-page":"1511.07122","article-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2015","journal-title":"ar Xiv preprint"},{"key":"ref59","first-page":"325","volume-title":"Bisenet: Bilateral segmentation network for real-time semantic segmentation. Proceedings of the European conference on computer vision (ECCV)","author":"Yu","year":"2018"},{"key":"ref60","first-page":"1809.00916","article-title":"Ocnet: object context network for scene parsing","author":"Yuan","year":"2018","journal-title":"ar Xiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.cag.2019.03.007","article-title":"Portrait net: real-time portrait segmentation network for mobile device","volume":"80","author":"Zhang","year":"2019","journal-title":"Comput. Graph."},{"key":"ref62","first-page":"405","article-title":"ICNet for real-time semantic segmentation on high-resolution images","volume-title":"Computer Vision \u2013 ECCV 2018. ECCV 2018. Lecture Notes in Computer Science()","author":"Zhao","year":"2018"},{"key":"ref63","first-page":"2881","volume-title":"Pyramid scene parsing network. Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Zhao","year":"2017"},{"key":"ref64","first-page":"8856","volume-title":"Improving semantic segmentation via video propagation and label relaxation. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Zhu","year":"2019"},{"key":"ref65","volume-title":"Shelfnet for fast semantic segmentation. Proceedings of the IEEE\/CVF international conference on computer vision workshops","author":"Zhuang","year":"2019"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2023.1280640\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T07:25:03Z","timestamp":1698045903000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2023.1280640\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,23]]},"references-count":59,"alternative-id":["10.3389\/fncom.2023.1280640"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2023.1280640","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,23]]},"article-number":"1280640"}}