{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T19:51:32Z","timestamp":1771530692691,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T00:00:00Z","timestamp":1672963200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T00:00:00Z","timestamp":1672963200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s11063-023-11145-z","type":"journal-article","created":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T18:04:04Z","timestamp":1673028244000},"page":"6425-6442","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["ELANet: Effective Lightweight Attention-Guided Network for Real-Time Semantic Segmentation"],"prefix":"10.1007","volume":"55","author":[{"given":"Qingming","family":"Yi","sequence":"first","affiliation":[]},{"given":"Guoshuai","family":"Dai","sequence":"additional","affiliation":[]},{"given":"Min","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Zunkai","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Aiwen","family":"Luo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,6]]},"reference":[{"issue":"12","key":"11145_CR1","doi-asserted-by":"publisher","first-page":"5659","DOI":"10.1109\/TIP.2015.2487860","volume":"24","author":"C Hong","year":"2015","unstructured":"Hong C, Yu J, Wan J, Tao D, Wang M (2015) Multimodal deep autoencoder for human pose recovery. IEEE Trans Image Process 24(12):5659\u20135670","journal-title":"IEEE Trans Image Process"},{"issue":"7","key":"11145_CR2","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1109\/TII.2018.2884211","volume":"15","author":"C Hong","year":"2018","unstructured":"Hong C, Yu J, Zhang J, Jin X, Lee K-H (2018) Multimodal face-pose estimation with multitask manifold deep learning. IEEE Trans Ind Inf 15(7):3952\u20133961","journal-title":"IEEE Trans Ind Inf"},{"issue":"2","key":"11145_CR3","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1109\/TPAMI.2019.2932058","volume":"44","author":"J Yu","year":"2019","unstructured":"Yu J, Tan M, Zhang H, Rui Y, Tao D (2019) Hierarchical deep click feature prediction for fine-grained image recognition. IEEE Trans Pattern Anal Mach Intell 44(2):563\u2013578","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"11145_CR4","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1109\/TCYB.2020.2969046","volume":"51","author":"J Yu","year":"2020","unstructured":"Yu J, Yao J, Zhang J, Yu Z, Tao D (2020) SPRNet: single-pixel reconstruction for one-stage instance segmentation. IEEE Trans Cybern 51(4):1731\u20131742","journal-title":"IEEE Trans Cybern"},{"key":"11145_CR5","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"11145_CR6","doi-asserted-by":"crossref","unstructured":"Siam M, Gamal M, Abdel-Razek M, Yogamani S, Jagersand M, Zhang H (2018) A comparative study of real-time semantic segmentation for autonomous driving. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 587\u2013597","DOI":"10.1109\/CVPRW.2018.00101"},{"key":"11145_CR7","doi-asserted-by":"crossref","unstructured":"Siam M, Elkerdawy S, Jagersand M, Yogamani S (2017) Deep semantic segmentation for automated driving: Taxonomy, roadmap and challenges. In: 2017 IEEE 20th international conference on intelligent transportation systems (ITSC). IEEE, pp 1\u20138","DOI":"10.1109\/ITSC.2017.8317714"},{"key":"11145_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.robot.2018.02.017","volume":"104","author":"B Bovcon","year":"2018","unstructured":"Bovcon B, Per\u0161 J, Kristan M et al (2018) Stereo obstacle detection for unmanned surface vehicles by imu-assisted semantic segmentation. Robot Auton Syst 104:1\u201313","journal-title":"Robot Auton Syst"},{"key":"11145_CR9","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017)MobileNets: efficient convolutional neural networks for mobile vision applications. Preprint at arXiv:1704.04861"},{"key":"11145_CR10","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou X, Lin M, Sun J (2018) ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6848\u20136856","DOI":"10.1109\/CVPR.2018.00716"},{"issue":"1","key":"11145_CR11","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1109\/TITS.2017.2750080","volume":"19","author":"E Romera","year":"2017","unstructured":"Romera E, Alvarez JM, Bergasa LM, Arroyo R (2017) ERFNet: efficient residual factorized convnet for real-time semantic segmentation. IEEE Trans Intell Transp Syst 19(1):263\u2013272","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"11145_CR12","unstructured":"Li G, Yun I, Kim J, Kim J (2019) DABNet: depth-wise asymmetric bottleneck for real-time semantic segmentation. Preprint at arXiv:1907.11357"},{"key":"11145_CR13","doi-asserted-by":"crossref","unstructured":"Zhang X, Du B, Wu Z, Wan T (2022) LAANet: lightweight attention-guided asymmetric network for real-time semantic segmentation. Neural Comput Appl:1\u201315","DOI":"10.1007\/s00521-022-06932-z"},{"key":"11145_CR14","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1109\/LSP.2021.3051845","volume":"28","author":"Y Li","year":"2021","unstructured":"Li Y, Li X, Xiao C, Li H, Zhang W (2021) EACNet: enhanced asymmetric convolution for real-time semantic segmentation. IEEE Signal Process Lett 28:234\u2013238","journal-title":"IEEE Signal Process Lett"},{"key":"11145_CR15","unstructured":"Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions. In: 4th international conference on learning representations"},{"key":"11145_CR16","doi-asserted-by":"crossref","unstructured":"Li Y, Li M, Li Z, Xiao C, Li H (2022) EFRNet: efficient feature reuse network for real-time semantic segmentation. Neural Process Lett:1\u201313","DOI":"10.1007\/s11063-022-10957-9"},{"key":"11145_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115090","volume":"183","author":"MA Elhassan","year":"2021","unstructured":"Elhassan MA, Huang C, Yang C, Munea TL (2021) DSANet: dilated spatial attention for real-time semantic segmentation in urban street scenes. Expert Syst Appl 183:115090","journal-title":"Expert Syst Appl"},{"key":"11145_CR18","doi-asserted-by":"crossref","unstructured":"Lin G, Milan A, Shen C, Reid I (2017) RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1925\u20131934","DOI":"10.1109\/CVPR.2017.549"},{"key":"11145_CR19","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"11145_CR20","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"11145_CR21","doi-asserted-by":"crossref","unstructured":"Wang Q, Wu B, Zhu PF, Li P, Zuo W, Hu Q (2020) ECA-Net: efficient channel attention for deep convolutional neural networks. In: 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 11531\u201311539","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"11145_CR22","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS (2018) CBAM: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"11145_CR23","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"issue":"2","key":"11145_CR24","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.patrec.2008.04.005","volume":"30","author":"GJ Brostow","year":"2009","unstructured":"Brostow GJ, Fauqueur J, Cipolla R (2009) Semantic object classes in video: a high-definition ground truth database. Pattern Recogn Lett 30(2):88\u201397","journal-title":"Pattern Recogn Lett"},{"key":"11145_CR25","doi-asserted-by":"crossref","unstructured":"Caesar H, Uijlings J, Ferrari V (2018) Coco-stuff: thing and stuff classes in context. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1209\u20131218","DOI":"10.1109\/CVPR.2018.00132"},{"issue":"6","key":"11145_CR26","doi-asserted-by":"publisher","first-page":"4177","DOI":"10.1007\/s11063-021-10587-7","volume":"53","author":"G Peng","year":"2021","unstructured":"Peng G, Yang S, Wang H (2021) Refine for semantic segmentation based on parallel convolutional network with attention model. Neural Process Lett 53(6):4177\u20134188","journal-title":"Neural Process Lett"},{"key":"11145_CR27","unstructured":"Paszke A, Chaurasia A, Kim S, Culurciello E (2016) ENet: a deep neural network architecture for real-time semantic segmentation. Preprint arXiv:1606.02147"},{"key":"11145_CR28","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/LSP.2021.3124186","volume":"29","author":"G Li","year":"2021","unstructured":"Li G, Li L, Zhang J (2021) BiAttnNet: bilateral attention for improving real-time semantic segmentation. IEEE Signal Process Lett 29:46\u201350","journal-title":"IEEE Signal Process Lett"},{"key":"11145_CR29","doi-asserted-by":"crossref","unstructured":"Wang Y, Zhou Q, Liu J, Xiong J, Gao G, Wu X, Latecki LJ (2019) LEDNet: a lightweight encoder-decoder network for real-time semantic segmentation. In: 2019 IEEE international conference on image processing (ICIP). IEEE, pp 1860\u20131864","DOI":"10.1109\/ICIP.2019.8803154"},{"key":"11145_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107952","volume":"116","author":"J Zhang","year":"2021","unstructured":"Zhang J, Cao Y, Wu Q (2021) Vector of locally and adaptively aggregated descriptors for image feature representation. Pattern Recogn 116:107952","journal-title":"Pattern Recogn"},{"key":"11145_CR31","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. Preprint at arXiv:2010.11929"},{"key":"11145_CR32","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"11145_CR33","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1016\/j.isprsjprs.2021.05.004","volume":"177","author":"X Yang","year":"2021","unstructured":"Yang X, Li S, Chen Z, Chanussot J, Jia X, Zhang B, Li B, Chen P (2021) An attention-fused network for semantic segmentation of very-high-resolution remote sensing imagery. ISPRS J Photogramm Remote Sens 177:238\u2013262","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"11145_CR34","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1109\/TIP.2020.3042065","volume":"30","author":"T Wu","year":"2020","unstructured":"Wu T, Tang S, Zhang R, Cao J, Zhang Y (2020) CGNet: a light-weight context guided network for semantic segmentation. IEEE Trans Image Process 30:1169\u20131179","journal-title":"IEEE Trans Image Process"},{"key":"11145_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104269","volume":"114","author":"X Hao","year":"2021","unstructured":"Hao X, Hao X, Zhang Y, Li Y, Wu C (2021) Real-time semantic segmentation with weighted factorized-depthwise convolution. Image Vis Comput 114:104269","journal-title":"Image Vis Comput"},{"key":"11145_CR36","unstructured":"Sutskever I, Martens J, Dahl G, Hinton G (2013) On the importance of initialization and momentum in deep learning. In: International conference on machine learning. PMLR, pp 1139\u20131147"},{"key":"11145_CR37","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. Preprint at arXiv:1412.6980"},{"key":"11145_CR38","doi-asserted-by":"crossref","unstructured":"Mehta S, Rastegari M, Caspi A, Shapiro L, Hajishirzi H (2018) ESPNet: efficient spatial pyramid of dilated convolutions for semantic segmentation. In: Proceedings of the European conference on computer vision (ECCV), pp 552\u2013568","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"11145_CR39","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1016\/j.neucom.2021.07.019","volume":"459","author":"M Zhuang","year":"2021","unstructured":"Zhuang M, Zhong X, Gu D, Feng L, Zhong X, Hu H (2021) LRDNet: a lightweight and efficient network with refined dual attention decorder for real-time semantic segmentation. Neurocomputing 459:349\u2013360","journal-title":"Neurocomputing"},{"key":"11145_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106682","volume":"96","author":"Q Zhou","year":"2020","unstructured":"Zhou Q, Wang Y, Fan Y, Wu X, Zhang S, Kang B, Latecki LJ (2020) AGLNet: towards real-time semantic segmentation of self-driving images via attention-guided lightweight network. Appl Soft Comput 96:106682","journal-title":"Appl Soft Comput"},{"key":"11145_CR41","unstructured":"Lu M, Chen Z, Wu QJ, Wang N, Rong X, Yan X (2020) FRNet: factorized and regular blocks network for semantic segmentation in road scene. IEEE Trans Intell Transp Syst"},{"key":"11145_CR42","doi-asserted-by":"crossref","unstructured":"Liu J, Zhou Q, Qiang Y, Kang B, Wu X, Zheng B (2020) FDDWNet: a lightweight convolutional neural network for real-time semantic segmentation. In: ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 2373\u20132377","DOI":"10.1109\/ICASSP40776.2020.9053838"},{"key":"11145_CR43","doi-asserted-by":"crossref","unstructured":"Jiang W, Xie Z, Li Y, Liu C, Lu H (2020) LRNNET: a light-weighted network with efficient reduced non-local operation for real-time semantic segmentation. In: 2020 IEEE international conference on multimedia & expo workshops (ICMEW). IEEE, pp 1\u20136","DOI":"10.1109\/ICMEW46912.2020.9106038"},{"key":"11145_CR44","doi-asserted-by":"crossref","unstructured":"Yu C, Xiao B, Gao C, Yuan L, Zhang L, Sang N, Wang J (2021) Lite-HRNet: a lightweight high-resolution network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10440\u201310450","DOI":"10.1109\/CVPR46437.2021.01030"},{"key":"11145_CR45","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.neucom.2021.12.003","volume":"474","author":"J Liu","year":"2022","unstructured":"Liu J, Xu X, Shi Y, Deng C, Shi M (2022) RELAXNet: residual efficient learning and attention expected fusion network for real-time semantic segmentation. Neurocomputing 474:115\u2013127","journal-title":"Neurocomputing"},{"key":"11145_CR46","doi-asserted-by":"crossref","unstructured":"Yu C, Wang J, Peng C, Gao C, Yu G, Sang N (2018) BiSeNet: bilateral segmentation network for real-time semantic segmentation. In: Proceedings of the European conference on computer vision (ECCV), pp 325\u2013341","DOI":"10.1007\/978-3-030-01261-8_20"},{"issue":"12","key":"11145_CR47","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11145_CR48","doi-asserted-by":"crossref","unstructured":"Li H, Xiong P, Fan H, Sun J (2019) DFAnet: deep feature aggregation for real-time semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9522\u20139531","DOI":"10.1109\/CVPR.2019.00975"},{"issue":"1","key":"11145_CR49","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1007\/s10489-021-02437-9","volume":"52","author":"X-L Zhang","year":"2022","unstructured":"Zhang X-L, Du B-C, Luo Z-C, Ma K (2022) Lightweight and efficient asymmetric network design for real-time semantic segmentation. Appl Intell 52(1):564\u2013579","journal-title":"Appl Intell"},{"key":"11145_CR50","doi-asserted-by":"crossref","unstructured":"Zhao H, Qi X, Shen X, Shi J, Jia J (2018) ICNet for real-time semantic segmentation on high-resolution images. In: Proceedings of the European conference on computer vision (ECCV), pp 405\u2013420","DOI":"10.1007\/978-3-030-01219-9_25"},{"issue":"4","key":"11145_CR51","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-023-11145-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-023-11145-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-023-11145-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T16:20:25Z","timestamp":1696004425000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-023-11145-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,6]]},"references-count":51,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["11145"],"URL":"https:\/\/doi.org\/10.1007\/s11063-023-11145-z","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,6]]},"assertion":[{"value":"1 January 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}