{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:25:24Z","timestamp":1773692724059,"version":"3.50.1"},"reference-count":32,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T00:00:00Z","timestamp":1685664000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Jilin Province Science and Technology Development Plan Project","award":["20210204195YY"],"award-info":[{"award-number":["20210204195YY"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>In this paper, we propose a method that uses the idea of decoupling and unites edge information for semantic segmentation. We build a new dual-stream CNN architecture that fully considers the interaction between the body and the edge of the object, and our method significantly improves the segmentation performance of small objects and object boundaries. The dual-stream CNN architecture mainly consists of a body-stream module and an edge-stream module, which process the feature map of the segmented object into two parts with low coupling: body features and edge features. The body stream warps the image features by learning the flow-field offset, warps the body pixels toward object inner parts, completes the generation of the body features, and enhances the object\u2019s inner consistency. In the generation of edge features, the current state-of-the-art model processes information such as color, shape, and texture under a single network, which will ignore the recognition of important information. Our method separates the edge-processing branch in the network, i.e., the edge stream. The edge stream processes information in parallel with the body stream and effectively eliminates the noise of useless information by introducing a non-edge suppression layer to emphasize the importance of edge information. We validate our method on the large-scale public dataset Cityscapes, and our method greatly improves the segmentation performance of hard-to-segment objects and achieves state-of-the-art result. Notably, the method in this paper can achieve 82.6% mIoU on the Cityscapes with only fine-annotated data.<\/jats:p>","DOI":"10.3390\/e25060891","type":"journal-article","created":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T02:41:35Z","timestamp":1685673695000},"page":"891","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Improving Semantic Segmentation via Decoupled Body and Edge Information"],"prefix":"10.3390","volume":"25","author":[{"given":"Lintao","family":"Yu","sequence":"first","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University of Science and Technology, Changchun 130022, China"}]},{"given":"Anni","family":"Yao","sequence":"additional","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University of Science and Technology, Changchun 130022, China"}]},{"given":"Jin","family":"Duan","sequence":"additional","affiliation":[{"name":"College of Electronic Information Engineering, Changchun University of Science and Technology, Changchun 130022, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,6,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Li, X., You, A., Zhu, Z., Zhao, H., Yang, M., Yang, K., and Tan, S. (2020, January 23\u201328). Semantic flow for fast and accurate scene parsing. Proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part I 16.","DOI":"10.1007\/978-3-030-58452-8_45"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2281","DOI":"10.1109\/TMI.2019.2903562","article-title":"Ce-net: Context encoder network for 2d medical image segmentation","volume":"38","author":"Gu","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Chen, G., Wu, T., Duan, J., Hu, Q., Huang, D., and Li, H. (2023). Centerpnets: A multi-task shared network for traffic perception. Sensors, 23.","DOI":"10.3390\/s23052467"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"43601","DOI":"10.1364\/OE.472214","article-title":"Semantic-guided polarization image fusion method based on a dual-discriminator GAN","volume":"30","author":"Liu","year":"2022","journal-title":"Opt. Express"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Jang, D.-H., Chu, S., Kim, J., and Han, B. (2022, January 19\u201324). Pooling revisited: Your receptive field is suboptimal. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00063"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., and Torr, P.H.S. (2015, January 11\u201318). Conditional random fields as recurrent neural networks. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Gong, K., Liang, X., Li, Y., Chen, Y., Yang, M., and Lin, L. (2018, January 8\u201314). Instance-level human parsing via part grouping network. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01225-0_47"},{"key":"ref_10","unstructured":"Bertasius, G., Shi, J., and Torresani, L. (July, January 26). Semantic segmentation with boundary neural fields. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_11","unstructured":"Tao, A., Sapra, K., and Catanzaro, B. (2020). Hierarchical multi-scale attention for semantic segmentation. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Li, X., Li, X., Zhang, L., Cheng, G., Shi, J., Lin, Z., and Tan, S. (2020, January 23\u201328). Improving semantic segmentation via decoupled body and edge supervision. Proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part XVII 16.","DOI":"10.1007\/978-3-030-58520-4_26"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ling, H., Gao, J., Kar, A., Chen, W., and Fidler, S. (2019, January 15\u201320). Fast interactive object annotation with curve-gcn. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00540"},{"key":"ref_14","unstructured":"Takikawa, T., Acuna, D., Jampani, V., and Fidler, S. (November, January 27). Gated-scnn: Gated shape cnns for semantic segmentation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_15","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (July, January 26). The cityscapes dataset for semantic urban scene understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., and Reid, I. (2017, January 21\u201326). Multi-path refinement networks for high-resolution semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Cheng, T., Wang, X., Huang, L., and Liu, W. (2020, January 23\u201328). Boundary-preserving mask r-cnn. Proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part XIV 16.","DOI":"10.1007\/978-3-030-58568-6_39"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Lin, G., Shen, C., Van Den Hengel, A., and Reid, I. (2016, January 27\u201330). Efficient piecewise training of deep structured models for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.348"},{"key":"ref_19","unstructured":"Krhenb\u00fchl, P., and Koltun, V. (2012). Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials, Curran Associates Inc."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Barron, J.T., Papandreou, G., Murphy, K., and Yuille, A.L. (2016, January 27\u201330). 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, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.492"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Xie, J., Chen, X., and Wang, J. (2020, January 23\u201328). Segfix: Model-agnostic boundary refinement for segmentation. Proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part XII 16.","DOI":"10.1007\/978-3-030-58610-2_29"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., and Girshick, R. (2020, January 14\u201319). Pointrend: Image segmentation as rendering. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Cheng, B., Girshick, R., Doll\u00e1r, P., Berg, A.C., and Kirillov, A. (2021, January 19\u201325). Boundary iou: Improving object-centric image segmentation evaluation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR46437.2021.01508"},{"key":"ref_24","unstructured":"Wang, C., Zhang, Y., Cui, M., Ren, P., Yang, Y., Xie, X., Hua, X.-S., Bao, H., and Xu, W. (March, January 22). Active boundary loss for semantic segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Sapra, K., Reda, F.A., Shih, K.J., Newsam, S., Tao, A., and Catanzaro, B. (2019, January 15\u201320). Improving semantic segmentation via video propagation and label relaxation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00906"},{"key":"ref_26","unstructured":"Jang, E., Gu, S., and Poole, B. (2016). Categorical reparameterization with gumbel-softmax. arXiv."},{"key":"ref_27","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., and Lerer, A. (2017, January 9). Automatic differentiation in pytorch. Proceedings of the NeurIPS Workshop, Long Beach, CA, USA."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8\u201314). Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., and Sorkine-Hornung, A. (2016, January 27\u201330). A benchmark dataset and evaluation methodology for video object segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., and Lu, H. (2019, January 16\u201317). Dual attention network for scene segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref_31","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., and Zhou, Y. (2021). Transunet: Transformers make strong encoders for medical image segmentation. arXiv."},{"key":"ref_32","first-page":"6575","article-title":"Volo: Vision outlooker for visual recognition","volume":"45","author":"Yuan","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/6\/891\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:47:35Z","timestamp":1760125655000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/6\/891"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,2]]},"references-count":32,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["e25060891"],"URL":"https:\/\/doi.org\/10.3390\/e25060891","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,2]]}}}