{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T00:45:12Z","timestamp":1760402712264,"version":"build-2065373602"},"reference-count":33,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T00:00:00Z","timestamp":1641945600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Edge detection is one of the fundamental computer vision tasks. Recent methods for edge detection based on a convolutional neural network (CNN) typically employ the weighted cross-entropy loss. Their predicted results being thick and needing post-processing before calculating the optimal dataset scale (ODS) F-measure for evaluation. To achieve end-to-end training, we propose a non-maximum suppression layer (NMS) to obtain sharp boundaries without the need for post-processing. The ODS F-measure can be calculated based on these sharp boundaries. So, the ODS F-measure loss function is proposed to train the network. Besides, we propose an adaptive multi-level feature pyramid network (AFPN) to better fuse different levels of features. Furthermore, to enrich multi-scale features learned by AFPN, we introduce a pyramid context module (PCM) that includes dilated convolution to extract multi-scale features. Experimental results indicate that the proposed AFPN achieves state-of-the-art performance on the BSDS500 dataset (ODS F-score of 0.837) and the NYUDv2 dataset (ODS F-score of 0.780).<\/jats:p>","DOI":"10.3390\/info13010032","type":"journal-article","created":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T09:10:36Z","timestamp":1641978636000},"page":"32","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Adaptive Feature Pyramid Network to Predict Crisp Boundaries via NMS Layer and ODS F-Measure Loss Function"],"prefix":"10.3390","volume":"13","author":[{"given":"Gang","family":"Sun","sequence":"first","affiliation":[{"name":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5191-402X","authenticated-orcid":false,"given":"Hancheng","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China"}]},{"given":"Xiangtao","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China"}]},{"given":"Mingkui","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,1,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1109\/34.99234","article-title":"Recognition by linear combinations of models","volume":"13","author":"Ullman","year":"1991","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1109\/TPAMI.2007.1144","article-title":"Groups of adjacent contour segments for object detection","volume":"30","author":"Ferrari","year":"2008","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"898","DOI":"10.1109\/TPAMI.2010.161","article-title":"Contour detection and hierarchical image segmentation","volume":"33","author":"Arbelaez","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1023\/A:1011174803800","article-title":"Contour and texture analysis for image segmentation","volume":"43","author":"Malik","year":"2001","journal-title":"IJCV"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s41095-018-0120-1","article-title":"BING: Binarized normed gradients for objectness estimation at 300 fps","volume":"5","author":"Cheng","year":"2019","journal-title":"Comput. Vis. Media"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/0262-8856(83)90006-9","article-title":"On the accuracy of the sobel edge detector","volume":"1","author":"Kittler","year":"1983","journal-title":"Image Vis. Comput."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","article-title":"A Computational Approach to Edge Detection","volume":"8","author":"Canny","year":"1986","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Lim, J.J., Zitnick, C.L., and Doll\u00e1r, P. (2013, January 25\u201327). Sketch tokens: A learned mid-level representation for contour and object detection. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, USA.","DOI":"10.1109\/CVPR.2013.406"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1558","DOI":"10.1109\/TPAMI.2014.2377715","article-title":"Fast Edge Detection Using Structured Forests","volume":"37","author":"Dollar","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s11263-017-1004-z","article-title":"Holistically-nested edge detection","volume":"125","author":"Xie","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Liu, Y., Cheng, M.-M., Hu, X., Bian, J.-W., Zhang, L., Bai, X., and Tang, J. (2017, January 21\u201326). Richer convolutional features for edge detection. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.622"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Deng, R., Shen, C., Liu, S., Wang, H., and Liu, X. (2018, January 8\u201314). Learning to predict crisp boundaries. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01231-1_35"},{"key":"ref_13","unstructured":"Simonyan, K., and Zisserman, A. (2014, January 23\u201328). Very deep convolutional networks for large-scale image recognition. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21\u201326). Feature pyramid networks for object detection. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"107024","DOI":"10.1109\/ACCESS.2021.3100369","article-title":"Adaptive Feature Pyramid Networks for Object Detection","volume":"9","author":"Wang","year":"2021","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xing, F., Shi, X., and Yang, L. (2016, January 27\u201330). SemiContour: A Semi-supervised Learning Approach for Contour Detection. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.34"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ganin, Y., and Lempitsky, V. (2014, January 1\u20135). N4 fields: Neural network nearest neighbor fields for image trans-forms. Proceedings of the Asian Conference on Computer Vision (ACCV), Singapore.","DOI":"10.1007\/978-3-319-16808-1_36"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Shi, J., and Torresani, L. (2015, January 7\u201312). DeepEdge: A multi-scale bifurcated deep network for top-down contour detection. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7299067"},{"key":"ref_19","unstructured":"Shen, W., Wang, X., Wang, Y., Bai, X., and Zhang, Z. (2015, January 7\u201312). Deep-Contour: A deep convolutional feature learned by positive-sharing loss for contour detection. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"He, J., Zhang, S., Yang, M., Shan, Y., and Huang, T. (2019, January 16\u201320). BDCN: Bi-Directional Cascade Network for Perceptual Edge Detection. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00395"},{"key":"ref_21","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1093\/comjnl\/29.6.481","article-title":"A non-classical logic for information retrieval","volume":"29","author":"Rijsbergen","year":"1986","journal-title":"Comput. J."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1109\/PROC.1979.11325","article-title":"Quantitative Design and Evaluation of Enhancement\/Thresholding Edge Detectors","volume":"67","author":"Abdou","year":"1979","journal-title":"Proc. IEEE"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D.P., and Fergus, R. (2012, January 7\u201313). Indoor segmentation and support inference from RGBD images. Proceedings of the European Conference on Computer Vision (ECCV), Florence, Italy.","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref_25","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 NIPS 2017 Autodiff Workshop: The Future of Gradient-Based Machine Learning Software and Techniques, Long Beach, CA, USA."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","article-title":"Efficient graph-based image segmentation","volume":"59","author":"Felzenszwalb","year":"2004","journal-title":"IJCV"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1109\/34.1000236","article-title":"Mean shift: A robust approach toward feature space analysis","volume":"24","author":"Comaniciu","year":"2002","journal-title":"IEEE Trans. Pattern Anal."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Arbel\u00e1ez, P., Pont-Tuset, J., Barron, J.T., Marques, F., and Malik, J. (2014, January 23\u201328). Multiscale combinatorial grouping. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.49"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Hallman, S., and Fowlkes, C.C. (2015, January 7\u201312). Oriented edge forests for boundary detection. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298782"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1939","DOI":"10.1109\/TPAMI.2018.2878849","article-title":"Richer convolutional features for edge detection","volume":"41","author":"Liu","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.visres.2015.11.007","article-title":"A systematic comparison between visual cues for boundary detection","volume":"120","author":"Kim","year":"2016","journal-title":"Vis. Res."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/13\/1\/32\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T14:02:07Z","timestamp":1760364127000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/13\/1\/32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,12]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,1]]}},"alternative-id":["info13010032"],"URL":"https:\/\/doi.org\/10.3390\/info13010032","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2022,1,12]]}}}