{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T01:02:28Z","timestamp":1760230948969,"version":"build-2065373602"},"reference-count":58,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T00:00:00Z","timestamp":1660608000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41901402","20A420005","2018NGCM04","22IRTSTHN010","2019037"],"award-info":[{"award-number":["41901402","20A420005","2018NGCM04","22IRTSTHN010","2019037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Scientific Research Projects of Higher Education Institutions of Henan","award":["41901402","20A420005","2018NGCM04","22IRTSTHN010","2019037"],"award-info":[{"award-number":["41901402","20A420005","2018NGCM04","22IRTSTHN010","2019037"]}]},{"name":"Key Laboratory for National Geographic Census and Monitoring, National Administration of Surveying, Mapping and Geoinformation","award":["41901402","20A420005","2018NGCM04","22IRTSTHN010","2019037"],"award-info":[{"award-number":["41901402","20A420005","2018NGCM04","22IRTSTHN010","2019037"]}]},{"name":"Program for Innovative Research Team (in Science and Technology) in the University of Henan Province","award":["41901402","20A420005","2018NGCM04","22IRTSTHN010","2019037"],"award-info":[{"award-number":["41901402","20A420005","2018NGCM04","22IRTSTHN010","2019037"]}]},{"DOI":"10.13039\/501100012337","name":"Nanhu Scholars Program for Young Scholars of XYNU","doi-asserted-by":"publisher","award":["41901402","20A420005","2018NGCM04","22IRTSTHN010","2019037"],"award-info":[{"award-number":["41901402","20A420005","2018NGCM04","22IRTSTHN010","2019037"]}],"id":[{"id":"10.13039\/501100012337","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Due to radiometric and geometric distortions between images, mismatches are inevitable. Thus, a mismatch removal process is required for improving matching accuracy. Although deep learning methods have been proved to outperform handcraft methods in specific scenarios, including image identification and point cloud classification, most learning methods are supervised and are susceptible to incorrect labeling, and labeling data is a time-consuming task. This paper takes advantage of deep reinforcement leaning (DRL) and proposes a framework named unsupervised learning for mismatch removal (ULMR). Resorting to DRL, ULMR firstly scores each state\u2013action pair guided by the output of classification network; then, it calculates the policy gradient of the expected reward; finally, through maximizing the expected reward of state\u2013action pairings, the optimal network can be obtained. Compared to supervised learning methods (e.g., NM-Net and LFGC), unsupervised learning methods (e.g., ULCM), and handcraft methods (e.g., RANSAC, GMS), ULMR can obtain higher precision, more remaining correct matches, and fewer remaining false matches in testing experiments. Moreover, ULMR shows greater stability, better accuracy, and higher quality in application experiments, demonstrating reduced sampling times and higher compatibility with other classification networks in ablation experiments, indicating its great potential for further use.<\/jats:p>","DOI":"10.3390\/s22166110","type":"journal-article","created":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T03:15:27Z","timestamp":1660706127000},"page":"6110","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["ULMR: An Unsupervised Learning Framework for Mismatch Removal"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8151-8183","authenticated-orcid":false,"given":"Cailong","family":"Deng","sequence":"first","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Geographic Sciences, Xinyang Normal University, Xinyang 464000, China"},{"name":"Henan Engineering Research Center for Big Data of Remote Sensing and Intelligent Analysis in Huaihe River Basin, Xinyang Normal University, Xinyang 464000, China"},{"name":"Key Laboratory for National Geographic Census and Monitoring, National Administration of Surveying, Mapping and Geoinformation, Wuhan University, Wuhan 430079, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0230-1395","authenticated-orcid":false,"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Visiontek Research, 6 Phoenix Avenue, Wuhan 430205, China"},{"name":"School of Electronics and Information Engineering, Wuzhou University, Wuzhou 543003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qixin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Geographic Sciences, Xinyang Normal University, Xinyang 464000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feiyan","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Geographic Sciences, Xinyang Normal University, Xinyang 464000, China"},{"name":"Henan Engineering Research Center for Big Data of Remote Sensing and Intelligent Analysis in Huaihe River Basin, Xinyang Normal University, Xinyang 464000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,8,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1007\/s11263-020-01385-0","article-title":"Image Matching Across Wide Baselines: From Paper to Practice","volume":"129","author":"Jin","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.inffus.2021.02.012","article-title":"A review of multimodal image matching: Methods and applications","volume":"73","author":"Jiang","year":"2021","journal-title":"Inf. Fusion."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.isprsjprs.2017.04.015","article-title":"Poor textural image tie point matching via graph theory","volume":"129","author":"Yuan","year":"2017","journal-title":"ISPRS-J. Photogramm. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s11263-020-01359-2","article-title":"Image Matching from Handcrafted to Deep Features: A Survey","volume":"129","author":"Ma","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1145\/358669.358692","article-title":"Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography","volume":"24","author":"Fischler","year":"1981","journal-title":"Commun. ACM"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1038\/293133a0","article-title":"A computer algorithm for reconstructing a scene from two projections","volume":"293","year":"1981","journal-title":"Nature"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1109\/34.601246","article-title":"In defense of the eight-point algorithm","volume":"19","author":"Hartley","year":"1997","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1006\/cviu.1999.0832","article-title":"MLESAC: A New Robust Estimator with Application to Estimating Image Geometry","volume":"78","author":"Torr","year":"2000","journal-title":"Comput. Vis. Image Underst."},{"unstructured":"Chum, O., and Matas, J. (2005, January 20\u201325). Matching with PROSAC-progressive sample consensus. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA.","key":"ref_9"},{"doi-asserted-by":"crossref","unstructured":"Brachmann, E., Krull, A., Nowozin, S., Shotton, J., Michel, F., Gumhold, S., and Rother, C. (2017, January 21\u201326). DSAC-differentiable ransac for camera localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","key":"ref_10","DOI":"10.1109\/CVPR.2017.267"},{"doi-asserted-by":"crossref","unstructured":"Barath, D., Noskova, J., Ivashechkin, M., and Matas, J. (2020, January 13\u201319). MAGSAC++, a fast, reliable and accurate robust estimator. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","key":"ref_11","DOI":"10.1109\/CVPR42600.2020.00138"},{"doi-asserted-by":"crossref","unstructured":"Barath, D., and Matas, J. (2018, January 18\u201323). Graph-Cut RANSAC. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","key":"ref_12","DOI":"10.1109\/CVPR.2018.00704"},{"doi-asserted-by":"crossref","unstructured":"Brachmann, E., and Rother, C. (2019, January 15\u201320). Neural-guided RANSAC: Learning where to sample model hypotheses. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","key":"ref_13","DOI":"10.1109\/ICCV.2019.00442"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3519","DOI":"10.1016\/j.patcog.2013.05.017","article-title":"Regularized vector field learning with sparse approximation for mismatch removal","volume":"46","author":"Ma","year":"2013","journal-title":"Pattern Recognit."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.isprsjprs.2019.05.006","article-title":"LAM: Locality affine-invariant feature matching","volume":"154","author":"Li","year":"2019","journal-title":"ISPRS-J. Photogramm. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1007\/s11263-018-1117-z","article-title":"Locality preserving matching","volume":"127","author":"Ma","year":"2019","journal-title":"Int. J. Comput. Vis."},{"doi-asserted-by":"crossref","unstructured":"Bian, J., Lin, W., Matsushita, Y., Yeung, S., Nguyen, T., and Cheng, M. (2017, January 21\u201326). GMS: Grid-based motion statistics for fast, ultra-robust feature correspondence. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","key":"ref_17","DOI":"10.1109\/CVPR.2017.302"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1016\/j.isprsjprs.2021.11.004","article-title":"Robust feature matching via neighborhood manifold representation consensus","volume":"183","author":"Ma","year":"2022","journal-title":"ISPRS-J. Photogramm. Remote Sens."},{"key":"ref_19","first-page":"1","article-title":"Robust feature matching via local consensus","volume":"60","author":"Chen","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3188931","article-title":"A Two-Step Descriptor-Based Keypoint Filtering Algorithm for Robust Image Matching","volume":"60","author":"Mousavi","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"doi-asserted-by":"crossref","unstructured":"Yi, K.M., Trulls, E., Ono, Y., Lepetit, V., Salzmann, M., and Fua, P. (2018, January 18\u201323). Learning to Find Good Correspondences. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","key":"ref_21","DOI":"10.1109\/CVPR.2018.00282"},{"doi-asserted-by":"crossref","unstructured":"Zhao, C., Cao, Z., Li, C., Li, X., and Yang, J. (2019, January 15\u201320). NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","key":"ref_22","DOI":"10.1109\/CVPR.2019.00030"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"147634","DOI":"10.1109\/ACCESS.2021.3123942","article-title":"CE-Net: A Coordinate Embedding Network for Mismatching Removal","volume":"9","author":"Chen","year":"2021","journal-title":"IEEE Access"},{"doi-asserted-by":"crossref","unstructured":"Cavalli, L., Larsson, V., Oswald, M., Sattler, T., and Pollefeys, M. (2020). AdaLAM: Revisiting Handcrafted Outlier Detection. arXiv.","key":"ref_24","DOI":"10.1007\/978-3-030-58529-7_45"},{"unstructured":"Qi, C.R., Su, H., Mo, K., and Guiba, L.J. (2017, January 21\u201326). PointNet: Deep learning on point sets for 3D classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","key":"ref_25"},{"unstructured":"Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017, January 4\u20139). PointNet++: Deep hierarchical feature learning on point sets in a metric space. Proceedings of the Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA.","key":"ref_26"},{"unstructured":"Ulyanov, D., Vedaldi, A., and Lempitsky, V. (2016). Instance normalization: The Missing Ingredient for Fast Stylization. arXiv.","key":"ref_27"},{"unstructured":"Ioffe, S., and Szegedy, C. (2015). Batch normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv.","key":"ref_28"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3947","DOI":"10.1007\/s10462-019-09784-7","article-title":"A survey of regularization strategies for deep models","volume":"53","author":"Moradi","year":"2020","journal-title":"Artif. Intell. Rev."},{"key":"ref_30","first-page":"1","article-title":"A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification","volume":"2","author":"Zheng","year":"2020","journal-title":"Discret. Dyn. Nat. Soc."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"123649","DOI":"10.1109\/ACCESS.2020.3005687","article-title":"Deep Facial Diagnosis: Deep Transfer Learning from Face Recognition to Facial Diagnosis","volume":"8","author":"Jin","year":"2020","journal-title":"IEEE Access"},{"unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention is all you need. arXiv.","key":"ref_32"},{"doi-asserted-by":"crossref","unstructured":"Sun, W., Jiang, W., Trulls, E., Tagliasacchi, A., and Yi, K. (2020, January 13\u201319). ACNe: Attentive Context Normalization for Robust Permutation Equivariant Learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","key":"ref_33","DOI":"10.1109\/CVPR42600.2020.01130"},{"unstructured":"Murphy, K.P. (2012). Machine Learning: A Probabilistic Perspective, MIT Press.","key":"ref_34"},{"key":"ref_35","first-page":"845","article-title":"Classification in the presence of label noise: A survey","volume":"25","author":"Verleysen","year":"2013","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"unstructured":"Sukhbaatar, S., and Fergus, R. (2014). Learning from noisy labels with deep neural networks. arXiv.","key":"ref_36"},{"doi-asserted-by":"crossref","unstructured":"Probst, T., Paudel, D.P., Chhatkuli, A., and Gool, L.V. (2019, January 15\u201320). Unsupervised learning of consensus maximization for 3D vision problems. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","key":"ref_37","DOI":"10.1109\/CVPR.2019.00102"},{"unstructured":"Schulman, J., Heess, N., Weber, T., and Abbeel, P. (2015, January 7\u201312). Gradient estimation using stochastic computation graphs. Proceedings of the Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada.","key":"ref_38"},{"unstructured":"Jang, E., Gu, S., and Poole, B. (2016). Categorical reparameterization with gumbel-softmax. arXiv.","key":"ref_39"},{"unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M. (2013). Playing Atari with deep reinforcement learning. arXiv.","key":"ref_40"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"unstructured":"Jaderberg, M., Mnih, V., Czarnecki, W.M., Schaul, T., Leibo, J.Z., Silver, D., and Kavukcuoglu, K. (2016). Reinforcement learning with unsupervised auxiliary tasks. arXiv.","key":"ref_42"},{"doi-asserted-by":"crossref","unstructured":"Truong, G., Le, H., Suter, D., Zhang, E., and Gilani, S.Z. (2021, January 19\u201325). Unsupervised learning for robust fitting: A reinforcement learning approach. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Virtual.","key":"ref_43","DOI":"10.1109\/CVPR46437.2021.01021"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1093\/biomet\/57.1.97","article-title":"Monte Carlo sampling methods using Markov chains and their applications","volume":"57","author":"Hastings","year":"1970","journal-title":"Biometrika"},{"unstructured":"Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, MIT Press.","key":"ref_45"},{"unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., and Riedmiller, M. (2014, January 21\u201326). Deterministic Policy Gradient Algorithms. Proceedings of the International Conference on Machine Learning (ICML), Beijing, China.","key":"ref_46"},{"doi-asserted-by":"crossref","unstructured":"Johnson, N.L., Kemp, A.W., and Kotz, S. (2005). Univariate Discrete Distributions, Wiley. [3rd ed.].","key":"ref_47","DOI":"10.1002\/0471715816"},{"unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019, January 8\u201314). Pytorch: An imperative style, high-performance deep learning library. Proceedings of the Neural Information Processing Systems (NeurIPS), Vancouver, BC, Canada.","key":"ref_48"},{"unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2\u20134). TensorFlow: A System for Large-Scale Machine Learning. Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI), Savannah, GA, USA.","key":"ref_49"},{"doi-asserted-by":"crossref","unstructured":"Bottou, L. (2010, January 22\u201327). Large-scale machine learning with stochastic gradient descent. Proceedings of the International Conference on Computational Statistics (COMPSTAT), Paris, France.","key":"ref_50","DOI":"10.1007\/978-3-7908-2604-3_16"},{"unstructured":"Kingma, D.P., and Ba, J.L. (2014). Adam: A method for stochastic optimization. arXiv.","key":"ref_51"},{"doi-asserted-by":"crossref","unstructured":"Hartley, R., and Zisserman, A. (2004). Multiple View Geometry in Computer Vision, Cambridge University Press. [2nd ed.].","key":"ref_52","DOI":"10.1017\/CBO9780511811685"},{"doi-asserted-by":"crossref","unstructured":"Xiao, J., Owens, A., and Torralba, A. (2013, January 1\u20138). SUN3D: A database of big spaces reconstructed using SfM and object labels. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Sydney, Australia.","key":"ref_53","DOI":"10.1109\/ICCV.2013.458"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1145\/2812802","article-title":"YFCC100M: The new data in multimedia research","volume":"59","author":"Thomee","year":"2016","journal-title":"Commun. ACM"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vis."},{"doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., and Frahm, J.M. (2016, January 27\u201330). Structure-from-Motion Revisited. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","key":"ref_56","DOI":"10.1109\/CVPR.2016.445"},{"doi-asserted-by":"crossref","unstructured":"Luo, Z., Shen, T., Zhou, L., Zhu, S., Zhang, R., Yao, Y., Fang, T., and Quan, L. (2018, January 8\u201314). GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","key":"ref_57","DOI":"10.1007\/978-3-030-01240-3_11"},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"3213","DOI":"10.1007\/s10462-021-10085-1","article-title":"Model-free reinforcement learning from expert demonstrations: A survey","volume":"55","author":"Yu","year":"2022","journal-title":"Artif. Intell. Rev."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/16\/6110\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:09:15Z","timestamp":1760141355000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/16\/6110"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,16]]},"references-count":58,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2022,8]]}},"alternative-id":["s22166110"],"URL":"https:\/\/doi.org\/10.3390\/s22166110","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2022,8,16]]}}}