Cross-graph meta matching correction for noisy graph matching
In recent years, significant advancements have been made in image feature point matching within the context of deep graph matching. However, keypoint annotations in images can be inaccurate due to various issues such as occlusion, changes in viewpoint, or poor recognizability, leading to noisy corre...
Saved in:
| Published in | Computer vision and image understanding Vol. 259; p. 104433 |
|---|---|
| Main Authors | , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Inc
01.09.2025
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1077-3142 |
| DOI | 10.1016/j.cviu.2025.104433 |
Cover
Loading…
| Abstract | In recent years, significant advancements have been made in image feature point matching within the context of deep graph matching. However, keypoint annotations in images can be inaccurate due to various issues such as occlusion, changes in viewpoint, or poor recognizability, leading to noisy correspondence. To address this limitation, we propose a novel Meta Matching Correction for noisy Graph Matching (MCGM), which introduces meta-learning to mitigate noisy correspondence for the first time. Specifically, we design a Meta Correcting Network (MCN) that integrates global features and geometric consistency information of graphs to generate confidence scores for nodes and edges. Based on the scores, MCN adaptively adjusts and penalizes the noisy assignments, enhancing the model’s ability to handle noisy correspondence. We conduct joint training of the main network and MCN to achieve dynamic correction through a bi-level optimization framework. Experimental evaluations on three public benchmark datasets demonstrate that our proposed method delivers robust performance improvements over state-of-the-art graph matching solutions and exhibits excellent stability when handling images under complex conditions.
•First use of meta-learning for correcting noisy correspondences in graph matching.•Generate matching confidence using global features and geometric consistency.•Bi-level optimization framework for joint training.•Significant performance and noise robustness on public benchmark datasets. |
|---|---|
| AbstractList | In recent years, significant advancements have been made in image feature point matching within the context of deep graph matching. However, keypoint annotations in images can be inaccurate due to various issues such as occlusion, changes in viewpoint, or poor recognizability, leading to noisy correspondence. To address this limitation, we propose a novel Meta Matching Correction for noisy Graph Matching (MCGM), which introduces meta-learning to mitigate noisy correspondence for the first time. Specifically, we design a Meta Correcting Network (MCN) that integrates global features and geometric consistency information of graphs to generate confidence scores for nodes and edges. Based on the scores, MCN adaptively adjusts and penalizes the noisy assignments, enhancing the model’s ability to handle noisy correspondence. We conduct joint training of the main network and MCN to achieve dynamic correction through a bi-level optimization framework. Experimental evaluations on three public benchmark datasets demonstrate that our proposed method delivers robust performance improvements over state-of-the-art graph matching solutions and exhibits excellent stability when handling images under complex conditions.
•First use of meta-learning for correcting noisy correspondences in graph matching.•Generate matching confidence using global features and geometric consistency.•Bi-level optimization framework for joint training.•Significant performance and noise robustness on public benchmark datasets. |
| ArticleNumber | 104433 |
| Author | Yin, Yilong Lu, Xiankai Meng, Wenjia Li, Fangkai Pan, Feiyu Sun, Haoliang Nie, Xiushan |
| Author_xml | – sequence: 1 givenname: Fangkai orcidid: 0009-0008-0549-7315 surname: Li fullname: Li, Fangkai email: lifangkai@mail.sdu.edu.cn organization: School of Software, Shandong University, Jinan, 250101, Shandong, China – sequence: 2 givenname: Feiyu orcidid: 0009-0000-8796-2680 surname: Pan fullname: Pan, Feiyu email: panfeiyu@mail.sdu.edu.cn organization: School of Software, Shandong University, Jinan, 250101, Shandong, China – sequence: 3 givenname: Wenjia surname: Meng fullname: Meng, Wenjia email: wjmeng@sdu.edu.cn organization: School of Software, Shandong University, Jinan, 250101, Shandong, China – sequence: 4 givenname: Haoliang orcidid: 0000-0001-7715-5682 surname: Sun fullname: Sun, Haoliang email: haolsun@sdu.edu.cn organization: School of Software, Shandong University, Jinan, 250101, Shandong, China – sequence: 5 givenname: Xiushan surname: Nie fullname: Nie, Xiushan email: niexiushan19@sdjzu.edu.cn organization: School of Computer Science and Technology, Shandong Jianzhu University, Jinan, 250101, Shandong, China – sequence: 6 givenname: Yilong surname: Yin fullname: Yin, Yilong email: ylyin@sdu.edu.cn organization: School of Software, Shandong University, Jinan, 250101, Shandong, China – sequence: 7 givenname: Xiankai surname: Lu fullname: Lu, Xiankai email: carrierlxk@gmail.com organization: School of Software, Shandong University, Jinan, 250101, Shandong, China |
| BookMark | eNp9j01Lw0AQhvdQwbb6BzzlDyTuZ9KAHiSoFQpe9LzsTibtBpMtu7HQf29CcvY0w_A-w_tsyKr3PRLywGjGKMsf2wwu7jfjlKvxIKUQK7JmtChSwSS_JZsYW0oZkyVbk-cq-BjTYzDnU9LhYJLODHBy_TEBHwLC4HyfND4kvXfxmizBJXNHbhrzE_F-mVvy_fb6Ve3Tw-f7R_VySIErMaRIawvAC8u5UELWEqxs0HJTSyV3O8tqW1opmhIB0dJcFZgDSqPGtVGYiy3h81-Y2gZs9Dm4zoSrZlRP0rrVk7SepPUsPUJPM4Rjs4vDoCM47AFrN3np2rv_8D-wTGVW |
| Cites_doi | 10.1109/ICCV.2009.5459303 10.1002/nav.3800020109 10.1016/j.ejor.2005.09.032 10.1109/CVPR46437.2021.00503 10.1007/s11263-020-01359-2 10.1109/ICRA40945.2020.9197023 10.1016/j.patcog.2022.109059 10.1609/aaai.v38i13.29392 10.1214/aoms/1177729586 10.1109/TPAMI.2022.3155499 10.1109/CVPR.2018.00097 10.1007/978-3-031-20050-2_22 10.1214/aoms/1177703591 10.1109/ICCV.2019.00315 10.1145/2911996.2912035 10.1109/ICCV51070.2023.02135 10.1007/978-3-030-58604-1_25 10.1109/DSW.2018.8439919 10.1109/CVPR.2014.471 10.1109/ICCV.2013.11 10.1109/CVPR.2018.00284 10.1609/aaai.v35i12.17319 10.1109/CVPR52688.2022.00656 10.1109/CVPR52688.2022.01483 10.1109/CVPR42600.2020.00759 10.1109/CVPR52729.2023.00726 10.1007/978-3-031-19812-0_6 10.1145/3503161.3547922 10.1109/TPAMI.2008.245 10.1109/CVPR.2016.465 10.1109/TPAMI.2017.2716350 10.1109/TPAMI.2015.2501802 10.1016/S0968-090X(00)00026-7 10.1007/s10044-008-0141-y 10.1016/j.cviu.2018.01.001 10.1016/j.cviu.2023.103803 10.1109/CVPR42600.2020.00458 10.1109/TPAMI.2020.3005590 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier Inc. |
| Copyright_xml | – notice: 2025 Elsevier Inc. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.cviu.2025.104433 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering Computer Science |
| ExternalDocumentID | 10_1016_j_cviu_2025_104433 S1077314225001560 |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 6TJ 7-5 71M 8P~ AABNK AAEDT AAEDW AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABEFU ABFNM ABJNI ABMAC ABWVN ABXDB ACDAQ ACGFS ACNNM ACRLP ACRPL ACVFH ACZNC ADBBV ADCNI ADEZE ADFGL ADJOM ADMUD ADNMO ADTZH AEBSH AECPX AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AGCQF AGHFR AGQPQ AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD APXCP ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CAG COF CS3 DM4 DU5 EBS EFBJH EFKBS EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HF~ HVGLF HZ~ IHE J1W JJJVA KOM LG5 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RNS ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SST SSV SSZ T5K TN5 XPP ZMT ~G- AAYXX CITATION |
| ID | FETCH-LOGICAL-c253t-e0dbcc27b223534d4cb4feb2ad45488b1db9b43f9eceeb0657e6ce4a5065f5e63 |
| IEDL.DBID | AIKHN |
| ISSN | 1077-3142 |
| IngestDate | Wed Aug 27 16:27:11 EDT 2025 Sat Sep 06 17:18:04 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Bi-level optimization Noisy correspondence Graph matching Meta learning |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c253t-e0dbcc27b223534d4cb4feb2ad45488b1db9b43f9eceeb0657e6ce4a5065f5e63 |
| ORCID | 0009-0008-0549-7315 0009-0000-8796-2680 0000-0001-7715-5682 |
| ParticipantIDs | crossref_primary_10_1016_j_cviu_2025_104433 elsevier_sciencedirect_doi_10_1016_j_cviu_2025_104433 |
| PublicationCentury | 2000 |
| PublicationDate | September 2025 2025-09-00 |
| PublicationDateYYYYMMDD | 2025-09-01 |
| PublicationDate_xml | – month: 09 year: 2025 text: September 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Computer vision and image understanding |
| PublicationYear | 2025 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Zhou, De la Torre (b54) 2015; 38 Rolínek, M., Swoboda, P., Zietlow, D., Paulus, A., Musil, V., Martius, G., 2020. Deep graph matching via blackbox differentiation of combinatorial solvers. In: Proceedings of the IEEE Proceedings of the European Conference on Computer Vision. pp. 407–424. Wang, Z., Hu, G., Hu, Q., 2020a. Training noise-robust deep neural networks via meta-learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 4524–4533. Zhou, L., Wang, S., Kaess, M., 2020. A fast and accurate solution for pose estimation from 3D correspondences. In: International Conference on Robotics and Automation. pp. 1308–1314. Zhang, Herrmann, Hur, Chen, Jampani, Sun, Yang (b51) 2023 Bourdev, L., Malik, J., 2009. Poselets: Body part detectors trained using 3D human pose annotations. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 1365–1372. Sinkhorn (b34) 1964; 35 Zheng, G., Awadallah, A.H., Dumais, S., 2021. Meta label correction for noisy label learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp. 11053–11061. Moskalev, A., Sosnovik, I., Fischer, V., Smeulders, A., 2022. Contrasting quadratic assignments for set-based representation learning. In: Proceedings of European Conference on Computer Vision. pp. 88–104. Wang, Ling (b37) 2017; 40 Xu, Luo, Carin (b43) 2019; 32 Yu, Sun, Yang, Rui, Yao (b47) 2018; 169 Han, Zheng, Luo, Miao, Tian, Chen (b9) 2024 Ren, Q., Bao, Q., Wang, R., Yan, J., 2022. Appearance and structure aware robust deep visual graph matching: Attack, defense and beyond. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 15263–15272. Fey, M., Lenssen, J.E., Morris, C., Masci, J., Kriege, N.M., 2019. Deep Graph Matching Consensus. In: Proceedings of the International Conference on Learning Representations. Yan, J., Yin, X.-C., Lin, W., Deng, C., Zha, H., Yang, X., 2016. A short survey of recent advances in graph matching. In: Proceedings of ACM on International Conference on Multimedia Retrieval. pp. 167–174. Jiang, Zhang, Zhang, Ma (b11) 2023; 235 Leordeanu, Hebert (b15) 2005; vol. 2 Zanfir, A., Sminchisescu, C., 2018. Deep learning of graph matching. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 2684–2693. White, Bernstein, Kornhauser (b42) 2000; 8 Zhou, Jia, Lin, Quan, Zhao, Lyu (b53) 2024; 36 Ma, Jiang, Fan, Jiang, Yan (b22) 2021; 129 Simonyan, K., Zisserman, A., 2015. Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations. Liu, C., Zhang, S., Yang, X., Yan, J., 2022. Self-supervised learning of visual graph matching. In: Proceedings of the European Conference on Computer Vision. pp. 370–388. Loiola, De Abreu, Boaventura-Netto, Hahn, Querido (b21) 2007; 176 Huang, Niu, Liu, Ding, Xiao, Wu, Peng (b10) 2021; 34 Gao, Q., Wang, F., Xue, N., Yu, J.-G., Xia, G.-S., 2021. Deep graph matching under quadratic constraint. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 5069–5078. Kuhn (b14) 1955; 2 Yang, Li, Hu, Bai, Lv, Peng (b45) 2022; 45 Yu, T., Wang, R., Yan, J., Li, B., 2019. Learning deep graph matching with channel-independent embedding and hungarian attention. In: Proceedings of the International Conference on Learning Representations. Wang, T., Liu, H., Li, Y., Jin, Y., Hou, X., Ling, H., 2020c. Learning combinatorial solver for graph matching. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 13–19. Robbins, Monro (b31) 1951 Que, X., Yu, Q., 2024. Dual-Level Curriculum Meta-Learning for Noisy Few-Shot Learning Tasks. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp. 14740–14748. Wang, Yan, Yang (b40) 2020; 45 Yew, Z.J., Lee, G.H., 2022. Regtr: End-to-end point cloud correspondences with transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 6677–6686. Qin, Y., Peng, D., Peng, X., Wang, X., Hu, P., 2022. Deep evidential learning with noisy correspondence for cross-modal retrieval. In: Proceedings of the ACM International Conference on Multimedia. pp. 4948–4956. Nam, H., Han, B., 2016. Learning multi-domain convolutional neural networks for visual tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 4293–4302. Qin, Chen, Peng, Peng, Zhou, Hu (b27) 2023 Wang, Hua, Liu, Zhang, Yan, Qi, Yang, Zhou, Yang (b36) 2021; 34 Gao, Xiao, Tao, Li (b7) 2010; 13 Cho, M., Alahari, K., Ponce, J., 2013. Learning graphs to match. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 25–32. Wang, R., Yan, J., Yang, X., 2019. Learning combinatorial embedding networks for deep graph matching. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 3056–3065. Kipf, T.N., Welling, M., 2016. Semi-Supervised Classification with Graph Convolutional Networks. In: Proceedings of the International Conference on Learning Representations. Kingma, D., 2014. Adam: a method for stochastic optimization. In: Proceedings of the Proceedings of International Conference on Machine Learning. Min, Lee, Ponce, Cho (b23) 2019 Fey, M., Lenssen, J.E., Weichert, F., Müller, H., 2018. Splinecnn: Fast geometric deep learning with continuous b-spline kernels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 869–877. Lin, Zhang, Huang, Liu, Wen, Peng (b18) 2024 Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B., 2014. 2d human pose estimation: New benchmark and state of the art analysis. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 3686–3693. Liu, Wang, Li, Lang, Jin, Ling (b19) 2023; 134 Han, H., Miao, K., Zheng, Q., Luo, M., 2023. Noisy correspondence learning with meta similarity correction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 7517–7526. Nowak, A., Villar, S., Bandeira, A.S., Bruna, J., 2018. Revised note on learning quadratic assignment with graph neural networks. In: Proceedings of the IEEE Data Science Workshop. pp. 1–5. Wang, Yan, Yang (b41) 2021; 44 Zaslavskiy, Bach, Vert (b50) 2008; 31 Li, Yang, Song, Hospedales (b16) 2018; vol. 32 Lin, Y., Yang, M., Yu, J., Hu, P., Zhang, C., Peng, X., 2023. Graph matching with bi-level noisy correspondence. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 23362–23371. 10.1016/j.cviu.2025.104433_b20 Wang (10.1016/j.cviu.2025.104433_b40) 2020; 45 Li (10.1016/j.cviu.2025.104433_b16) 2018; vol. 32 Ma (10.1016/j.cviu.2025.104433_b22) 2021; 129 Wang (10.1016/j.cviu.2025.104433_b37) 2017; 40 Jiang (10.1016/j.cviu.2025.104433_b11) 2023; 235 Yang (10.1016/j.cviu.2025.104433_b45) 2022; 45 Leordeanu (10.1016/j.cviu.2025.104433_b15) 2005; vol. 2 10.1016/j.cviu.2025.104433_b17 White (10.1016/j.cviu.2025.104433_b42) 2000; 8 10.1016/j.cviu.2025.104433_b13 10.1016/j.cviu.2025.104433_b12 10.1016/j.cviu.2025.104433_b55 10.1016/j.cviu.2025.104433_b52 Qin (10.1016/j.cviu.2025.104433_b27) 2023 Kuhn (10.1016/j.cviu.2025.104433_b14) 1955; 2 Robbins (10.1016/j.cviu.2025.104433_b31) 1951 Sinkhorn (10.1016/j.cviu.2025.104433_b34) 1964; 35 Zhou (10.1016/j.cviu.2025.104433_b53) 2024; 36 Xu (10.1016/j.cviu.2025.104433_b43) 2019; 32 Wang (10.1016/j.cviu.2025.104433_b36) 2021; 34 Wang (10.1016/j.cviu.2025.104433_b41) 2021; 44 10.1016/j.cviu.2025.104433_b49 10.1016/j.cviu.2025.104433_b48 10.1016/j.cviu.2025.104433_b46 10.1016/j.cviu.2025.104433_b44 Zaslavskiy (10.1016/j.cviu.2025.104433_b50) 2008; 31 Loiola (10.1016/j.cviu.2025.104433_b21) 2007; 176 10.1016/j.cviu.2025.104433_b8 Zhou (10.1016/j.cviu.2025.104433_b54) 2015; 38 10.1016/j.cviu.2025.104433_b5 Gao (10.1016/j.cviu.2025.104433_b7) 2010; 13 10.1016/j.cviu.2025.104433_b4 Min (10.1016/j.cviu.2025.104433_b23) 2019 10.1016/j.cviu.2025.104433_b39 10.1016/j.cviu.2025.104433_b38 10.1016/j.cviu.2025.104433_b6 10.1016/j.cviu.2025.104433_b1 10.1016/j.cviu.2025.104433_b35 10.1016/j.cviu.2025.104433_b3 10.1016/j.cviu.2025.104433_b2 10.1016/j.cviu.2025.104433_b33 10.1016/j.cviu.2025.104433_b32 10.1016/j.cviu.2025.104433_b30 Lin (10.1016/j.cviu.2025.104433_b18) 2024 Zhang (10.1016/j.cviu.2025.104433_b51) 2023 Huang (10.1016/j.cviu.2025.104433_b10) 2021; 34 Liu (10.1016/j.cviu.2025.104433_b19) 2023; 134 Han (10.1016/j.cviu.2025.104433_b9) 2024 10.1016/j.cviu.2025.104433_b29 10.1016/j.cviu.2025.104433_b28 Yu (10.1016/j.cviu.2025.104433_b47) 2018; 169 10.1016/j.cviu.2025.104433_b26 10.1016/j.cviu.2025.104433_b25 10.1016/j.cviu.2025.104433_b24 |
| References_xml | – year: 2024 ident: b9 article-title: Noise-tolerant learning for audio-visual action recognition publication-title: IEEE Trans. Multimed. – volume: 2 start-page: 83 year: 1955 end-page: 97 ident: b14 article-title: The hungarian method for the assignment problem publication-title: Nav. Res. Logist. Q. – reference: Zheng, G., Awadallah, A.H., Dumais, S., 2021. Meta label correction for noisy label learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp. 11053–11061. – volume: 32 year: 2019 ident: b43 article-title: Scalable Gromov-Wasserstein learning for graph partitioning and matching publication-title: Adv. Neural Inf. Process. Syst. – volume: 235 year: 2023 ident: b11 article-title: Improving sparse graph attention for feature matching by informative keypoints exploration publication-title: Comput. Vis. Image Underst. – reference: Ren, Q., Bao, Q., Wang, R., Yan, J., 2022. Appearance and structure aware robust deep visual graph matching: Attack, defense and beyond. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 15263–15272. – reference: Kipf, T.N., Welling, M., 2016. Semi-Supervised Classification with Graph Convolutional Networks. In: Proceedings of the International Conference on Learning Representations. – volume: 40 start-page: 1494 year: 2017 end-page: 1501 ident: b37 article-title: Gracker: A graph-based planar object tracker publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 169 start-page: 40 year: 2018 end-page: 51 ident: b47 article-title: Hierarchical semantic image matching using CNN feature pyramid publication-title: Comput. Vis. Image Underst. – reference: Zanfir, A., Sminchisescu, C., 2018. Deep learning of graph matching. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 2684–2693. – year: 2023 ident: b27 article-title: Noisy-correspondence learning for text-to-image person re-identification – reference: Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B., 2014. 2d human pose estimation: New benchmark and state of the art analysis. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 3686–3693. – volume: 134 year: 2023 ident: b19 article-title: Joint graph learning and matching for semantic feature correspondence publication-title: Pattern Recognit. – reference: Wang, T., Liu, H., Li, Y., Jin, Y., Hou, X., Ling, H., 2020c. Learning combinatorial solver for graph matching. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 13–19. – reference: Yan, J., Yin, X.-C., Lin, W., Deng, C., Zha, H., Yang, X., 2016. A short survey of recent advances in graph matching. In: Proceedings of ACM on International Conference on Multimedia Retrieval. pp. 167–174. – reference: Fey, M., Lenssen, J.E., Weichert, F., Müller, H., 2018. Splinecnn: Fast geometric deep learning with continuous b-spline kernels. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 869–877. – volume: 8 start-page: 91 year: 2000 end-page: 108 ident: b42 article-title: Some map matching algorithms for personal navigation assistants publication-title: Transp. Res. Part C: Emerg. Technol. – volume: 38 start-page: 1774 year: 2015 end-page: 1789 ident: b54 article-title: Factorized graph matching publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: Nam, H., Han, B., 2016. Learning multi-domain convolutional neural networks for visual tracking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 4293–4302. – reference: Nowak, A., Villar, S., Bandeira, A.S., Bruna, J., 2018. Revised note on learning quadratic assignment with graph neural networks. In: Proceedings of the IEEE Data Science Workshop. pp. 1–5. – volume: 35 start-page: 876 year: 1964 end-page: 879 ident: b34 article-title: A relationship between arbitrary positive matrices and doubly stochastic matrices publication-title: Ann. Math. Stat. – volume: 34 start-page: 21453 year: 2021 end-page: 21466 ident: b36 article-title: A bi-level framework for learning to solve combinatorial optimization on graphs publication-title: Adv. Neural Inf. Process. Syst. – reference: Liu, C., Zhang, S., Yang, X., Yan, J., 2022. Self-supervised learning of visual graph matching. In: Proceedings of the European Conference on Computer Vision. pp. 370–388. – reference: Gao, Q., Wang, F., Xue, N., Yu, J.-G., Xia, G.-S., 2021. Deep graph matching under quadratic constraint. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 5069–5078. – year: 2019 ident: b23 article-title: Spair-71k: A large-scale benchmark for semantic correspondence – year: 2023 ident: b51 article-title: Telling left from right: Identifying geometry-aware semantic correspondence – volume: 36 year: 2024 ident: b53 article-title: Improving graph matching with positional reconstruction encoder-decoder network publication-title: Adv. Neural Inf. Process. Syst. – volume: vol. 2 start-page: 1482 year: 2005 end-page: 1489 ident: b15 article-title: A spectral technique for correspondence problems using pairwise constraints publication-title: Proceedings of the IEEE International Conference on Computer Vision – volume: 13 start-page: 113 year: 2010 end-page: 129 ident: b7 article-title: A survey of graph edit distance publication-title: Pattern Anal. Appl. – reference: Rolínek, M., Swoboda, P., Zietlow, D., Paulus, A., Musil, V., Martius, G., 2020. Deep graph matching via blackbox differentiation of combinatorial solvers. In: Proceedings of the IEEE Proceedings of the European Conference on Computer Vision. pp. 407–424. – reference: Fey, M., Lenssen, J.E., Morris, C., Masci, J., Kriege, N.M., 2019. Deep Graph Matching Consensus. In: Proceedings of the International Conference on Learning Representations. – reference: Simonyan, K., Zisserman, A., 2015. Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations. – reference: Wang, Z., Hu, G., Hu, Q., 2020a. Training noise-robust deep neural networks via meta-learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 4524–4533. – reference: Kingma, D., 2014. Adam: a method for stochastic optimization. In: Proceedings of the Proceedings of International Conference on Machine Learning. – reference: Bourdev, L., Malik, J., 2009. Poselets: Body part detectors trained using 3D human pose annotations. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 1365–1372. – reference: Yew, Z.J., Lee, G.H., 2022. Regtr: End-to-end point cloud correspondences with transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 6677–6686. – start-page: 400 year: 1951 end-page: 407 ident: b31 article-title: A stochastic approximation method publication-title: Ann. Math. Stat. – reference: Moskalev, A., Sosnovik, I., Fischer, V., Smeulders, A., 2022. Contrasting quadratic assignments for set-based representation learning. In: Proceedings of European Conference on Computer Vision. pp. 88–104. – reference: Yu, T., Wang, R., Yan, J., Li, B., 2019. Learning deep graph matching with channel-independent embedding and hungarian attention. In: Proceedings of the International Conference on Learning Representations. – volume: vol. 32 year: 2018 ident: b16 article-title: Learning to generalize: Meta-learning for domain generalization publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – volume: 31 start-page: 2227 year: 2008 end-page: 2242 ident: b50 article-title: A path following algorithm for the graph matching problem publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2024 ident: b18 article-title: Multi-granularity correspondence learning from long-term noisy videos – volume: 44 start-page: 5261 year: 2021 end-page: 5279 ident: b41 article-title: Neural graph matching network: Learning Lawler’s quadratic assignment problem with extension to hypergraph and multiple-graph matching publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 129 start-page: 23 year: 2021 end-page: 79 ident: b22 article-title: Image matching from handcrafted to deep features: A survey publication-title: Int. J. Comput. Vis. – reference: Zhou, L., Wang, S., Kaess, M., 2020. A fast and accurate solution for pose estimation from 3D correspondences. In: International Conference on Robotics and Automation. pp. 1308–1314. – reference: Cho, M., Alahari, K., Ponce, J., 2013. Learning graphs to match. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 25–32. – reference: Han, H., Miao, K., Zheng, Q., Luo, M., 2023. Noisy correspondence learning with meta similarity correction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 7517–7526. – volume: 45 start-page: 1055 year: 2022 end-page: 1069 ident: b45 article-title: Robust multi-view clustering with incomplete information publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 34 start-page: 29406 year: 2021 end-page: 29419 ident: b10 article-title: Learning with noisy correspondence for cross-modal matching publication-title: Adv. Neural Inf. Process. Syst. – reference: Lin, Y., Yang, M., Yu, J., Hu, P., Zhang, C., Peng, X., 2023. Graph matching with bi-level noisy correspondence. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 23362–23371. – volume: 45 start-page: 6984 year: 2020 end-page: 7000 ident: b40 article-title: Combinatorial learning of robust deep graph matching: an embedding based approach publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: Qin, Y., Peng, D., Peng, X., Wang, X., Hu, P., 2022. Deep evidential learning with noisy correspondence for cross-modal retrieval. In: Proceedings of the ACM International Conference on Multimedia. pp. 4948–4956. – reference: Wang, R., Yan, J., Yang, X., 2019. Learning combinatorial embedding networks for deep graph matching. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 3056–3065. – volume: 176 start-page: 657 year: 2007 end-page: 690 ident: b21 article-title: A survey for the quadratic assignment problem publication-title: European J. Oper. Res. – reference: Que, X., Yu, Q., 2024. Dual-Level Curriculum Meta-Learning for Noisy Few-Shot Learning Tasks. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp. 14740–14748. – ident: 10.1016/j.cviu.2025.104433_b2 doi: 10.1109/ICCV.2009.5459303 – volume: 2 start-page: 83 issue: 1–2 year: 1955 ident: 10.1016/j.cviu.2025.104433_b14 article-title: The hungarian method for the assignment problem publication-title: Nav. Res. Logist. Q. doi: 10.1002/nav.3800020109 – volume: 176 start-page: 657 issue: 2 year: 2007 ident: 10.1016/j.cviu.2025.104433_b21 article-title: A survey for the quadratic assignment problem publication-title: European J. Oper. Res. doi: 10.1016/j.ejor.2005.09.032 – ident: 10.1016/j.cviu.2025.104433_b6 doi: 10.1109/CVPR46437.2021.00503 – volume: 129 start-page: 23 issue: 1 year: 2021 ident: 10.1016/j.cviu.2025.104433_b22 article-title: Image matching from handcrafted to deep features: A survey publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-020-01359-2 – ident: 10.1016/j.cviu.2025.104433_b55 doi: 10.1109/ICRA40945.2020.9197023 – ident: 10.1016/j.cviu.2025.104433_b4 – volume: 134 year: 2023 ident: 10.1016/j.cviu.2025.104433_b19 article-title: Joint graph learning and matching for semantic feature correspondence publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2022.109059 – ident: 10.1016/j.cviu.2025.104433_b12 – ident: 10.1016/j.cviu.2025.104433_b29 doi: 10.1609/aaai.v38i13.29392 – start-page: 400 year: 1951 ident: 10.1016/j.cviu.2025.104433_b31 article-title: A stochastic approximation method publication-title: Ann. Math. Stat. doi: 10.1214/aoms/1177729586 – volume: 45 start-page: 1055 issue: 1 year: 2022 ident: 10.1016/j.cviu.2025.104433_b45 article-title: Robust multi-view clustering with incomplete information publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2022.3155499 – ident: 10.1016/j.cviu.2025.104433_b5 doi: 10.1109/CVPR.2018.00097 – ident: 10.1016/j.cviu.2025.104433_b20 doi: 10.1007/978-3-031-20050-2_22 – year: 2023 ident: 10.1016/j.cviu.2025.104433_b51 – volume: 35 start-page: 876 issue: 2 year: 1964 ident: 10.1016/j.cviu.2025.104433_b34 article-title: A relationship between arbitrary positive matrices and doubly stochastic matrices publication-title: Ann. Math. Stat. doi: 10.1214/aoms/1177703591 – ident: 10.1016/j.cviu.2025.104433_b39 doi: 10.1109/ICCV.2019.00315 – ident: 10.1016/j.cviu.2025.104433_b44 doi: 10.1145/2911996.2912035 – ident: 10.1016/j.cviu.2025.104433_b17 doi: 10.1109/ICCV51070.2023.02135 – ident: 10.1016/j.cviu.2025.104433_b32 doi: 10.1007/978-3-030-58604-1_25 – ident: 10.1016/j.cviu.2025.104433_b48 – ident: 10.1016/j.cviu.2025.104433_b26 doi: 10.1109/DSW.2018.8439919 – ident: 10.1016/j.cviu.2025.104433_b1 doi: 10.1109/CVPR.2014.471 – ident: 10.1016/j.cviu.2025.104433_b13 – ident: 10.1016/j.cviu.2025.104433_b33 – volume: 34 start-page: 21453 year: 2021 ident: 10.1016/j.cviu.2025.104433_b36 article-title: A bi-level framework for learning to solve combinatorial optimization on graphs publication-title: Adv. Neural Inf. Process. Syst. – year: 2024 ident: 10.1016/j.cviu.2025.104433_b9 article-title: Noise-tolerant learning for audio-visual action recognition publication-title: IEEE Trans. Multimed. – ident: 10.1016/j.cviu.2025.104433_b3 doi: 10.1109/ICCV.2013.11 – ident: 10.1016/j.cviu.2025.104433_b49 doi: 10.1109/CVPR.2018.00284 – ident: 10.1016/j.cviu.2025.104433_b52 doi: 10.1609/aaai.v35i12.17319 – ident: 10.1016/j.cviu.2025.104433_b46 doi: 10.1109/CVPR52688.2022.00656 – volume: 44 start-page: 5261 issue: 9 year: 2021 ident: 10.1016/j.cviu.2025.104433_b41 article-title: Neural graph matching network: Learning Lawler’s quadratic assignment problem with extension to hypergraph and multiple-graph matching publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – ident: 10.1016/j.cviu.2025.104433_b30 doi: 10.1109/CVPR52688.2022.01483 – year: 2019 ident: 10.1016/j.cviu.2025.104433_b23 – ident: 10.1016/j.cviu.2025.104433_b38 doi: 10.1109/CVPR42600.2020.00759 – ident: 10.1016/j.cviu.2025.104433_b8 doi: 10.1109/CVPR52729.2023.00726 – ident: 10.1016/j.cviu.2025.104433_b24 doi: 10.1007/978-3-031-19812-0_6 – ident: 10.1016/j.cviu.2025.104433_b28 doi: 10.1145/3503161.3547922 – volume: 32 year: 2019 ident: 10.1016/j.cviu.2025.104433_b43 article-title: Scalable Gromov-Wasserstein learning for graph partitioning and matching publication-title: Adv. Neural Inf. Process. Syst. – year: 2023 ident: 10.1016/j.cviu.2025.104433_b27 – volume: 36 year: 2024 ident: 10.1016/j.cviu.2025.104433_b53 article-title: Improving graph matching with positional reconstruction encoder-decoder network publication-title: Adv. Neural Inf. Process. Syst. – volume: 31 start-page: 2227 issue: 12 year: 2008 ident: 10.1016/j.cviu.2025.104433_b50 article-title: A path following algorithm for the graph matching problem publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2008.245 – ident: 10.1016/j.cviu.2025.104433_b25 doi: 10.1109/CVPR.2016.465 – volume: 40 start-page: 1494 issue: 6 year: 2017 ident: 10.1016/j.cviu.2025.104433_b37 article-title: Gracker: A graph-based planar object tracker publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2017.2716350 – volume: 38 start-page: 1774 issue: 9 year: 2015 ident: 10.1016/j.cviu.2025.104433_b54 article-title: Factorized graph matching publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2015.2501802 – volume: vol. 2 start-page: 1482 year: 2005 ident: 10.1016/j.cviu.2025.104433_b15 article-title: A spectral technique for correspondence problems using pairwise constraints – volume: 34 start-page: 29406 year: 2021 ident: 10.1016/j.cviu.2025.104433_b10 article-title: Learning with noisy correspondence for cross-modal matching publication-title: Adv. Neural Inf. Process. Syst. – volume: 8 start-page: 91 issue: 1–6 year: 2000 ident: 10.1016/j.cviu.2025.104433_b42 article-title: Some map matching algorithms for personal navigation assistants publication-title: Transp. Res. Part C: Emerg. Technol. doi: 10.1016/S0968-090X(00)00026-7 – year: 2024 ident: 10.1016/j.cviu.2025.104433_b18 – volume: vol. 32 year: 2018 ident: 10.1016/j.cviu.2025.104433_b16 article-title: Learning to generalize: Meta-learning for domain generalization – volume: 13 start-page: 113 year: 2010 ident: 10.1016/j.cviu.2025.104433_b7 article-title: A survey of graph edit distance publication-title: Pattern Anal. Appl. doi: 10.1007/s10044-008-0141-y – volume: 169 start-page: 40 year: 2018 ident: 10.1016/j.cviu.2025.104433_b47 article-title: Hierarchical semantic image matching using CNN feature pyramid publication-title: Comput. Vis. Image Underst. doi: 10.1016/j.cviu.2018.01.001 – volume: 235 year: 2023 ident: 10.1016/j.cviu.2025.104433_b11 article-title: Improving sparse graph attention for feature matching by informative keypoints exploration publication-title: Comput. Vis. Image Underst. doi: 10.1016/j.cviu.2023.103803 – ident: 10.1016/j.cviu.2025.104433_b35 doi: 10.1109/CVPR42600.2020.00458 – volume: 45 start-page: 6984 issue: 6 year: 2020 ident: 10.1016/j.cviu.2025.104433_b40 article-title: Combinatorial learning of robust deep graph matching: an embedding based approach publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2020.3005590 |
| SSID | ssj0011491 |
| Score | 2.4599915 |
| Snippet | In recent years, significant advancements have been made in image feature point matching within the context of deep graph matching. However, keypoint... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 104433 |
| SubjectTerms | Bi-level optimization Graph matching Meta learning Noisy correspondence |
| Title | Cross-graph meta matching correction for noisy graph matching |
| URI | https://dx.doi.org/10.1016/j.cviu.2025.104433 |
| Volume | 259 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEB76uOjBR1Wsj7IHbxLbzT7SHDyUolTFXrTQW8g-AhFMi00FL_52d7MbqSAevIRk2CVhksx8s_PNLMBFlR7LuA4oFuYQyywQLKOBwCkXhMZDLG2g-Djlkxm9n7N5A8Z1LYylVXrb72x6Za29pO-12V_mef_JBC4RsUsYzNUDN6EdkpizFrRHdw-T6XcywQQB2FEP7ZIcDX3tjKN5yfd8bcLEkNlsJyXkd_-04XNu92DHg0U0cs-zDw1ddGDXA0fkf8uVEdV7M9SyDmxvNBo8gOuxvVlQdadGr7pMkQGqFYsSSbs9R1XcgAx-RcUiX30gP9CPOYTZ7c3zeBL4jRMCGTJSBnqghJRhJIzvZ4QqKgXNTAidKmoClKHASsSCkizWxkUKA0IizaWmKTOnGdOcHEGrWBT6GBCXaiC4iHDMUjpkNM2YIukAqzhVWhHehctaXcnS9cdIauLYS2KVm1jlJk65XWC1RpMfbzkxBvyPeSf_nHcKW_bKccLOoFW-rfW5ARGl6EHz6hP3_KfyBRSRxos |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEB5qPagHH1WxPvfgTdY23UeagwcplqptL7bgLewrEMG02FTw4m93N9lIBfHgJYTNLAmTZOab3W9mAC6L7bGEG0wDaQ-RSrBkCcUyEFwSGnUD5QLF0ZgPpvThmT3XoFflwjhapbf9pU0vrLUfaXlttuZp2nqygUtI3BIGK_OB12CdMhI6Xt_15zfPw-L9om2ek8ZO3GfOlCQv9Z4ubZDYYW6vkxLyu3da8Tj9Xdj2UBHdlk-zBzWTNWDHw0bkf8qFHao6M1RjDdhaKTO4Dzc9dzNc1KZGryYXyMLUgkOJlGvOUaQ2IIteUTZLFx_IC3qZA5j27ya9AfZtE7DqMJJj09ZSqU4orednhGqqJE1sAC00teFJVwZaRpKSJDLWQUoLQULDlaGC2dOEGU4OoZ7NMnMEiCvdllyGQcQE7TIqEqaJaAc6EtpowptwVakrnpfVMeKKNvYSO-XGTrlxqdwmsEqj8Y93HFvz_ce843_Ou4CNwWQ0jIf348cT2HRXSnbYKdTzt6U5s3Ail-fF5_IFvJ7HVg |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Cross-graph+meta+matching+correction+for+noisy+graph+matching&rft.jtitle=Computer+vision+and+image+understanding&rft.au=Li%2C+Fangkai&rft.au=Pan%2C+Feiyu&rft.au=Meng%2C+Wenjia&rft.au=Sun%2C+Haoliang&rft.date=2025-09-01&rft.pub=Elsevier+Inc&rft.issn=1077-3142&rft.volume=259&rft_id=info:doi/10.1016%2Fj.cviu.2025.104433&rft.externalDocID=S1077314225001560 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1077-3142&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1077-3142&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1077-3142&client=summon |