mlsanityData to 7 Oct 2026

Graph Matching with Bi-level Noisy Correspondence

arXiv 2212.04085 ↗First posted 8 Dec 2022cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

In this paper, we study a novel and widely existing problem in graph matching (GM), namely, Bi-level Noisy Correspondence (BNC), which refers to node-level noisy correspondence (NNC) and edge-level noisy correspondence (ENC). In brief, on the one hand, due to the poor recognizability and viewpoint differences between images, it is inevitable to inaccurately annotate some keypoints with offset and confusion, leading to the mismatch between two associated nodes, i.e., NNC. On the other hand, the noisy node-to-node correspondence will further contaminate the edge-to-edge correspondence, thus leading to ENC. For the BNC challenge, we propose a novel method termed Contrastive Matching with Momentum Distillation. Specifically, the proposed method is with a robust quadratic contrastive loss which enjoys the following merits: i) better exploring the node-to-node and edge-to-edge correlations through a GM customized quadratic contrastive learning paradigm; ii) adaptively penalizing the noisy assignments based on the confidence estimated by the momentum teacher. Extensive experiments on three real-world datasets show the robustness of our model compared with 12 competitive baselines. The code is available at https://github.com/XLearning-SCU/2023-ICCV-COMMON.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 37 of its 64 references that are in the map. First posted on arXiv 8 Dec 2022.

Builds on

37 of 64 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  8. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  9. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  10. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  11. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  12. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
25 more
  1. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  2. 2017A Closer Look at Memorization in Deep Networkscited by 936
  3. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  4. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  5. 2016Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Agecited by 405
  6. 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297
  7. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  8. 2017SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernelscited by 160
  9. 2020Unsupervised Learning of Dense Visual Representationscited by 147
  10. 2019SPair-71k: A Large-scale Benchmark for Semantic Correspondencecited by 140
  11. 2022CyCLIP: Cyclic Contrastive Language-Image Pretrainingcited by 127
  12. 2019Learning Combinatorial Embedding Networks for Deep Graph Matchingcited by 98
  13. 2020Deep Graph Matching Consensuscited by 85
  14. 2019Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matchingcited by 83
  15. 2020Deep Graph Matching via Blackbox Differentiation of Combinatorial Solverscited by 81
  16. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  17. 2022Twin Contrastive Learning for Online Clusteringcited by 60
  18. 2022Learning with Neighbor Consistency for Noisy Labelscited by 55
  19. 2021Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Trackingcited by 37
  20. 2021Deep Graph Matching under Quadratic Constraintcited by 18
  21. 2020Graph Edit Distance Reward: Learning to Edit Scene Graphcited by 14
  22. 2021Stochastic Iterative Graph Matchingcited by 10
  23. 2021Joint Graph Learning and Matching for Semantic Feature Correspondencecited by 8
  24. 2022Contrasting quadratic assignments for set-based representation learningcited by 6
  25. 2020Zero-Assignment Constraint for Graph Matching with Outlierscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 9; 2024: 13; 2025: 6; 2026: 2.

30 papers.

Sort:

  1. 2024Multi-granularity Correspondence Learning from Long-term Noisy Videoscited by 34
  2. 2023Decoupled Contrastive Multi-View Clustering with High-Order Random Walkscited by 23
  3. 2023Cross-modal Active Complementary Learning with Self-refining Correspondencecited by 22
  4. 2025No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasetscited by 16
  5. 2025Incomplete Multi-view Clustering via Diffusion Contrastive Generationcited by 13
  6. 2024Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrievalcited by 11
  7. 2024A Survey on Deep Clustering: From the Prior Perspectivecited by 9
  8. 2023Deep Semantic Graph Matching for Large-scale Outdoor Point Clouds Registrationcited by 5
  9. 2023Noisy Correspondence Learning with Self-Reinforcing Errors Mitigationcited by 5
  10. 2024Learning Solution-Aware Transformers for Efficiently Solving Quadratic Assignment Problemcited by 4
  11. 2024Disentangled Noisy Correspondence Learningcited by 4
  12. 2023CAPro: Webly Supervised Learning with Cross-Modality Aligned Prototypescited by 3
18 more
  1. 2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identificationcited by 2
  2. 2025Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignmentcited by 2
  3. 2025Normalized Matching Transformercited by 1
  4. 2023Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adaptercited by 0
  5. 2023GMTR: Graph Matching Transformerscited by 0
  6. 2023DarkShot: Lighting Dark Images with Low-Compute and High-Qualitycited by 0
  7. 2024TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processingcited by 0
  8. 2024TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networkscited by 0
  9. 2024T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Imagecited by 0
  10. 2024Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithmscited by 0
  11. 2024Towards General Deepfake Detection with Dynamic Curriculumcited by 0
  12. 2024Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphscited by 0
  13. 2024CLAP: Concave Linear APproximation for Quadratic Graph Matchingcited by 0
  14. 2024Robust Noisy Correspondence Learning via Self-Drop and Dual-Weightcited by 0
  15. 2025Adaptive Hardness-driven Augmentation and Alignment Strategies for Multi-Source Domain Adaptationscited by 0
  16. 2025Mask6D: Masked Pose Priors For 6D Object Pose Estimationcited by 0
  17. 2026EXHIB: A Benchmark for Realistic and Diverse Evaluation of Function Similarity in the Wildcited by 0
  18. 2026Robust Fuzzy Multi-view Learning under View Conflictcited by 0