mlsanityData to 14 Oct 2026

Image Patch-Matching with Graph-Based Learning in Street Scenes

arXiv 2311.04617 ↗First posted 8 Nov 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Matching landmark patches from a real-time image captured by an on-vehicle camera with landmark patches in an image database plays an important role in various computer perception tasks for autonomous driving. Current methods focus on local matching for regions of interest and do not take into account spatial neighborhood relationships among the image patches, which typically correspond to objects in the environment. In this paper, we construct a spatial graph with the graph vertices corresponding to patches and edges capturing the spatial neighborhood information. We propose a joint feature and metric learning model with graph-based learning. We provide a theoretical basis for the graph-based loss by showing that the information distance between the distributions conditioned on matched and unmatched pairs is maximized under our framework. We evaluate our model using several street-scene datasets and demonstrate that our approach achieves state-of-the-art matching results.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 37 of its 77 references that are in the map. First posted on arXiv 8 Nov 2023.

Builds on

37 of 77 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2017Graph Attention Networkscited by 8,923
  5. 2017Mask R-CNNcited by 7,277
  6. 2017Inductive Representation Learning on Large Graphscited by 6,320
  7. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  8. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  9. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  10. 2018Deep Graph Infomaxcited by 1,106
  11. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  12. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
25 more
  1. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  2. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  3. 2016LIFT: Learned Invariant Feature Transformcited by 306
  4. 2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 238
  5. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 216
  6. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  7. 2018PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognitioncited by 198
  8. 2019The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Datasetcited by 134
  9. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
  10. 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 130
  11. 2017Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenescited by 122
  12. 2020HR-Depth: High Resolution Self-Supervised Monocular Depth Estimationcited by 115
  13. 2015Learning to Compare Image Patches via Convolutional Neural Networkscited by 109
  14. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  15. 2021Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimationcited by 63
  16. 2020SOLAR: Second-Order Loss and Attention for Image Retrievalcited by 45
  17. 2017Learning Spread-out Local Feature Descriptorscited by 34
  18. 2015Learning Local Image Descriptors with Deep Siamese and Triplet Convolutional Networks by Minimising Global Loss Functionscited by 33
  19. 2020EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Associationcited by 24
  20. 2018Vehicle Re-identification Using Quadruple Directional Deep Learning Featurescited by 14
  21. 2020TCDesc: Learning Topology Consistent Descriptors for Image Matchingcited by 10
  22. 2019DeepLocalization: Landmark-based Self-Localization with Deep Neural Networkscited by 9
  23. 2020Dynamic Object Tracking and Masking for Visual SLAMcited by 8
  24. 2021Joint Graph Learning and Matching for Semantic Feature Correspondencecited by 8
  25. 2020Semantic SLAM with Autonomous Object-Level Data Associationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 1.

5 papers.

  1. 2024Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FRONDcited by 17
  2. 2024Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Studycited by 9
  3. 2024PRFusion: Toward Effective and Robust Multi-Modal Place Recognition with Image and Point Cloud Fusioncited by 2
  4. 2025Personalized Subgraph Federated Learning with Sheaf Collaborationcited by 1
  5. 2026Modeling Scientific Experiment Scenes: Dataset and Modelcited by 0