mlsanityData to 7 Oct 2026

Convolutional Hough Matching Networks

arXiv 2103.16831 ↗First posted 31 Mar 2021cs.CVcited by 43

Not on the map. Why?

Abstract (arXiv)

Despite advances in feature representation, leveraging geometric relations is crucial for establishing reliable visual correspondences under large variations of images. In this work we introduce a Hough transform perspective on convolutional matching and propose an effective geometric matching algorithm, dubbed Convolutional Hough Matching (CHM). The method distributes similarities of candidate matches over a geometric transformation space and evaluate them in a convolutional manner. We cast it into a trainable neural layer with a semi-isotropic high-dimensional kernel, which learns non-rigid matching with a small number of interpretable parameters. To validate the effect, we develop the neural network with CHM layers that perform convolutional matching in the space of translation and scaling. Our method sets a new state of the art on standard benchmarks for semantic visual correspondence, proving its strong robustness to challenging intra-class variations.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). Builds on 35 of its 66 references that are in the map. First posted on arXiv 31 Mar 2021.

Builds on

35 of 66 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  8. 2019Learning Correspondence from the Cycle-Consistency of Timecited by 269
  9. 2018Neighbourhood Consensus Networkscited by 173
  10. 2019SPair-71k: A Large-scale Benchmark for Semantic Correspondencecited by 140
  11. 2019GLU-Net: Global-Local Universal Network for Dense Flow and Correspondencescited by 139
  12. 2017Convolutional neural network architecture for geometric matchingcited by 138
23 more
  1. 2020Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutionscited by 92
  2. 2020Deep Graph Matching Consensuscited by 85
  3. 2016Universal Correspondence Networkcited by 82
  4. 2020Deep Graph Matching via Blackbox Differentiation of Combinatorial Solverscited by 81
  5. 2015Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposalscited by 69
  6. 2017End-to-end weakly-supervised semantic alignmentcited by 60
  7. 2019SFNet: Learning Object-aware Semantic Correspondencecited by 60
  8. 2015Proposal Flowcited by 57
  9. 2019Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Featurescited by 56
  10. 2020Learning to Compose Hypercolumns for Visual Correspondencecited by 53
  11. 2017SCNet: Learning Semantic Correspondencecited by 48
  12. 2017Proposal Flow: Semantic Correspondences from Object Proposalscited by 46
  13. 2019Dynamic Context Correspondence Network for Semantic Alignmentcited by 43
  14. 2020Correspondence Networks with Adaptive Neighbourhood Consensuscited by 42
  15. 2016Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimationcited by 34
  16. 2018Recurrent Transformer Networks for Semantic Correspondencecited by 32
  17. 2018Attentive Semantic Alignment with Offset-Aware Correlation Kernelscited by 31
  18. 2018PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondencecited by 26
  19. 2018Semi-convolutional Operators for Instance Segmentationcited by 21
  20. 2015Unsupervised Object Discovery and Tracking in Video Collectionscited by 17
  21. 2016Hough-CNN: Deep Learning for Segmentation of Deep Brain Regions in MRI and Ultrasoundcited by 17
  22. 2015Dense Semantic Correspondence where Every Pixel is a Classifiercited by 15
  23. 2017DCTM: Discrete-Continuous Transformation Matching for Semantic Flowcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 13; 2023: 13; 2024: 4; 2025: 4; 2026: 2.

43 papers.

Sort:

By area:

  1. 2023Emergent Correspondence from Image Diffusioncited by 437
  2. 2023CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentationcited by 215
  3. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  4. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 170
  5. 2022AiATrack: Attention in Attention for Transformer Visual Trackingcited by 137
  6. 2023Cross-Image Attention for Zero-Shot Appearance Transfercited by 135
  7. 2021CATs: Cost Aggregation Transformers for Visual Correspondencecited by 77
  8. 2021Relational Embedding for Few-Shot Classificationcited by 74
  9. 2021GAN-Supervised Dense Visual Alignmentcited by 61
  10. 2021Deep Hough Voting for Robust Global Registrationcited by 53
  11. 2022CATs++: Boosting Cost Aggregation with Convolutions and Transformerscited by 53
  12. 2022Correlation Verification for Image Retrievalcited by 47
31 more
  1. 2023SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matchingcited by 38
  2. 2022Visual correspondence-based explanations improve AI robustness and human-AI team accuracycited by 37
  3. 2022Learning Semantic Correspondence with Sparse Annotationscited by 31
  4. 2022Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondencescited by 30
  5. 2023Neural Congealing: Aligning Images to a Joint Semantic Atlascited by 30
  6. 2022TransforMatcher: Match-to-Match Attention for Semantic Correspondencecited by 29
  7. 2022Peripheral Vision Transformercited by 27
  8. 2023ASIC: Aligning Sparse in-the-wild Image Collectionscited by 26
  9. 2023Diffusion Model for Dense Matchingcited by 21
  10. 2022Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labelscited by 16
  11. 2024Learning Correlation Structures for Vision Transformerscited by 15
  12. 2022Semantic-Aware Fine-Grained Correspondencecited by 13
  13. 2021Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondencecited by 12
  14. 2023Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentationcited by 10
  15. 2022Demystifying Unsupervised Semantic Correspondence Estimationcited by 9
  16. 20243D Geometric Shape Assembly via Efficient Point Cloud Matchingcited by 8
  17. 2023SimSC: A Simple Framework for Semantic Correspondence with Temperature Learningcited by 6
  18. 2023Efficient Semantic Matching with Hypercolumn Correlationcited by 6
  19. 2025Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondencecited by 5
  20. 2025Semantic Correspondence: Unified Benchmarking and a Strong Baselinecited by 3
  21. 2026MARCO: Navigating the Unseen Space of Semantic Correspondencecited by 3
  22. 2022Towards Privacy-Preserving, Real-Time and Lossless Feature Matchingcited by 2
  23. 2023Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Imagescited by 2
  24. 2024Independently Keypoint Learning for Small Object Semantic Correspondencecited by 2
  25. 2025Similarity-Aware Selective State-Space Modeling for Semantic Correspondencecited by 1
  26. 2021HoughCL: Finding Better Positive Pairs in Dense Self-supervised Learningcited by 0
  27. 2023LostNet: A smart way for lost and findcited by 0
  28. 2023Learning Space-Time Semantic Correspondencescited by 0
  29. 2024Boosting Few-Shot Segmentation via Instance-Aware Data Augmentation and Local Consensus Guided Cross Attentioncited by 0
  30. 2025Towards Robust Semantic Correspondence: A Benchmark and Insightscited by 0
  31. 2026SimpleMatch: A Simple and Strong Baseline for Semantic Correspondencecited by 0