mlsanityData to 14 Oct 2026

TransforMatcher: Match-to-Match Attention for Semantic Correspondence

arXiv 2205.11634 ↗First posted 23 May 2022cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

Establishing correspondences between images remains a challenging task, especially under large appearance changes due to different viewpoints or intra-class variations. In this work, we introduce a strong semantic image matching learner, dubbed TransforMatcher, which builds on the success of transformer networks in vision domains. Unlike existing convolution- or attention-based schemes for correspondence, TransforMatcher performs global match-to-match attention for precise match localization and dynamic refinement. To handle a large number of matches in a dense correlation map, we develop a light-weight attention architecture to consider the global match-to-match interactions. We also propose to utilize a multi-channel correlation map for refinement, treating the multi-level scores as features instead of a single score to fully exploit the richer layer-wise semantics. In experiments, TransforMatcher sets a new state of the art on SPair-71k while performing on par with existing SOTA methods on the PF-PASCAL dataset.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 45 of its 62 references that are in the map. First posted on arXiv 23 May 2022.

Builds on

45 of 62 references.

References · 45

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  9. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  10. 2020Reformer: The Efficient Transformercited by 1,668
  11. 2020Rethinking Attention with Performerscited by 1,601
  12. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
33 more
  1. 2020Linformer: Self-Attention with Linear Complexitycited by 1,474
  2. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  3. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  4. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  5. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  6. 2019On the Relationship between Self-Attention and Convolutional Layerscited by 300
  7. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  8. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 207
  9. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 183
  10. 2018Neighbourhood Consensus Networkscited by 174
  11. 2019SPair-71k: A Large-scale Benchmark for Semantic Correspondencecited by 146
  12. 2019GLU-Net: Global-Local Universal Network for Dense Flow and Correspondencescited by 139
  13. 2017Convolutional neural network architecture for geometric matchingcited by 138
  14. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
  15. 2020Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutionscited by 93
  16. 2020Dual-Resolution Correspondence Networkscited by 90
  17. 2016Universal Correspondence Networkcited by 82
  18. 2015Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposalscited by 69
  19. 2021Fastformer: Additive Attention Can Be All You Needcited by 61
  20. 2017End-to-end weakly-supervised semantic alignmentcited by 60
  21. 2019SFNet: Learning Object-aware Semantic Correspondencecited by 60
  22. 2015Proposal Flowcited by 57
  23. 2019Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Featurescited by 56
  24. 2020Learning to Compose Hypercolumns for Visual Correspondencecited by 53
  25. 2017SCNet: Learning Semantic Correspondencecited by 48
  26. 2017Proposal Flow: Semantic Correspondences from Object Proposalscited by 47
  27. 2019Dynamic Context Correspondence Network for Semantic Alignmentcited by 43
  28. 2021Convolutional Hough Matching Networkscited by 43
  29. 2020Correspondence Networks with Adaptive Neighbourhood Consensuscited by 42
  30. 2018Recurrent Transformer Networks for Semantic Correspondencecited by 32
  31. 2021Multi-scale Matching Networks for Semantic Correspondencecited by 32
  32. 2018PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondencecited by 26
  33. 2021Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondencecited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 9; 2025: 9; 2026: 2.

29 papers.

Sort:

By area:

  1. 2023Emergent Correspondence from Image Diffusioncited by 446
  2. 2023SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matchingcited by 38
  3. 20246DGS: 6D Pose Estimation from a Single Image and a 3D Gaussian Splatting Modelcited by 28
  4. 2023Learning Rotation-Equivariant Features for Visual Correspondencecited by 23
  5. 2023SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentationcited by 19
  6. 2024Distillation of Diffusion Features for Semantic Correspondencecited by 17
  7. 2025MangaNinja: Line Art Colorization with Precise Reference Followingcited by 17
  8. 2024Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondencecited by 14
  9. 2025Follow-Your-Color: Multi-Instance Sketch Colorizationcited by 10
  10. 20243D Geometric Shape Assembly via Efficient Point Cloud Matchingcited by 9
  11. 2025Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondencecited by 7
  12. 2023SimSC: A Simple Framework for Semantic Correspondence with Temperature Learningcited by 6
17 more
  1. 2023Efficient Semantic Matching with Hypercolumn Correlationcited by 6
  2. 2024CorrespondentDream: Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondencescited by 6
  3. 2025Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondencecited by 6
  4. 2024CONDA: Condensed Deep Association Learning for Co-Salient Object Detectioncited by 4
  5. 2025Learning 3D Scene Analogies with Neural Contextual Scene Mapscited by 4
  6. 2024Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transformcited by 3
  7. 2025SplatPose: Geometry-Aware 6-DoF Pose Estimation from Single RGB Image via 3D Gaussian Splattingcited by 3
  8. 2025Semantic Correspondence: Unified Benchmarking and a Strong Baselinecited by 3
  9. 2023Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Imagescited by 2
  10. 2024Independently Keypoint Learning for Small Object Semantic Correspondencecited by 2
  11. 2022A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objectivecited by 1
  12. 2023VGTS: Visually Guided Text Spotting for Novel Categories in Historical Manuscriptscited by 1
  13. 2025Similarity-Aware Selective State-Space Modeling for Semantic Correspondencecited by 1
  14. 2024Boosting Few-Shot Segmentation via Instance-Aware Data Augmentation and Local Consensus Guided Cross Attentioncited by 0
  15. 2025Towards Robust Semantic Correspondence: A Benchmark and Insightscited by 0
  16. 2026SimpleMatch: A Simple and Strong Baseline for Semantic Correspondencecited by 0
  17. 2026AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifierscited by 0