mlsanityData to 7 Oct 2026

Demystifying Unsupervised Semantic Correspondence Estimation

arXiv 2207.05054 ↗First posted 11 Jul 2022cs.CV cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

We explore semantic correspondence estimation through the lens of unsupervised learning. We thoroughly evaluate several recently proposed unsupervised methods across multiple challenging datasets using a standardized evaluation protocol where we vary factors such as the backbone architecture, the pre-training strategy, and the pre-training and finetuning datasets. To better understand the failure modes of these methods, and in order to provide a clearer path for improvement, we provide a new diagnostic framework along with a new performance metric that is better suited to the semantic matching task. Finally, we introduce a new unsupervised correspondence approach which utilizes the strength of pre-trained features while encouraging better matches during training. This results in significantly better matching performance compared to current state-of-the-art methods.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 64 of its 81 references that are in the map. First posted on arXiv 11 Jul 2022.

Builds on

64 of 81 references.

References · 64

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  9. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  10. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  11. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  12. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
38 more
  1. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  2. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  3. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  4. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  5. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  6. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  7. 2021Deep ViT Features as Dense Visual Descriptorscited by 327
  8. 2020A Metric Learning Reality Checkcited by 317
  9. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
  10. 2018Neighbourhood Consensus Networkscited by 173
  11. 2021Benchmarking Representation Learning for Natural World Image Collectionscited by 167
  12. 2020Unsupervised Learning of Dense Visual Representationscited by 147
  13. 2019SPair-71k: A Large-scale Benchmark for Semantic Correspondencecited by 140
  14. 2017Convolutional neural network architecture for geometric matchingcited by 138
  15. 2018Unsupervised Learning of Object Landmarks through Conditional Image Generationcited by 113
  16. 2021Aligning Pretraining for Detection via Object-Level Contrastive Learningcited by 110
  17. 2019Unsupervised Learning of Object Keypoints for Perception and Controlcited by 109
  18. 2020Evaluating Weakly Supervised Object Localization Methods Rightcited by 104
  19. 2021Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentationcited by 101
  20. 2020Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutionscited by 92
  21. 2016Universal Correspondence Networkcited by 82
  22. 2020Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loopcited by 81
  23. 2021CATs: Cost Aggregation Transformers for Visual Correspondencecited by 77
  24. 2018Unsupervised Discovery of Object Landmarks as Structural Representationscited by 73
  25. 2018Diagnosing Error in Temporal Action Detectorscited by 71
  26. 2017Unsupervised learning of object landmarks by factorized spatial embeddingscited by 64
  27. 2021Spatially Consistent Representation Learningcited by 64
  28. 2019SFNet: Learning Object-aware Semantic Correspondencecited by 60
  29. 2019Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Featurescited by 56
  30. 2020Learning to Compose Hypercolumns for Visual Correspondencecited by 53
  31. 2017SCNet: Learning Semantic Correspondencecited by 48
  32. 2017Benchmarking and Error Diagnosis in Multi-Instance Pose Estimationcited by 48
  33. 2017Proposal Flow: Semantic Correspondences from Object Proposalscited by 46
  34. 2019Dynamic Context Correspondence Network for Semantic Alignmentcited by 43
  35. 2021Convolutional Hough Matching Networkscited by 43
  36. 2017FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondencecited by 42
  37. 2020Correspondence Networks with Adaptive Neighbourhood Consensuscited by 42
  38. 2019Unsupervised Learning of Landmarks by Descriptor Vector Exchangecited by 39

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 1; 2025: 3.

9 papers.

  1. 2023Telling Left from Right: Identifying Geometry-Aware Semantic Correspondencecited by 85
  2. 2022Teaching Matters: Investigating the Role of Supervision in Vision Transformerscited by 45
  3. 2023Improving Semantic Correspondence with Viewpoint-Guided Spherical Mapscited by 33
  4. 2023ASIC: Aligning Sparse in-the-wild Image Collectionscited by 26
  5. 2025SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representationscited by 6
  6. 2023PARTICLE: Part Discovery and Contrastive Learning for Fine-grained Recognitioncited by 5
  7. 2025Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondencecited by 5
  8. 2025Semantic Correspondence: Unified Benchmarking and a Strong Baselinecited by 3
  9. 2024Matching Semantically Similar Non-Identical Objectscited by 0