mlsanityData to 7 Oct 2026

SPair-71k: A Large-scale Benchmark for Semantic Correspondence

arXiv 1908.10543 ↗First posted 28 Aug 2019cs.CVcited by 140

Not on the map. Why?

Abstract (arXiv)

Establishing visual correspondences under large intra-class variations, which is often referred to as semantic correspondence or semantic matching, remains a challenging problem in computer vision. Despite its significance, however, most of the datasets for semantic correspondence are limited to a small amount of image pairs with similar viewpoints and scales. In this paper, we present a new large-scale benchmark dataset of semantically paired images, SPair-71k, which contains 70,958 image pairs with diverse variations in viewpoint and scale. Compared to previous datasets, it is significantly larger in number and contains more accurate and richer annotations. We believe this dataset will provide a reliable testbed to study the problem of semantic correspondence and will help to advance research in this area. We provide the results of recent methods on our new dataset as baselines for further research. Our benchmark is available online at http://cvlab.postech.ac.kr/research/SPair-71k/.

Key facts. Cited by 140 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 16; 2023: 23; 2024: 28; 2025: 26; 2026: 30.

140 papers.

Sort:

By area:

  1. 2024BLINK: Multimodal Large Language Models Can See but Not Perceivecited by 529
  2. 2023Emergent Correspondence from Image Diffusioncited by 437
  3. 2021Deep ViT Features as Dense Visual Descriptorscited by 327
  4. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 297
  5. 2023What does CLIP know about a red circle? Visual prompt engineering for VLMscited by 215
  6. 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondencecited by 211
  7. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  8. 2024Probing the 3D Awareness of Visual Foundation Modelscited by 175
  9. 2023Unsupervised Semantic Correspondence Using Stable Diffusioncited by 120
  10. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  11. 2023Telling Left from Right: Identifying Geometry-Aware Semantic Correspondencecited by 85
  12. 2024RandAR: Decoder-only Autoregressive Visual Generation in Random Orderscited by 82
38 more
  1. 2021CATs: Cost Aggregation Transformers for Visual Correspondencecited by 77
  2. 2021GAN-Supervised Dense Visual Alignmentcited by 61
  3. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  4. 2022CATs++: Boosting Cost Aggregation with Convolutions and Transformerscited by 53
  5. 2023NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotationscited by 53
  6. 2024Diffusion Models and Representation Learning: A Surveycited by 53
  7. 2023Going Denser with Open-Vocabulary Part Segmentationcited by 51
  8. 2021CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraintscited by 49
  9. 2023FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Modelscited by 47
  10. 2022Teaching Matters: Investigating the Role of Supervision in Vision Transformerscited by 45
  11. 2021Convolutional Hough Matching Networkscited by 43
  12. 2021Warp Consistency for Unsupervised Learning of Dense Correspondencescited by 42
  13. 2024CleanDIFT: Diffusion Features without Noisecited by 42
  14. 2023SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matchingcited by 38
  15. 2023Improving Semantic Correspondence with Viewpoint-Guided Spherical Mapscited by 33
  16. 2021Multi-scale Matching Networks for Semantic Correspondencecited by 32
  17. 2022Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondencecited by 32
  18. 2022Learning Semantic Correspondence with Sparse Annotationscited by 31
  19. 2022Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondencescited by 30
  20. 2022Graph Matching with Bi-level Noisy Correspondencecited by 30
  21. 2023Neural Congealing: Aligning Images to a Joint Semantic Atlascited by 30
  22. 2022TransforMatcher: Match-to-Match Attention for Semantic Correspondencecited by 29
  23. 2022Backpropagation through Combinatorial Algorithms: Identity with Projection Workscited by 29
  24. 2024LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptorscited by 27
  25. 2023ASIC: Aligning Sparse in-the-wild Image Collectionscited by 26
  26. 2024Not All Diffusion Model Activations Have Been Evaluated as Discriminative Featurescited by 23
  27. 2025Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learningcited by 21
  28. 2025Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activationscited by 20
  29. 2023SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentationcited by 19
  30. 2024Distillation of Diffusion Features for Semantic Correspondencecited by 17
  31. 2021Cost Aggregation Is All You Need for Few-Shot Segmentationcited by 16
  32. 2022Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labelscited by 16
  33. 2024Law of Vision Representation in MLLMscited by 16
  34. 2025Latent Implicit Visual Reasoningcited by 16
  35. 2024Near, far: Patch-ordering enhances vision foundation models' scene understandingcited by 15
  36. 2024Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondencecited by 14
  37. 2024Toward a Holistic Evaluation of Robustness in CLIP Modelscited by 13
  38. 2025Do It Yourself: Learning Semantic Correspondence from Pseudo-Labelscited by 13

50 most cited of 140 All 140 (JSON)