mlsanityData to 7 Oct 2026

Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features

arXiv 1908.06537 ↗First posted 18 Aug 2019cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

Establishing visual correspondences under large intra-class variations requires analyzing images at different levels, from features linked to semantics and context to local patterns, while being invariant to instance-specific details. To tackle these challenges, we represent images by "hyperpixels" that leverage a small number of relevant features selected among early to late layers of a convolutional neural network. Taking advantage of the condensed features of hyperpixels, we develop an effective real-time matching algorithm based on Hough geometric voting. The proposed method, hyperpixel flow, sets a new state of the art on three standard benchmarks as well as a new dataset, SPair-71k, which contains a significantly larger number of image pairs than existing datasets, with more accurate and richer annotations for in-depth analysis.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 16; 2023: 12; 2024: 5; 2025: 6; 2026: 2.

56 papers.

Sort:

By area:

  1. 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondencecited by 211
  2. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  3. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  4. 2021CATs: Cost Aggregation Transformers for Visual Correspondencecited by 77
  5. 2021Relational Embedding for Few-Shot Classificationcited by 74
  6. 2021GAN-Supervised Dense Visual Alignmentcited by 61
  7. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  8. 2021Deep Hough Voting for Robust Global Registrationcited by 53
  9. 2022CATs++: Boosting Cost Aggregation with Convolutions and Transformerscited by 53
  10. 2021Convolutional Hough Matching Networkscited by 43
  11. 2023SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matchingcited by 38
  12. 2021Multi-scale Matching Networks for Semantic Correspondencecited by 32
38 more
  1. 2022Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondencecited by 32
  2. 2021Input-level Inductive Biases for 3D Reconstructioncited by 31
  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. 2022Self-Supervised Equivariant Learning for Oriented Keypoint Detectioncited by 26
  8. 2023ASIC: Aligning Sparse in-the-wild Image Collectionscited by 26
  9. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  10. 2023Learning Rotation-Equivariant Features for Visual Correspondencecited by 23
  11. 2022MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentationcited by 21
  12. 2021Cost Aggregation Is All You Need for Few-Shot Segmentationcited by 16
  13. 2022Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labelscited by 16
  14. 2024Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondencecited by 14
  15. 2022Semantic-Aware Fine-Grained Correspondencecited by 13
  16. 2025MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglementcited by 13
  17. 2021Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondencecited by 12
  18. 2021Learning Contrastive Representation for Semantic Correspondencecited by 11
  19. 2022Demystifying Unsupervised Semantic Correspondence Estimationcited by 9
  20. 2025RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extractioncited by 9
  21. 2023Masked and Adaptive Transformer for Exemplar Based Image Translationcited by 8
  22. 2022Integrative Feature and Cost Aggregation with Transformers for Dense Correspondencecited by 6
  23. 2023SimSC: A Simple Framework for Semantic Correspondence with Temperature Learningcited by 6
  24. 2023Efficient Semantic Matching with Hypercolumn Correlationcited by 6
  25. 2022Multi-layer Representation Learning for Robust OOD Image Classificationcited by 5
  26. 2023DeDA: Deep Directed Accumulatorcited by 5
  27. 2025Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentationcited by 4
  28. 2025Learning 3D Scene Analogies with Neural Contextual Scene Mapscited by 4
  29. 2026PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentationcited by 4
  30. 2022Motion Aware Self-Supervision for Generic Event Boundary Detectioncited by 3
  31. 2024SAMIC: Segment Anything with In-Context Spatial Prompt Engineeringcited by 3
  32. 2025Semantic Correspondence: Unified Benchmarking and a Strong Baselinecited by 3
  33. 2021Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Enginecited by 2
  34. 2023Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Imagescited by 2
  35. 2024Independently Keypoint Learning for Small Object Semantic Correspondencecited by 2
  36. 2022DSI2I: Dense Style for Unpaired Image-to-Image Translationcited by 1
  37. 2021Reconstructing and grounding narrated instructional videos in 3Dcited by 0
  38. 2021HoughCL: Finding Better Positive Pairs in Dense Self-supervised Learningcited by 0

50 most cited of 56 All 56 (JSON)