mlsanityData to 7 Oct 2026

Dynamic Context Correspondence Network for Semantic Alignment

arXiv 1909.03444 ↗First posted 8 Sep 2019cs.CVcited by 43

Not on the map. Why?

Abstract (arXiv)

Establishing semantic correspondence is a core problem in computer vision and remains challenging due to large intra-class variations and lack of annotated data. In this paper, we aim to incorporate global semantic context in a flexible manner to overcome the limitations of prior work that relies on local semantic representations. To this end, we first propose a context-aware semantic representation that incorporates spatial layout for robust matching against local ambiguities. We then develop a novel dynamic fusion strategy based on attention mechanism to weave the advantages of both local and context features by integrating semantic cues from multiple scales. We instantiate our strategy by designing an end-to-end learnable deep network, named as Dynamic Context Correspondence Network (DCCNet). To train the network, we adopt a multi-auxiliary task loss to improve the efficiency of our weakly-supervised learning procedure. Our approach achieves superior or competitive performance over previous methods on several challenging datasets, including PF-Pascal, PF-Willow, and TSS, demonstrating its effectiveness and generality.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 13; 2022: 13; 2023: 8; 2024: 5; 2025: 4.

43 papers.

Sort:

By area:

  1. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  2. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  3. 2021Learning Accurate Dense Correspondences and When to Trust Themcited by 113
  4. 2021PDC-Net+: Enhanced Probabilistic Dense Correspondence Networkcited by 80
  5. 2021CATs: Cost Aggregation Transformers for Visual Correspondencecited by 77
  6. 2021Relational Embedding for Few-Shot Classificationcited by 74
  7. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  8. 2022CATs++: Boosting Cost Aggregation with Convolutions and Transformerscited by 53
  9. 2021Convolutional Hough Matching Networkscited by 43
  10. 2021Warp Consistency for Unsupervised Learning of Dense Correspondencescited by 42
  11. 2023Towards Scalable Neural Representation for Diverse Videoscited by 37
  12. 2021Multi-scale Matching Networks for Semantic Correspondencecited by 32
31 more
  1. 2022Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondencecited by 32
  2. 2022Learning Semantic Correspondence with Sparse Annotationscited by 31
  3. 2021Deep Matching Prior: Test-Time Optimization for Dense Correspondencecited by 30
  4. 2022Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondencescited by 30
  5. 2022TransforMatcher: Match-to-Match Attention for Semantic Correspondencecited by 29
  6. 2022Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wildcited by 22
  7. 2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
  8. 2023Adaptive Spot-Guided Transformer for Consistent Local Feature Matchingcited by 22
  9. 2021Cost Aggregation Is All You Need for Few-Shot Segmentationcited by 16
  10. 2022Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labelscited by 16
  11. 2024Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondencecited by 14
  12. 2022Semantic-Aware Fine-Grained Correspondencecited by 13
  13. 2021Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondencecited by 12
  14. 2021Learning Contrastive Representation for Semantic Correspondencecited by 11
  15. 2023Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentationcited by 10
  16. 2024ARDuP: Active Region Video Diffusion for Universal Policiescited by 10
  17. 2022Demystifying Unsupervised Semantic Correspondence Estimationcited by 9
  18. 2023Structured Epipolar Matcher for Local Feature Matchingcited by 8
  19. 2025TREND: Tri-teaching for Robust Preference-based Reinforcement Learning with Demonstrationscited by 7
  20. 2025Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognitioncited by 7
  21. 2022Integrative Feature and Cost Aggregation with Transformers for Dense Correspondencecited by 6
  22. 2023SimSC: A Simple Framework for Semantic Correspondence with Temperature Learningcited by 6
  23. 2023Efficient Semantic Matching with Hypercolumn Correlationcited by 6
  24. 2024What is Point Supervision Worth in Video Instance Segmentation?cited by 5
  25. 2024UVIS: Unsupervised Video Instance Segmentationcited by 5
  26. 2022Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulationcited by 4
  27. 2025Semantic Correspondence: Unified Benchmarking and a Strong Baselinecited by 3
  28. 2023Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Imagescited by 2
  29. 2024Independently Keypoint Learning for Small Object Semantic Correspondencecited by 2
  30. 2022Joint Learning of Feature Extraction and Cost Aggregation for Semantic Correspondencecited by 0
  31. 2025A Lightweight Multi-Module Fusion Approach for Korean Character Recognitioncited by 0