mlsanityData to 14 Oct 2026

Dense Affinity Matching for Few-Shot Segmentation

arXiv 2307.08434 ↗First posted 17 Jul 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Few-Shot Segmentation (FSS) aims to segment the novel class images with a few annotated samples. In this paper, we propose a dense affinity matching (DAM) framework to exploit the support-query interaction by densely capturing both the pixel-to-pixel and pixel-to-patch relations in each support-query pair with the bidirectional 3D convolutions. Different from the existing methods that remove the support background, we design a hysteretic spatial filtering module (HSFM) to filter the background-related query features and retain the foreground-related query features with the assistance of the support background, which is beneficial for eliminating interference objects in the query background. We comprehensively evaluate our DAM on ten benchmarks under cross-category, cross-dataset, and cross-domain FSS tasks. Experimental results demonstrate that DAM performs very competitively under different settings with only 0.68M parameters, especially under cross-domain FSS tasks, showing its effectiveness and efficiency.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 42 of its 64 references that are in the map. First posted on arXiv 17 Jul 2023.

Builds on

42 of 64 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2023Segment Anythingcited by 8,234
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  7. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
  8. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  9. 2017One-Shot Learning for Semantic Segmentationcited by 337
  10. 2018DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Imagescited by 277
  11. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  12. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
30 more
  1. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  2. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  3. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  4. 2019FSS-1000: A 1000-Class Dataset for Few-Shot Segmentationcited by 160
  5. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  6. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  7. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  8. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  9. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  10. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  11. 2020Semantic Segmentation of Underwater Imagery: Dataset and Benchmarkcited by 95
  12. 2021CATs: Cost Aggregation Transformers for Visual Correspondencecited by 77
  13. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  14. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  15. 2021Recurrent Mask Refinement for Few-Shot Medical Image Segmentationcited by 63
  16. 2020Generalized Few-shot Semantic Segmentationcited by 59
  17. 2022Feature-Proxy Transformer for Few-Shot Segmentationcited by 58
  18. 2022Learning Non-target Knowledge for Few-shot Semantic Segmentationcited by 57
  19. 2021Learning Meta-class Memory for Few-Shot Semantic Segmentationcited by 56
  20. 2022Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningcited by 50
  21. 2021Incremental Few-Shot Instance Segmentationcited by 49
  22. 2022Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentationcited by 43
  23. 2022Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentationcited by 37
  24. 2021Few-shot Segmentation with Optimal Transport Matching and Message Flowcited by 36
  25. 2022Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentationcited by 28
  26. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  27. 2022Mask Matching Transformer for Few-Shot Segmentationcited by 22
  28. 2021Dense Gaussian Processes for Few-Shot Segmentationcited by 17
  29. 2022CATrans: Context and Affinity Transformer for Few-Shot Segmentationcited by 7
  30. 2022Texture based Prototypical Network for Few-Shot Semantic Segmentation of Forest Cover: Generalizing for Different Geographical Regionscited by 4

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 2.

5 papers.

  1. 2024Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Miningcited by 30
  2. 2024Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentationcited by 22
  3. 2024Cross-Domain Few-Shot Semantic Segmentation via Doubly Matching Transformationcited by 13
  4. 2025Adapting In-Domain Few-Shot Segmentation to New Domains without Source Domain Retrainingcited by 4
  5. 2025Textual and Visual Guided Task Adaptation for Source-Free Cross-Domain Few-Shot Segmentationcited by 1