mlsanityData to 7 Oct 2026

Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation

arXiv 2207.08549 ↗First posted 18 Jul 2022cs.CVcited by 65

Not on the map. Why?

Abstract (arXiv)

Research into Few-shot Semantic Segmentation (FSS) has attracted great attention, with the goal to segment target objects in a query image given only a few annotated support images of the target class. A key to this challenging task is to fully utilize the information in the support images by exploiting fine-grained correlations between the query and support images. However, most existing approaches either compressed the support information into a few class-wise prototypes, or used partial support information (e.g., only foreground) at the pixel level, causing non-negligible information loss. In this paper, we propose Dense pixel-wise Cross-query-and-support Attention weighted Mask Aggregation (DCAMA), where both foreground and background support information are fully exploited via multi-level pixel-wise correlations between paired query and support features. Implemented with the scaled dot-product attention in the Transformer architecture, DCAMA treats every query pixel as a token, computes its similarities with all support pixels, and predicts its segmentation label as an additive aggregation of all the support pixels' labels -- weighted by the similarities. Based on the unique formulation of DCAMA, we further propose efficient and effective one-pass inference for n-shot segmentation, where pixels of all support images are collected for the mask aggregation at once. Experiments show that our DCAMA significantly advances the state of the art on standard FSS benchmarks of PASCAL-5i, COCO-20i, and FSS-1000, e.g., with 3.1%, 9.7%, and 3.6% absolute improvements in 1-shot mIoU over previous best records. Ablative studies also verify the design DCAMA.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). Builds on 41 of its 53 references that are in the map. First posted on arXiv 18 Jul 2022.

Builds on

41 of 53 references.

References · 41

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  8. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  9. 2017Graph Attention Networkscited by 8,854
  10. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  11. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  12. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
29 more
  1. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2016Pyramid Scene Parsing Networkcited by 2,472
  4. 2016Matching Networks for One Shot Learningcited by 2,246
  5. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  6. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  7. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  8. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  9. 2017One-Shot Learning for Semantic Segmentationcited by 337
  10. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  11. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  12. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  13. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  14. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  15. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  16. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  17. 2019FSS-1000: A 1000-Class Dataset for Few-Shot Segmentationcited by 160
  18. 2014Simultaneous Detection and Segmentationcited by 158
  19. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  20. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  21. 2019Deep Semantic Segmentation of Natural and Medical Images: A Reviewcited by 124
  22. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  23. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  24. 2017Few-Shot Learning Through an Information Retrieval Lenscited by 51
  25. 2020On the Texture Bias for Few-Shot CNN Segmentationcited by 38
  26. 2021A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Datacited by 16
  27. 2021A Unified Efficient Pyramid Transformer for Semantic Segmentationcited by 14
  28. 2021Rethinking Semantic Segmentation Evaluation for Explainability and Model Selectioncited by 11
  29. 2021Boosting Few-shot Semantic Segmentation with Transformerscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 15; 2024: 22; 2025: 20; 2026: 5.

65 papers.

Sort:

By area:

  1. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  2. 2024VRP-SAM: SAM with Visual Reference Promptcited by 75
  3. 2024Bridge the Points: Graph-based Few-shot Segment Anything Semanticallycited by 35
  4. 2023Self-Calibrated Cross Attention Network for Few-Shot Segmentationcited by 32
  5. 2024Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learningcited by 32
  6. 2023DifFSS: Diffusion Model for Few-Shot Semantic Segmentationcited by 22
  7. 2024Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentationcited by 22
  8. 2024Hybrid Mamba for Few-Shot Segmentationcited by 21
  9. 2024Rethinking Prior Information Generation with CLIP for Few-Shot Segmentationcited by 20
  10. 2023Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyondcited by 19
  11. 2024Eliminating Feature Ambiguity for Few-Shot Segmentationcited by 19
  12. 2022MSI: Maximize Support-Set Information for Few-Shot Segmentationcited by 18
38 more
  1. 2022Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overviewcited by 16
  2. 2024Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentationcited by 16
  3. 2025DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistencycited by 15
  4. 2024Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentationcited by 14
  5. 2023Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentationcited by 13
  6. 2024Explore In-Context Segmentation via Latent Diffusion Modelscited by 12
  7. 2025Not All Data Are Unlearned Equallycited by 12
  8. 2023Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentationcited by 11
  9. 2025Unlocking the Power of SAM 2 for Few-Shot Segmentationcited by 11
  10. 2023Towards More Unified In-context Visual Understandingcited by 10
  11. 2024Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Promptscited by 9
  12. 2025No time to train! Training-Free Reference-Based Instance Segmentationcited by 9
  13. 2025SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentationcited by 8
  14. 2022Prototype as Query for Few Shot Semantic Segmentationcited by 6
  15. 2025DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentationcited by 6
  16. 2023[CLS] Token is All You Need for Zero-Shot Semantic Segmentationcited by 5
  17. 2023Dense Affinity Matching for Few-Shot Segmentationcited by 5
  18. 2024MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototypingcited by 5
  19. 2024Boosting Few-Shot Semantic Segmentation Via Segment Anything Modelcited by 4
  20. 2025Rethinking Few-Shot Medical Image Segmentation by SAM2: A Training-Free Framework with Augmentative Prompting and Dynamic Matchingcited by 4
  21. 2024Group-On: Boosting One-Shot Segmentation with Supportive Querycited by 3
  22. 2024Beyond Mask: Rethinking Guidance Types in Few-shot Segmentationcited by 3
  23. 2026Revealing the Semantic Selection Gap in DINOv3 through Training-Free Few-Shot Segmentationcited by 3
  24. 2023Multi-Content Interaction Network for Few-Shot Segmentationcited by 2
  25. 2023Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesiscited by 2
  26. 2024Embedding Generalized Semantic Knowledge into Few-Shot Remote Sensing Segmentationcited by 2
  27. 2024Few-Shot 3D Volumetric Segmentation with Multi-Surrogate Fusioncited by 2
  28. 2025Omni-Referring Image Segmentationcited by 2
  29. 2026VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentationcited by 2
  30. 2024mTREE: Multi-Level Text-Guided Representation End-to-End Learning for Whole Slide Image Analysiscited by 1
  31. 2025Reducing Annotation Burden: Exploiting Image Knowledge for Few-Shot Medical Video Object Segmentation via Spatiotemporal Consistency Relearningcited by 1
  32. 2025UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelationcited by 1
  33. 2025SAM2-SGP: Enhancing SAM2 for Medical Image Segmentation via Support-Set Guided Promptingcited by 1
  34. 2025Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentationcited by 1
  35. 2025Object-level Correlation for Few-Shot Segmentationcited by 1
  36. 2025FS-SAM2: Adapting Segment Anything Model 2 for Few-Shot Semantic Segmentation via Low-Rank Adaptationcited by 1
  37. 2025Unbiased Semantic Decoding with Vision Foundation Models for Few-shot Segmentationcited by 1
  38. 2025Take a Peek: Efficient Encoder Adaptation for Few-Shot Semantic Segmentation via LoRAcited by 1

50 most cited of 65 All 65 (JSON)