mlsanityData to 7 Oct 2026

Self-Calibrated Cross Attention Network for Few-Shot Segmentation

arXiv 2308.09294 ↗First posted 18 Aug 2023cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

The key to the success of few-shot segmentation (FSS) lies in how to effectively utilize support samples. Most solutions compress support foreground (FG) features into prototypes, but lose some spatial details. Instead, others use cross attention to fuse query features with uncompressed support FG. Query FG could be fused with support FG, however, query background (BG) cannot find matched BG features in support FG, yet inevitably integrates dissimilar features. Besides, as both query FG and BG are combined with support FG, they get entangled, thereby leading to ineffective segmentation. To cope with these issues, we design a self-calibrated cross attention (SCCA) block. For efficient patch-based attention, query and support features are firstly split into patches. Then, we design a patch alignment module to align each query patch with its most similar support patch for better cross attention. Specifically, SCCA takes a query patch as Q, and groups the patches from the same query image and the aligned patches from the support image as K&V. In this way, the query BG features are fused with matched BG features (from query patches), and thus the aforementioned issues will be mitigated. Moreover, when calculating SCCA, we design a scaled-cosine mechanism to better utilize the support features for similarity calculation. Extensive experiments conducted on PASCAL-5^i and COCO-20^i demonstrate the superiority of our model, e.g., the mIoU score under 5-shot setting on COCO-20^i is 5.6%+ better than previous state-of-the-arts. The code is available at https://github.com/Sam1224/SCCAN.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 42 of its 49 references that are in the map. First posted on arXiv 18 Aug 2023.

Builds on

42 of 49 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  8. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  9. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  10. 2016Pyramid Scene Parsing Networkcited by 2,472
  11. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  12. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
30 more
  1. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  2. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  3. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  4. 2017One-Shot Learning for Semantic Segmentationcited by 337
  5. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  6. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  7. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  8. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  9. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  10. 2014Simultaneous Detection and Segmentationcited by 158
  11. 2018Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentationcited by 145
  12. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  13. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  14. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  15. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  16. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  17. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  18. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  19. 2022L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentationcited by 57
  20. 2022Learning Non-target Knowledge for Few-shot Semantic Segmentationcited by 57
  21. 2022Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningcited by 50
  22. 2022UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentationcited by 45
  23. 2022Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentationcited by 43
  24. 2022Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentationcited by 37
  25. 2021PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Maskcited by 31
  26. 2022Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentationcited by 28
  27. 2022HiViT: Hierarchical Vision Transformer Meets Masked Image Modelingcited by 23
  28. 2022Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentationcited by 23
  29. 2022Mask Matching Transformer for Few-Shot Segmentationcited by 22
  30. 2022MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentationcited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 12; 2025: 10; 2026: 9.

32 papers.

Sort:

By area:

  1. 2023LLaFS: When Large Language Models Meet Few-Shot Segmentationcited by 48
  2. 2024Bridge the Points: Graph-based Few-shot Segment Anything Semanticallycited by 35
  3. 2024Hybrid Mamba for Few-Shot Segmentationcited by 21
  4. 2024Eliminating Feature Ambiguity for Few-Shot Segmentationcited by 19
  5. 2024Cross-modulated Attention Transformer for RGBT Trackingcited by 14
  6. 2025Unlocking the Power of SAM 2 for Few-Shot Segmentationcited by 11
  7. 2024Prompt-and-Transfer: Dynamic Class-aware Enhancement for Few-shot Segmentationcited by 10
  8. 2024A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsamplingcited by 7
  9. 2024AgMTR: Agent Mining Transformer for Few-shot Segmentation in Remote Sensingcited by 6
  10. 2024RobustEMD: Domain Robust Matching for Cross-domain Few-shot Medical Image Segmentationcited by 6
  11. 2025DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentationcited by 6
  12. 2025MOVE: Motion-Guided Few-Shot Video Object Segmentationcited by 6
20 more
  1. 2024Small Object Few-shot Segmentation for Vision-based Industrial Inspectioncited by 5
  2. 2024MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototypingcited by 5
  3. 2024Boosting Few-Shot Semantic Segmentation Via Segment Anything Modelcited by 4
  4. 2024Group-On: Boosting One-Shot Segmentation with Supportive Querycited by 3
  5. 2026Few-Shot Semantic Segmentation Meets SAM3cited by 3
  6. 2025UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelationcited by 1
  7. 2025ViRefSAM: Visual Reference-Guided Segment Anything Model for Remote Sensing Segmentationcited by 1
  8. 2025Object-level Correlation for Few-Shot Segmentationcited by 1
  9. 2025FS-SAM2: Adapting Segment Anything Model 2 for Few-Shot Semantic Segmentation via Low-Rank Adaptationcited by 1
  10. 2026Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentationcited by 1
  11. 2026Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matchingcited by 1
  12. 2025Inter- and Intra-image Refinement for Few Shot Segmentationcited by 0
  13. 2025Efficient Masked Attention Transformer for Few-Shot Classification and Segmentationcited by 0
  14. 2025Cross-Domain Few-Shot Segmentation via Ordinary Differential Equations over Time Intervalscited by 0
  15. 2026Adaptive Attention Distillation for Robust Few-Shot Segmentation under Environmental Perturbationscited by 0
  16. 2026Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptationcited by 0
  17. 2026Training-Free Generalized Few-Shot Segmentation through Open-Vocabulary Semantic Arbitrationcited by 0
  18. 2026Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentationcited by 0
  19. 2026P3-SAM: SAM with Perceptual Parallel Prompt for Few-Shot Strip Steel Surface Defect Segmentationcited by 0
  20. 2026Exploiting Target Knowledge from MLLMs for Robust Few-Shot Segmentationcited by 0