mlsanityData to 14 Oct 2026

Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentation

arXiv 2507.19140 ↗First posted 25 Jul 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper studies the few-shot segmentation (FSS) task, which aims to segment objects belonging to unseen categories in a query image by learning a model on a small number of well-annotated support samples. Our analysis of two mainstream FSS paradigms reveals that the predictions made by prototype learning methods are usually conservative, while those of affinity learning methods tend to be more aggressive. This observation motivates us to balance the conservative and aggressive information captured by these two types of FSS frameworks so as to improve the segmentation performance. To achieve this, we propose a **P**rototype-**A**ffinity **H**ybrid **Net**work (PAHNet), which introduces a Prototype-guided Feature Enhancement (PFE) module and an Attention Score Calibration (ASC) module in each attention block of an affinity learning model (called affinity learner). These two modules utilize the predictions generated by a pre-trained prototype learning model (called prototype predictor) to enhance the foreground information in support and query image representations and suppress the mismatched foreground-background (FG-BG) relationships between them, respectively. In this way, the aggressiveness of the affinity learner can be effectively mitigated, thereby eventually increasing the segmentation accuracy of our PAHNet method. Experimental results show that PAHNet outperforms most recently proposed methods across 1-shot and 5-shot settings on both PASCAL-5i and COCO-20i datasets, suggesting its effectiveness. The code is available at: [GitHub - tianyu-zou/PAHNet: Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentation (ICCV'25)](https://github.com/tianyu-zou/PAHNet)

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 35 of its 51 references that are in the map. First posted on arXiv 25 Jul 2025.

Builds on

35 of 51 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  5. 2017One-Shot Learning for Semantic Segmentationcited by 337
  6. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  7. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  8. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  9. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  10. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  11. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  12. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
23 more
  1. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  2. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  3. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  4. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  5. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  6. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  7. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  8. 2022Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentationcited by 43
  9. 2018Few-Shot Segmentation Propagation with Guided Networkscited by 29
  10. 2020BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentationcited by 28
  11. 2022Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentationcited by 28
  12. 2023Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentationcited by 26
  13. 2022Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentationcited by 23
  14. 2022Mask Matching Transformer for Few-Shot Segmentationcited by 22
  15. 2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
  16. 2024Hybrid Mamba for Few-Shot Segmentationcited by 21
  17. 2024Rethinking Prior Information Generation with CLIP for Few-Shot Segmentationcited by 20
  18. 2024Eliminating Feature Ambiguity for Few-Shot Segmentationcited by 19
  19. 2021Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentationcited by 15
  20. 2024Query-guided Prototype Evolution Network for Few-Shot Segmentationcited by 12
  21. 2023Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentationcited by 11
  22. 2021MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learningcited by 10
  23. 2023Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Exploiting Target Knowledge from MLLMs for Robust Few-Shot Segmentationcited by 0