mlsanityData to 14 Oct 2026

Unlocking the Power of SAM 2 for Few-Shot Segmentation

arXiv 2505.14100 ↗First posted 20 May 2025cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Few-Shot Segmentation (FSS) aims to learn class-agnostic segmentation on few classes to segment arbitrary classes, but at the risk of overfitting. To address this, some methods use the well-learned knowledge of foundation models (e.g., SAM) to simplify the learning process. Recently, SAM 2 has extended SAM by supporting video segmentation, whose class-agnostic matching ability is useful to FSS. A simple idea is to encode support foreground (FG) features as memory, with which query FG features are matched and fused. Unfortunately, the FG objects in different frames of SAM 2's video data are always the same identity, while those in FSS are different identities, i.e., the matching step is incompatible. Therefore, we design Pseudo Prompt Generator to encode pseudo query memory, matching with query features in a compatible way. However, the memories can never be as accurate as the real ones, i.e., they are likely to contain incomplete query FG, and some unexpected query background (BG) features, leading to wrong segmentation. Hence, we further design Iterative Memory Refinement to fuse more query FG features into the memory, and devise a Support-Calibrated Memory Attention to suppress the unexpected query BG features in memory. Extensive experiments have been conducted on PASCAL-5i and COCO-20i to validate the effectiveness of our design, e.g., the 1-shot mIoU can be 4.2% better than the best baseline.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 36 of its 43 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

36 of 43 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2023Segment Anythingcited by 8,234
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  7. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  8. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  9. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  10. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  11. 2017One-Shot Learning for Semantic Segmentationcited by 337
  12. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
24 more
  1. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 232
  2. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  3. 2014Simultaneous Detection and Segmentationcited by 159
  4. 2023Matcher: Segment Anything with One Shot Using All-Purpose Feature Matchingcited by 142
  5. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  6. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  7. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  8. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  9. 2024VRP-SAM: SAM with Visual Reference Promptcited by 75
  10. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  11. 2023LLaFS: When Large Language Models Meet Few-Shot Segmentationcited by 48
  12. 2024Bridge the Points: Graph-based Few-shot Segment Anything Semanticallycited by 35
  13. 2023Self-Calibrated Cross Attention Network for Few-Shot Segmentationcited by 32
  14. 2022Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentationcited by 23
  15. 2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
  16. 2022MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentationcited by 21
  17. 2024Hybrid Mamba for Few-Shot Segmentationcited by 21
  18. 2024Eliminating Feature Ambiguity for Few-Shot Segmentationcited by 19
  19. 2024A Simple Image Segmentation Framework via In-Context Examplescited by 19
  20. 2020Attention-based Joint Detection of Object and Semantic Partcited by 11
  21. 2023Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentationcited by 11
  22. 2023Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancementcited by 10
  23. 2023Task-Disruptive Background Suppression for Few-Shot Segmentationcited by 7
  24. 2024High-Performance Few-Shot Segmentation with Foundation Models: An Empirical Studycited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 8.

11 papers.

  1. 2025Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentationcited by 3
  2. 2026Few-Shot Semantic Segmentation Meets SAM3cited by 3
  3. 2025Omni-Referring Image Segmentationcited by 2
  4. 2026Boosting SAM for Cross-Domain Few-Shot Segmentation via Conditional Point Sparsificationcited by 1
  5. 2026Make It Up: Fake Images, Real Gains in Generalized Few-shot Semantic Segmentationcited by 1
  6. 2026Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matchingcited by 1
  7. 2025Inter- and Intra-image Refinement for Few Shot Segmentationcited by 0
  8. 2026Adaptive Attention Distillation for Robust Few-Shot Segmentation under Environmental Perturbationscited by 0
  9. 2026Training-Free Generalized Few-Shot Segmentation through Open-Vocabulary Semantic Arbitrationcited by 0
  10. 2026Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentationcited by 0
  11. 2026Exploiting Target Knowledge from MLLMs for Robust Few-Shot Segmentationcited by 0