mlsanityData to 14 Oct 2026

Beyond Visual Cues: Leveraging General Semantics as Support for Few-Shot Segmentation

arXiv 2511.16435 ↗First posted 20 Nov 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Few-shot segmentation (FSS) aims to segment novel classes under the guidance of limited support samples by a meta-learning paradigm. Existing methods mainly mine references from support images as meta guidance. However, due to intra-class variations among visual representations, the meta information extracted from support images cannot produce accurate guidance to segment untrained classes. In this paper, we argue that the references from support images may not be essential, the key to the support role is to provide unbiased meta guidance for both trained and untrained classes. We then introduce a Language-Driven Attribute Generalization (LDAG) architecture to utilize inherent target property language descriptions to build robust support strategy. Specifically, to obtain an unbiased support representation, we design a Multi-attribute Enhancement (MaE) module, which produces multiple detailed attribute descriptions of the target class through Large Language Models (LLMs), and then builds refined visual-text prior guidance utilizing multi-modal matching. Meanwhile, due to text-vision modal shift, attribute text struggles to promote visual feature representation, we design a Multi-modal Attribute Alignment (MaA) to achieve cross-modal interaction between attribute texts and visual feature. Experiments show that our proposed method outperforms existing approaches by a clear margin and achieves the new state-of-the art performance. The code will be released.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 49 of its 67 references that are in the map. First posted on arXiv 20 Nov 2025.

Builds on

49 of 67 references.

References · 49

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2023Segment Anythingcited by 8,234
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  9. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  10. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  11. 2021Image Segmentation Using Text and Image Promptscited by 512
  12. 2017One-Shot Learning for Semantic Segmentationcited by 337
37 more
  1. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  2. 2023Personalize Segment Anything Model with One Shotcited by 250
  3. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  4. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  5. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  6. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  7. 2023Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imagingcited by 161
  8. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  9. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  10. 2022CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentationcited by 118
  11. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  12. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  13. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  14. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  15. 2024VRP-SAM: SAM with Visual Reference Promptcited by 75
  16. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  17. 2023SAM.MD: Zero-shot medical image segmentation capabilities of the Segment Anything Modelcited by 61
  18. 2023Learning Mask-aware CLIP Representations for Zero-Shot Segmentationcited by 57
  19. 2024ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentationcited by 49
  20. 2021PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Maskcited by 31
  21. 2024Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Miningcited by 30
  22. 2022A Strong Baseline for Generalized Few-Shot Semantic Segmentationcited by 22
  23. 2022Mask Matching Transformer for Few-Shot Segmentationcited by 22
  24. 2023Multi-Modal Prototypes for Open-World Semantic Segmentationcited by 22
  25. 2024Hybrid Mamba for Few-Shot Segmentationcited by 21
  26. 2024Rethinking Prior Information Generation with CLIP for Few-Shot Segmentationcited by 20
  27. 2023Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyondcited by 19
  28. 2024Eliminating Feature Ambiguity for Few-Shot Segmentationcited by 19
  29. 2021Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localizationcited by 18
  30. 2020Self-Supervised Tuning for Few-Shot Segmentationcited by 17
  31. 2025Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Modelcited by 17
  32. 2023Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentationcited by 10
  33. 2024Prompt-and-Transfer: Dynamic Class-aware Enhancement for Few-shot Segmentationcited by 10
  34. 2025Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentationcited by 9
  35. 2024RevSAM2: Prompt SAM2 for Medical Image Segmentation via Reverse-Propagation without Fine-tuningcited by 7
  36. 2025DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentationcited by 6
  37. 2025Unbiased Semantic Decoding with Vision Foundation Models for Few-shot Segmentationcited by 1

Built on by

Not cited yet.