mlsanityData to 14 Oct 2026

Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation

arXiv 2506.07376 ↗First posted 9 Jun 2025cs.CV cs.AI cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Cross-domain few-shot segmentation (CD-FSS) is proposed to pre-train the model on a source-domain dataset with sufficient samples, and then transfer the model to target-domain datasets where only a few samples are available for efficient fine-tuning. There are majorly two challenges in this task: (1) the domain gap and (2) fine-tuning with scarce data. To solve these challenges, we revisit the adapter-based methods, and discover an intriguing insight not explored in previous works: the adapter not only helps the fine-tuning of downstream tasks but also naturally serves as a domain information decoupler. Then, we delve into this finding for an interpretation, and find the model's inherent structure could lead to a natural decoupling of domain information. Building upon this insight, we propose the Domain Feature Navigator (DFN), which is a structure-based decoupler instead of loss-based ones like current works, to capture domain-specific information, thereby directing the model's attention towards domain-agnostic knowledge. Moreover, to prevent the potential excessive overfitting of DFN during the source-domain training, we further design the SAM-SVN method to constrain DFN from learning sample-specific knowledge. On target domains, we freeze the model and fine-tune the DFN to learn target-specific knowledge specific. Extensive experiments demonstrate that our method surpasses the state-of-the-art method in CD-FSS significantly by 2.69% and 4.68% MIoU in 1-shot and 5-shot scenarios, respectively.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 46 of its 60 references that are in the map. First posted on arXiv 9 Jun 2025.

Builds on

46 of 60 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2023Segment Anythingcited by 8,234
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  7. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  9. 2016Pyramid Scene Parsing Networkcited by 2,479
  10. 2016Matching Networks for One Shot Learningcited by 2,255
  11. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  12. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
34 more
  1. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  2. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
  3. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 576
  4. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 554
  5. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  6. 2017One-Shot Learning for Semantic Segmentationcited by 337
  7. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  8. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 323
  9. 2021Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworkscited by 284
  10. 2018DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Imagescited by 277
  11. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  12. 2023Personalize Segment Anything Model with One Shotcited by 250
  13. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  14. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 206
  15. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  16. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  17. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  18. 2019FSS-1000: A 1000-Class Dataset for Few-Shot Segmentationcited by 160
  19. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  20. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  21. 2022When Do Flat Minima Optimizers Work?cited by 78
  22. 2022Feature-Proxy Transformer for Few-Shot Segmentationcited by 58
  23. 2022Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigationcited by 45
  24. 2022Domain-invariant Feature Exploration for Domain Generalizationcited by 34
  25. 2024Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Miningcited by 30
  26. 2023Normalization Layers Are All That Sharpness-Aware Minimization Needscited by 27
  27. 2024Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learningcited by 26
  28. 2024APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentationcited by 26
  29. 2024Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentationcited by 22
  30. 2024Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentationcited by 20
  31. 2024Rethinking Few-shot 3D Point Cloud Semantic Segmentationcited by 18
  32. 2024Compositional Few-Shot Class-Incremental Learningcited by 18
  33. 2023RestNet: Boosting Cross-Domain Few-Shot Segmentation with Residual Transformation Networkcited by 17
  34. 2024Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentationcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptationcited by 6
  2. 2026Make It Up: Fake Images, Real Gains in Generalized Few-shot Semantic Segmentationcited by 1
  3. 2026Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matchingcited by 1
  4. 2025Inter- and Intra-image Refinement for Few Shot Segmentationcited by 0
  5. 2025Cross-Domain Few-Shot Segmentation via Ordinary Differential Equations over Time Intervalscited by 0
  6. 2026Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentationcited by 0
  7. 2026Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentationcited by 0