mlsanityData to 14 Oct 2026

Cross-Domain Few-Shot Semantic Segmentation via Doubly Matching Transformation

arXiv 2405.15265 ↗First posted 24 May 2024cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Cross-Domain Few-shot Semantic Segmentation (CD-FSS) aims to train generalized models that can segment classes from different domains with a few labeled images. Previous works have proven the effectiveness of feature transformation in addressing CD-FSS. However, they completely rely on support images for feature transformation, and repeatedly utilizing a few support images for each class may easily lead to overfitting and overlooking intra-class appearance differences. In this paper, we propose a Doubly Matching Transformation-based Network (DMTNet) to solve the above issue. Instead of completely relying on support images, we propose Self-Matching Transformation (SMT) to construct query-specific transformation matrices based on query images themselves to transform domain-specific query features into domain-agnostic ones. Calculating query-specific transformation matrices can prevent overfitting, especially for the meta-testing stage where only one or several images are used as support images to segment hundreds or thousands of images. After obtaining domain-agnostic features, we exploit a Dual Hypercorrelation Construction (DHC) module to explore the hypercorrelations between the query image with the foreground and background of the support image, based on which foreground and background prediction maps are generated and supervised, respectively, to enhance the segmentation result. In addition, we propose a Test-time Self-Finetuning (TSF) strategy to more accurately self-tune the query prediction in unseen domains. Extensive experiments on four popular datasets show that DMTNet achieves superior performance over state-of-the-art approaches. Code is available at https://github.com/ChenJiayi68/DMTNet.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 35 of its 45 references that are in the map. First posted on arXiv 24 May 2024.

Builds on

35 of 45 references.

References · 35

  1. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  2. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  5. 2016Pyramid Scene Parsing Networkcited by 2,479
  6. 2016Matching Networks for One Shot Learningcited by 2,255
  7. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  8. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  9. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
  10. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  11. 2017One-Shot Learning for Semantic Segmentationcited by 337
  12. 2018DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Imagescited by 277
23 more
  1. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  2. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  3. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  4. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  5. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  6. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  7. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 164
  8. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  9. 2019FSS-1000: A 1000-Class Dataset for Few-Shot Segmentationcited by 160
  10. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  11. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  12. 2019Switchable Whitening for Deep Representation Learningcited by 106
  13. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  14. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  15. 2022Semantic-Aware Domain Generalized Segmentationcited by 79
  16. 2021Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentationcited by 57
  17. 2018Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Trainingcited by 31
  18. 2022Interclass Prototype Relation for Few-Shot Segmentationcited by 25
  19. 2023RestNet: Boosting Cross-Domain Few-Shot Segmentation with Residual Transformation Networkcited by 17
  20. 2021Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentationcited by 15
  21. 2022Cross-domain Few-shot Segmentation with Transductive Fine-tuningcited by 7
  22. 2023Dense Affinity Matching for Few-Shot Segmentationcited by 5
  23. 2020Task-Adaptive Feature Transformer for Few-Shot Segmentationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 5.

13 papers.

Sort:

  1. 2024RobustEMD: Domain Robust Matching for Cross-domain Few-shot Medical Image Segmentationcited by 6
  2. 2024TAVP: Task-Adaptive Visual Prompt for Cross-domain Few-shot Segmentationcited by 4
  3. 2025Adapting In-Domain Few-Shot Segmentation to New Domains without Source Domain Retrainingcited by 4
  4. 2025Textual and Visual Guided Task Adaptation for Source-Free Cross-Domain Few-Shot Segmentationcited by 1
  5. 2025Take a Peek: Efficient Encoder Adaptation for Few-Shot Semantic Segmentation via LoRAcited by 1
  6. 2026Boosting SAM for Cross-Domain Few-Shot Segmentation via Conditional Point Sparsificationcited by 1
  7. 2025Cross-Domain Few-Shot Segmentation via Ordinary Differential Equations over Time Intervalscited by 0
  8. 2025Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Designcited by 0
  9. 2025DistillFSS: Synthesizing Few-Shot Knowledge into a Lightweight Segmentation Modelcited by 0
  10. 2026Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptationcited by 0
  11. 2026Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentationcited by 0
  12. 2026Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentationcited by 0
1 more
  1. 2026DAUPNet: Domain-Aware Uncertainty Modeling for Reliable Prototype Discrimination in Cross-Domain Few-Shot Semantic Segmentationcited by 0