mlsanityData to 14 Oct 2026

Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation

arXiv 2410.22135 ↗First posted 29 Oct 2024cs.CV cs.AIcited by 17

Not on the map. Why?

Abstract (arXiv)

Cross-domain few-shot segmentation (CD-FSS) is proposed to first pre-train the model on a large-scale source-domain dataset, and then transfer the model to data-scarce target-domain datasets for pixel-level segmentation. The significant domain gap between the source and target datasets leads to a sharp decline in the performance of existing few-shot segmentation (FSS) methods in cross-domain scenarios. In this work, we discover an intriguing phenomenon: simply filtering different frequency components for target domains can lead to a significant performance improvement, sometimes even as high as 14% mIoU. Then, we delve into this phenomenon for an interpretation, and find such improvements stem from the reduced inter-channel correlation in feature maps, which benefits CD-FSS with enhanced robustness against domain gaps and larger activated regions for segmentation. Based on this, we propose a lightweight frequency masker, which further reduces channel correlations by an Amplitude-Phase Masker (APM) module and an Adaptive Channel Phase Attention (ACPA) module. Notably, APM introduces only 0.01% additional parameters but improves the average performance by over 10%, and ACPA imports only 2.5% parameters but further improves the performance by over 1.5%, which significantly surpasses the state-of-the-art CD-FSS methods.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 42 of its 53 references that are in the map. First posted on arXiv 29 Oct 2024.

Builds on

42 of 53 references.

References · 42

  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. 2017Squeeze-and-Excitation Networkscited by 4,789
  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. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,057
  12. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
30 more
  1. 2018MINE: Mutual Information Neural Estimationcited by 683
  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. 2019Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networkscited by 368
  7. 2017One-Shot Learning for Semantic Segmentationcited by 337
  8. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  9. 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
  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. 2021Global Filter Networks for Image Classificationcited by 260
  13. 2023Personalize Segment Anything Model with One Shotcited by 250
  14. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  15. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 211
  16. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  17. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  18. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  19. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  20. 2019FSS-1000: A 1000-Class Dataset for Few-Shot Segmentationcited by 160
  21. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  22. 2021Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domaincited by 71
  23. 2018Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?cited by 62
  24. 2022Feature-Proxy Transformer for Few-Shot Segmentationcited by 58
  25. 2022Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigationcited by 45
  26. 2022Deep Frequency Filtering for Domain Generalizationcited by 43
  27. 2023Decompose, Adjust, Compose: Effective Normalization by Playing with Frequency for Domain Generalizationcited by 26
  28. 2022Channel Importance Matters in Few-Shot Image Classificationcited by 20
  29. 2019A Broader Study of Cross-Domain Few-Shot Learningcited by 10
  30. 2024Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learningcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 7.

17 papers.

Sort:

By area:

  1. 2025The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentationcited by 8
  2. 2025Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentationcited by 7
  3. 2025Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasetscited by 6
  4. 2025Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptationcited by 6
  5. 2025Towards Intelligent Transportation with Pedestrians and Vehicles In-the-Loop: A Surveillance Video-Assisted Federated Digital Twin Frameworkcited by 1
  6. 2025FAD: Frequency Adaptation and Diversion for Cross-domain Few-shot Learningcited by 1
  7. 2025Contrastive Graph Modeling for Cross-Domain Few-Shot Medical Image Segmentationcited by 1
  8. 2026Boosting SAM for Cross-Domain Few-Shot Segmentation via Conditional Point Sparsificationcited by 1
  9. 2026Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matchingcited by 1
  10. 2025Inter- and Intra-image Refinement for Few Shot Segmentationcited by 0
  11. 2025Cross-Domain Few-Shot Segmentation via Ordinary Differential Equations over Time Intervalscited by 0
  12. 2025FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Networkcited by 0
5 more
  1. 2026Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptationcited by 0
  2. 2026Geometry-aware Prototype Learning for Cross-domain Few-shot Medical Image Segmentationcited by 0
  3. 2026Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentationcited by 0
  4. 2026Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentationcited by 0
  5. 2026The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answeringcited by 0