mlsanityData to 14 Oct 2026

Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning

arXiv 2411.01432 ↗First posted 3 Nov 2024cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Meta-learning offers a promising avenue for few-shot learning (FSL), enabling models to glean a generalizable feature embedding through episodic training on synthetic FSL tasks in a source domain. Yet, in practical scenarios where the target task diverges from that in the source domain, meta-learning based method is susceptible to over-fitting. To overcome this, we introduce a novel framework, Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning, which is crafted to comprehensively exploit the cross-domain transferable image prior that each image can be decomposed into complementary low-frequency content details and high-frequency robust structural characteristics. Motivated by this insight, we propose to decompose each query image into its high-frequency and low-frequency components, and parallel incorporate them into the feature embedding network to enhance the final category prediction. More importantly, we introduce a feature reconstruction prior and a prediction consistency prior to separately encourage the consistency of the intermediate feature as well as the final category prediction between the original query image and its decomposed frequency components. This allows for collectively guiding the network's meta-learning process with the aim of learning generalizable image feature embeddings, while not introducing any extra computational cost in the inference phase. Our framework establishes new state-of-the-art results on multiple cross-domain few-shot learning benchmarks.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 38 of its 55 references that are in the map. First posted on arXiv 3 Nov 2024.

Builds on

38 of 55 references.

References · 38

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2016Matching Networks for One Shot Learningcited by 2,255
  6. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  7. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  8. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  10. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 972
  11. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  12. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
26 more
  1. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  2. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  3. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 211
  4. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
  5. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  6. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 118
  7. 2021Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Biascited by 83
  8. 2020Meta-Learning with Adaptive Hyperparameterscited by 79
  9. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  10. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  11. 2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
  12. 2022HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learningcited by 55
  13. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  14. 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
  15. 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
  16. 2022Adversarial Feature Augmentation for Cross-domain Few-shot Classificationcited by 36
  17. 2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
  18. 2021Ranking Distance Calibration for Cross-Domain Few-Shot Learningcited by 27
  19. 2022Test-time Fourier Style Calibration for Domain Generalizationcited by 25
  20. 2022Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learningcited by 23
  21. 2021Combining Diverse Feature Priorscited by 12
  22. 2021Few-Shot Learning by Integrating Spatial and Frequency Representationcited by 11
  23. 2022Kernel Relative-prototype Spectral Filtering for Few-shot Learningcited by 4
  24. 2023LSFSL: Leveraging Shape Information in Few-shot Learningcited by 4
  25. 2019Texture Bias Of CNNs Limits Few-Shot Classification Performancecited by 3
  26. 2023Domain Generalization Emerges from Dreamingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

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

11 papers.

  1. 2025VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learningcited by 7
  2. 2025Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservationcited by 2
  3. 2026DVLA-RL: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learningcited by 2
  4. 2026Adaptive receptive field-based spatial-frequency feature reconstruction network for fine-grained few-shot image classificationcited by 2
  5. 2025FAD: Frequency Adaptation and Diversion for Cross-domain Few-shot Learningcited by 1
  6. 2025SS-DC: Spatial-Spectral Decoupling and Coupling Across Visible-Infrared Gap for Domain Adaptive Object Detectioncited by 1
  7. 2025Color as the Impetus: Transforming Few-Shot Learnercited by 0
  8. 2026SRasP: Self-Reorientation Adversarial Style Perturbation for Cross-Domain Few-Shot Learningcited by 0
  9. 2026STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognitioncited by 0
  10. 2026Phase-Aware Spatial-Frequency Fusion for Few-Shot Fine-Grained Image Classificationcited by 0
  11. 2026Training-Free Spectral Transductive Refinement for Cross-Domain Few-Shot Classificationcited by 0