mlsanityData to 7 Oct 2026

Few-Shot Learning by Integrating Spatial and Frequency Representation

arXiv 2105.05348 ↗First posted 11 May 2021cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Human beings can recognize new objects with only a few labeled examples, however, few-shot learning remains a challenging problem for machine learning systems. Most previous algorithms in few-shot learning only utilize spatial information of the images. In this paper, we propose to integrate the frequency information into the learning model to boost the discrimination ability of the system. We employ Discrete Cosine Transformation (DCT) to generate the frequency representation, then, integrate the features from both the spatial domain and frequency domain for classification. The proposed strategy and its effectiveness are validated with different backbones, datasets, and algorithms. Extensive experiments demonstrate that the frequency information is complementary to the spatial representations in few-shot classification. The classification accuracy is boosted significantly by integrating features from both the spatial and frequency domains in different few-shot learning tasks.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 27 of its 46 references that are in the map. First posted on arXiv 11 May 2021.

Builds on

27 of 46 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2016Wide Residual Networkscited by 3,057
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  8. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  9. 2019A Closer Look at Few-shot Classificationcited by 679
  10. 2018Meta-learning with differentiable closed-form solverscited by 395
  11. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  12. 2020Learning in the Frequency Domaincited by 196
15 more
  1. 2018Low-Shot Learning from Imaginary Datacited by 181
  2. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
  3. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  4. 2020DPGN: Distribution Propagation Graph Network for Few-shot Learningcited by 79
  5. 2020Leveraging the Feature Distribution in Transfer-based Few-Shot Learningcited by 72
  6. 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
  7. 2019Few-Shot Learning via Saliency-guided Hallucination of Samplescited by 49
  8. 2019Few-Shot Learning with Global Class Representationscited by 44
  9. 2021SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular imagescited by 33
  10. 2019Coloring With Limited Data: Few-Shot Colorization via Memory-Augmented Networkscited by 32
  11. 2015Compressing Convolutional Neural Networkscited by 25
  12. 2020Deep Feature Augmentation for Occluded Image Classificationcited by 21
  13. 2019Band-limited Training and Inference for Convolutional Neural Networkscited by 13
  14. 2020Location-Aware Box Reasoning for Anchor-Based Single-Shot Object Detectioncited by 7
  15. 2020Multi-Resolution Fusion and Multi-scale Input Priors Based Crowd Countingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 4; 2023: 0; 2024: 3; 2025: 1; 2026: 1.

11 papers.

  1. 2022Accumulated Trivial Attention Matters in Vision Transformers on Small Datasetscited by 15
  2. 2021Audio-Visual Transformer Based Crowd Countingcited by 12
  3. 2024Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learningcited by 11
  4. 2022The Self-Optimal-Transport Feature Transformcited by 7
  5. 2022Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulationcited by 4
  6. 2021Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 2
  7. 2024The Balanced-Pairwise-Affinities Feature Transformcited by 2
  8. 2022Class-Specific Channel Attention for Few-Shot Learningcited by 0
  9. 2024Image edge enhancement for effective image classificationcited by 0
  10. 2025FreqGRL: Suppressing Low-Frequency Bias and Mining High-Frequency Knowledge for Cross-Domain Few-Shot Learningcited by 0
  11. 2026Spectral Analysis for Sparse Matrix Computation: Insights and Potentialcited by 0