mlsanityData to 14 Oct 2026

Kernel Relative-prototype Spectral Filtering for Few-shot Learning

arXiv 2207.11685 ↗First posted 24 Jul 2022cs.CV cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Few-shot learning performs classification tasks and regression tasks on scarce samples. As one of the most representative few-shot learning models, Prototypical Network represents each class as sample average, or a prototype, and measures the similarity of samples and prototypes by Euclidean distance. In this paper, we propose a framework of spectral filtering (shrinkage) for measuring the difference between query samples and prototypes, or namely the relative prototypes, in a reproducing kernel Hilbert space (RKHS). In this framework, we further propose a method utilizing Tikhonov regularization as the filter function for few-shot classification. We conduct several experiments to verify our method utilizing different kernels based on the miniImageNet dataset, tiered-ImageNet dataset and CIFAR-FS dataset. The experimental results show that the proposed model can perform the state-of-the-art. In addition, the experimental results show that the proposed shrinkage method can boost the performance. Source code is available at https://github.com/zhangtao2022/DSFN.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 35 of its 51 references that are in the map. First posted on arXiv 24 Jul 2022.

Builds on

35 of 51 references.

References · 35

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  3. 2016Matching Networks for One Shot Learningcited by 2,255
  4. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  5. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  6. 2019A Closer Look at Few-shot Classificationcited by 684
  7. 2016Learning to learn by gradient descent by gradient descentcited by 620
  8. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  9. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  10. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  11. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  12. 2018Meta-learning with differentiable closed-form solverscited by 397
23 more
  1. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  2. 2016Kernel Mean Embedding of Distributions: A Review and Beyondcited by 364
  3. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  4. 2017Meta Networkscited by 269
  5. 2018Meta-Learning: A Surveycited by 256
  6. 2019Hyperbolic Image Embeddingscited by 221
  7. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
  8. 2019Improved Few-Shot Visual Classificationcited by 115
  9. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  10. 2019Prototype Rectification for Few-Shot Learningcited by 97
  11. 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
  12. 2020Laplacian Regularized Few-Shot Learningcited by 92
  13. 2020Embedding Propagation: Smoother Manifold for Few-Shot Classificationcited by 80
  14. 2021Relational Embedding for Few-Shot Classificationcited by 74
  15. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  16. 2020A Refined Laser Method and Faster Matrix Multiplicationcited by 56
  17. 2020Multimodal Prototypical Networks for Few-shot Learningcited by 48
  18. 2017Gaussian Prototypical Networks for Few-Shot Learning on Omniglotcited by 20
  19. 2019Variational Metric Scaling for Metric-Based Meta-Learningcited by 17
  20. 2014Kernel Mean Shrinkage Estimatorscited by 16
  21. 2013Kernel Mean Estimation and Stein's Effectcited by 11
  22. 2018Zero-Shot Kernel Learningcited by 11
  23. 2014Kernel Mean Estimation via Spectral Filteringcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 1.

4 papers.

  1. 2024Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learningcited by 11
  2. 2023SENet: A Spectral Filtering Approach to Represent Exemplars for Few-shot Learningcited by 0
  3. 2024LDCA: Local Descriptors with Contextual Augmentation for Few-Shot Learningcited by 0
  4. 2025ProtoTopic: Prototypical Network for Few-Shot Medical Topic Modelingcited by 0