mlsanityData to 14 Oct 2026

Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulation

arXiv 2207.08547 ↗First posted 18 Jul 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Traditional fine-grained image classification typically relies on large-scale training samples with annotated ground-truth. However, some sub-categories have few available samples in real-world applications, and current few-shot models still have difficulty in distinguishing subtle differences among fine-grained categories. To solve this challenge, we propose a novel few-shot fine-grained image classification network (FicNet) using multi-frequency neighborhood (MFN) and double-cross modulation (DCM). MFN focuses on both spatial domain and frequency domain to capture multi-frequency structural representations, which reduces the influence of appearance and background changes to the intra-class distance. DCM consists of bi-crisscross component and double 3D cross-attention component. It modulates the representations by considering global context information and inter-class relationship respectively, which enables the support and query samples respond to the same parts and accurately identify the subtle inter-class differences. The comprehensive experiments on three fine-grained benchmark datasets for two few-shot tasks verify that FicNet has excellent performance compared to the state-of-the-art methods. Especially, the experiments on two datasets, "Caltech-UCSD Birds" and "Stanford Cars", can obtain classification accuracy 93.17% and 95.36%, respectively. They are even higher than that the general fine-grained image classification methods can achieve.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 44 of its 72 references that are in the map. First posted on arXiv 18 Jul 2022.

Builds on

44 of 72 references.

References · 44

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2016Matching Networks for One Shot Learningcited by 2,255
  5. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  6. 2019A Closer Look at Few-shot Classificationcited by 684
  7. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 549
  8. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  9. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  10. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  11. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  12. 2019Cross Attention Network for Few-shot Classificationcited by 219
32 more
  1. 2020Learning in the Frequency Domaincited by 198
  2. 2020FcaNet: Frequency Channel Attention Networkscited by 179
  3. 2021Benchmarking Representation Learning for Natural World Image Collectionscited by 168
  4. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  5. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
  6. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  7. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  8. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  9. 2014Part-based R-CNNs for Fine-grained Category Detectioncited by 109
  10. 2021Relational Embedding for Few-Shot Classificationcited by 74
  11. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  12. 2019Dense Classification and Implanting for Few-Shot Learningcited by 56
  13. 2021Pareto Self-Supervised Training for Few-Shot Learningcited by 52
  14. 2022Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classificationcited by 50
  15. 2018Deep Residual Learning in the JPEG Transform Domaincited by 44
  16. 2019Dynamic Context Correspondence Network for Semantic Alignmentcited by 43
  17. 2019Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classificationcited by 36
  18. 2020BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classificationcited by 30
  19. 2018Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examplescited by 27
  20. 2020Mixture-based Feature Space Learning for Few-shot Image Classificationcited by 23
  21. 2019Multi-Channel Deep Networks for Block-Based Image Compressive Sensingcited by 22
  22. 2022Task Discrepancy Maximization for Fine-grained Few-Shot Classificationcited by 21
  23. 2020TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samplescited by 13
  24. 2021NDPNet: A novel non-linear data projection network for few-shot fine-grained image classificationcited by 13
  25. 2022Multi-level Second-order Few-shot Learningcited by 12
  26. 2021Few-Shot Learning by Integrating Spatial and Frequency Representationcited by 11
  27. 2021FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpaintingcited by 11
  28. 2019Few-shot Learning for Domain-specific Fine-grained Image Classificationcited by 10
  29. 2020Multi-scale Adaptive Task Attention Network for Few-Shot Learningcited by 10
  30. 2021Multi-level Metric Learning for Few-shot Image Recognitioncited by 8
  31. 2021Fine-Grained Few Shot Learning with Foreground Object Transformationcited by 7
  32. 2019Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learningcited by 4

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2024Harnessing the Power of Local Representations for Few-Shot Classificationcited by 1
  2. 2025FiGKD: Fine-Grained Knowledge Distillation via High-Frequency Detail Transfercited by 0
  3. 2025FreqGRL: Suppressing Low-Frequency Bias and Mining High-Frequency Knowledge for Cross-Domain Few-Shot Learningcited by 0
  4. 2025CausalFSFG: Rethinking Few-Shot Fine-Grained Visual Categorization from Causal Perspectivecited by 0