mlsanityData to 14 Oct 2026

Phase-Aware Spatial-Frequency Fusion for Few-Shot Fine-Grained Image Classification

arXiv 2609.03829 ↗First posted 3 Sep 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Few-shot fine-grained image classification (FSFGIC) aims to classify similar images with limited labeled examples. This work highlights the critical yet underutilized role of phase information in capturing structural relationships within an image. This study introduces a novel plug-and-play amplitude-phase integration (API) module that effectively combines local and global frequency amplitude and phase information for obtaining more comprehensive feature descriptors. Additionally, a dedicated network, named PSF-Net, is proposed that adaptively fuses phase-based spatial and frequency information for FSFGIS. The designed PSF-Net can be easily integrated into standard episodic training architectures for end-to-end training from scratch. Extensive experiments on five public datasets demonstrate that the method outperforms existing state-of-the-art benchmarks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 80 references that are in the map. First posted on arXiv 3 Sep 2026.

Builds on

22 of 80 references.

References · 22

  1. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  2. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  3. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  4. 2020DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learningcited by 49
  5. 2019Few-Shot Learning with Localization in Realistic Settingscited by 34
  6. 2018Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examplescited by 27
  7. 2021NDPNet: A novel non-linear data projection network for few-shot fine-grained image classificationcited by 13
  8. 2025Dynamic Accumulated Attention Map for Interpreting Evolution of Decision-Making in Vision Transformercited by 12
  9. 2024Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learningcited by 11
  10. 2022Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classificationcited by 9
  11. 2024Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Promptingcited by 9
  12. 2022Few-Shot Learning of Compact Models via Task-Specific Meta Distillationcited by 5
10 more
  1. 2023Task-Oriented Channel Attention for Fine-Grained Few-Shot Classificationcited by 4
  2. 2025Feature Complementation Architecture for Visual Place Recognitioncited by 4
  3. 2026Meningioma Analysis and Diagnosis using Limited Labeled Samplescited by 4
  4. 2024Neuron Abandoning Attention Flow: Visual Explanation of Dynamics inside CNN Modelscited by 3
  5. 2026Second-order Gaussian directional derivative representations for image high-resolution corner detectioncited by 3
  6. 2026Deep learning-based neurodevelopmental assessment in preterm infantscited by 3
  7. 2023Feature Activation Map: Visual Explanation of Deep Learning Models for Image Classificationcited by 2
  8. 2026Adaptive receptive field-based spatial-frequency feature reconstruction network for fine-grained few-shot image classificationcited by 2
  9. 2026Frequency-Enhanced Dual-Subspace Networks for Few-Shot Fine-Grained Image Classificationcited by 1
  10. 2026GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury predictioncited by 1

Built on by

Not cited yet.