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

arXiv: https://arxiv.org/abs/2609.03829 · HTML: https://mlsanity.com/paper/2609.03829/

## 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 (most cited first, 22 of 22)

- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [Few-Shot Classification with Feature Map Reconstruction Networks](https://mlsanity.com/paper/2012.01506/) (2020)
- [DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning](https://mlsanity.com/paper/2003.06777/) (2020)
- [Few-Shot Learning with Localization in Realistic Settings](https://mlsanity.com/paper/1904.08502/) (2019)
- [Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples](https://mlsanity.com/paper/1805.04288/) (2018)
- [NDPNet: A novel non-linear data projection network for few-shot fine-grained image classification](https://mlsanity.com/paper/2106.06988/) (2021)
- [Dynamic Accumulated Attention Map for Interpreting Evolution of Decision-Making in Vision Transformer](https://mlsanity.com/paper/2503.14640/) (2025)
- [Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2411.01432/) (2024)
- [Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification](https://mlsanity.com/paper/2207.00784/) (2022)
- [Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Prompting](https://mlsanity.com/paper/2406.16422/) (2024)
- [Few-Shot Learning of Compact Models via Task-Specific Meta Distillation](https://mlsanity.com/paper/2210.09922/) (2022)
- [Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification](https://mlsanity.com/paper/2308.00093/) (2023)
- [Feature Complementation Architecture for Visual Place Recognition](https://mlsanity.com/paper/2506.12401/) (2025)
- [Meningioma Analysis and Diagnosis using Limited Labeled Samples](https://mlsanity.com/paper/2602.13335/) (2026)
- [Neuron Abandoning Attention Flow: Visual Explanation of Dynamics inside CNN Models](https://mlsanity.com/paper/2412.01202/) (2024)
- [Second-order Gaussian directional derivative representations for image high-resolution corner detection](https://mlsanity.com/paper/2601.08182/) (2026)
- [Deep learning-based neurodevelopmental assessment in preterm infants](https://mlsanity.com/paper/2601.11944/) (2026)
- [Feature Activation Map: Visual Explanation of Deep Learning Models for Image Classification](https://mlsanity.com/paper/2307.05017/) (2023)
- [Adaptive receptive field-based spatial-frequency feature reconstruction network for fine-grained few-shot image classification](https://mlsanity.com/paper/2604.16936/) (2026)
- [Frequency-Enhanced Dual-Subspace Networks for Few-Shot Fine-Grained Image Classification](https://mlsanity.com/paper/2604.14958/) (2026)
- [GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury prediction](https://mlsanity.com/paper/2606.02498/) (2026)

## 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.