Frequency-Enhanced Dual-Subspace Networks for Few-Shot Fine-Grained Image Classification
Not on the map. Why?
Abstract (arXiv)
Few-shot fine-grained image classification aims to recognize subcategories with high visual similarity using only a limited number of annotated samples. Existing metric learning-based methods typically rely solely on spatial domain features. Confined to this single perspective, models inevitably suffer from inherent texture biases, entangling essential structural details with high-frequency background noise. Furthermore, lacking cross-view geometric constraints, single-view metrics tend to overfit this noise, resulting in structural instability under few-shot conditions. To address these issues, this paper proposes the Frequency-Enhanced Dual-Subspace Network (FEDSNet). Specifically, FEDSNet utilizes the Discrete Cosine Transform (DCT) and a low-pass filtering mechanism to explicitly isolate low-frequency global structural components from spatial features, thereby suppressing background interference. Truncated Singular Value Decomposition (SVD) is employed to construct independent, low-rank linear subspaces for both spatial texture and frequency structural features. An adaptive gating mechanism is designed to dynamically fuse the projection distances from these dual views. This strategy leverages the structural stability of the frequency subspace to prevent the spatial subspace from overfitting to background features. Extensive experiments on four benchmark datasets - CUB-200-2011, Stanford Cars, Stanford Dogs, and FGVC-Aircraft - demonstrate that FEDSNet exhibits excellent classification performance and robustness, achieving highly competitive results compared to existing metric learning algorithms. Complexity analysis further confirms that the proposed network achieves a favorable balance between high accuracy and computational efficiency, providing an effective new paradigm for few-shot fine-grained visual recognition.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 41 of its 70 references that are in the map. First posted on arXiv 16 Apr 2026.
Builds on
41 of 70 references.
References · 41
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2017Squeeze-and-Excitation Networkscited by 4,789
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2018CBAM: Convolutional Block Attention Modulecited by 2,477
- 2016Matching Networks for One Shot Learningcited by 2,255
- 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
- 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
- 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 523
29 more
- 2018Meta-Learning with Latent Embedding Optimizationcited by 476
- 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
- 2014Deep metric learning using Triplet networkcited by 422
- 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
- 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
- 2021Global Filter Networks for Image Classificationcited by 260
- 2020Learning in the Frequency Domaincited by 198
- 2020FcaNet: Frequency Channel Attention Networkscited by 179
- 2020CrossTransformers: spatially-aware few-shot transfercited by 174
- 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
- 2014A Tutorial on Principal Component Analysiscited by 141
- 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 126
- 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
- 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
- 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
- 2020DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learningcited by 49
- 2017SVDNet for Pedestrian Retrievalcited by 43
- 2019Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classificationcited by 36
- 2020BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classificationcited by 30
- 2022Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignmentcited by 29
- 2020Mixture-based Feature Space Learning for Few-shot Image Classificationcited by 23
- 2020Asymmetric Distribution Measure for Few-shot Learningcited by 18
- 2020TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samplescited by 13
- 2022Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classificationcited by 12
- 2022Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classificationcited by 9
- 2021Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classificationcited by 8
- 2025Feature Complementation Architecture for Visual Place Recognitioncited by 4
- 2026Meningioma Analysis and Diagnosis using Limited Labeled Samplescited by 4
- 2026Deep learning-based neurodevelopmental assessment in preterm infantscited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.