Dual-Subspace Network for Few-Shot Fine-Grained Image Classification
Applied Sciences · 08.05.2026 · 16 (10) · 4664
DOI: 10.3390/app16104664 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 08.05.2026. Verfasst von Meijia Wang und 6 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Education Department of Shaanxi Province, People's Government of Shaanxi Province.
Abstract (Originalsprache)
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 Dual-Subspace Network (DSNet). Specifically, DSNet 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 DSNet 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.
Förderung
- Education Department of Shaanxi Province
- People's Government of Shaanxi Province
Zitieren
APA
Wang, M., Wang, G., Chu, H., Yao, B., Zhang, W., Wang, Y., & Yang, J. (2026). Dual-Subspace Network for Few-Shot Fine-Grained Image Classification. Applied Sciences, 16(10), 4664. https://doi.org/10.3390/app16104664
Vancouver
Wang M, Wang G, Chu H, Yao B, Zhang W, Wang Y, et al. Dual-Subspace Network for Few-Shot Fine-Grained Image Classification. Applied Sciences. 2026;16(10):4664. doi:10.3390/app16104664
BibTeX
@article{Wang2026,
author = {Wang, Meijia and Wang, Guochao and Chu, Haozhen and Yao, Bin and Zhang, Weichuan and Wang, Yuan and Yang, Junpo},
title = {Dual-Subspace Network for Few-Shot Fine-Grained Image Classification},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {10},
pages = {4664},
doi = {10.3390/app16104664}
}
EUVIMED