Metraipolis › archive › dc_11e6bdfdab67

Phase-Aware Spatial-Frequency Fusion for Few-Shot Fine-Grained Image Classification — arXiv:2609.03829

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.03829
License (as archived): CC0-1.0
Archived: 2026-10-17T01:12:07.516Z
SHA-256 of the archived text: 09943b5448283c26d2ca6455aba6e07891fa9cb2c268db488d45294bbbec0a26
Stable URL of this page: https://metraipolis.com/documento/dc_11e6bdfdab67

How to cite

Phase-Aware Spatial-Frequency Fusion for Few-Shot Fine-Grained Image Classification — arXiv:2609.03829 — arXiv (en), https://arxiv.org/abs/2609.03829 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_11e6bdfdab67 (Metraipolis archive dc_11e6bdfdab67, sha256 09943b5448283c26d2ca6455aba6e07891fa9cb2c268db488d45294bbbec0a26)

BibTeX

@misc{dc11e6bdfdab67,
  title = {Phase-Aware Spatial-Frequency Fusion for Few-Shot Fine-Grained Image Classification — arXiv:2609.03829},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03829},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_11e6bdfdab67; sha256 09943b5448283c26d2ca6455aba6e07891fa9cb2c268db488d45294bbbec0a26},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03829. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.03829 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T00:28:03.006Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).