Metraipolis › archive › dc_63e6e55c874f

Training-Free Spectral Transductive Refinement for Cross-Domain Few-Shot Classification — arXiv:2609.23758

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23758
License (as archived)
CC0-1.0
Archived
2026-10-09T22:03:47.091Z
SHA-256 of the archived text
73eef5748a7d1d626ff54ae5f34b3d1e02c1453e99fd75f2824d5609a2edb10c
Stable URL of this page
https://metraipolis.com/documento/dc_63e6e55c874f

How to cite

Training-Free Spectral Transductive Refinement for Cross-Domain Few-Shot Classification — arXiv:2609.23758 — arXiv (en), https://arxiv.org/abs/2609.23758 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_63e6e55c874f (Metraipolis archive dc_63e6e55c874f, sha256 73eef5748a7d1d626ff54ae5f34b3d1e02c1453e99fd75f2824d5609a2edb10c)
BibTeX
@misc{dc63e6e55c874f,
  title = {Training-Free Spectral Transductive Refinement for Cross-Domain Few-Shot Classification — arXiv:2609.23758},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23758},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_63e6e55c874f; sha256 73eef5748a7d1d626ff54ae5f34b3d1e02c1453e99fd75f2824d5609a2edb10c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23758. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Few-shot recognition with frozen visual features is especially fragile under domain shift and one-shot supervision, where a single labelled image is an unreliable estimate of its class. We ask how far this fragility can be reduced purely at test time, without retraining the encoder or augmenting the source domain. We present Spectral Transductive Refinement (STR), a training-free transductive inference rule that exploits the geometry of the complete support-query episode. Given frozen embeddings, STR builds a joint k-nearest-neighbour graph, maps the episode into a normalized-Laplacian spectral coordinate system, initializes class representatives from the labelled support, and iteratively refines them using pseudo-labelled queries. We evaluate STR under two protocols. A controlled component study with frozen ResNet-18 features shows that spectral refinement consistently improves over single-prototype spectral initialization across five shifted domains, with the largest gains in the one-shot regime where support estimates are weakest. We then benchmark STR against recent Cross-Domain Few-Shot Learning (CD-FSL) methods using the standard miniImageNet-pretrained ResNet-10 backbone over eight established target domains. Operating entirely at inference time, STR attains the highest 1-shot average among compared methods and remains competitive at 5-shot, rivalling approaches relying on heavy source-domain meta-training augmentations. Because STR is transductive, we report its setting explicitly. Diagnostics attribute its gains to iterative refinement in spectral coordinates rather than added prototype capacity, which remains inactive in our configuration.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.23758 — 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 2026-10-09T21:45:20.949Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).