SOURCE-LINKED INTELLIGENCE

Training-Free Spectral Transductive Refinement for Cross-Domain Few-Shot Classification

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

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 spectra

Read original source ↗ Open in workspace

recordType

paper

region

Global