Spectral Transductive Refinement (STR), a training-free transductive inference rule that exploits the geometry of the complete support-query episode, operating entirely at inference time, 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.
Abstract
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.
Cross-domain few-shot action recognition (CD-FSAR) aims to recognise unseen action classes in a target domain from a handful of labelled videos. Despite advances in representation learning, CD-FSAR inference still relies on prototypes estimated from extremely limited support examples. To assess this bottleneck, we perf...
Query Prototype Rectification (QPR), a batch-transductive extension that uses gated unlabeled queries to update novel directions while preserving the selected geometry, is introduced, a batch-transductive extension that uses gated unlabeled queries to update novel directions while preserving the selected geometry.
Md Tanvir Hossain Saikat, Md Akib Haider, M. Tomal et al.· 0 citations
Few-shot adaptation often relies on an encoder's final global representation, leaving complementary information in intermediate layers underused. Combining these features is challenging because their dimensions can differ and their usefulness varies across tasks. We propose LAMP, Layerwise Adaptive Mixing of Predictors...
Zhi-Peng Ye, Feng Jiang, Qiu-Feng Wang et al.· 0 citations
Overall, WIPT provides a streaming-compatible form of test-time prototype adaptation that can improve difficult low-shot cross-domain decisions without target-time optimization.
Rushab Rasik Karania, T. Maul· arXiv.org· 0 citations
Across ResNet12 and Conv64 in 5-way 1-shot and 5-shot evaluation, SAMPLESELECT gives the best OOD accuracy among the compared methods and improves the matched full-representation control by 4.90-8.38 percentage points.
Feng-Rui Liu, Ning Shen, Yi Li et al.· arXiv.org· 0 citations
Training-free few-shot adaptation of vision-language models typically constructs a classifier from CLIP's final projected image representation, leaving intermediate representations unused. Combining them is not straightforward. Class scores from different representations differ in spread by orders of magnitude for the...
Pavodi Maniamfu, Vogel M. Kiketa, Zezina Kuzulu Kuetu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.