English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Few-shot learning aims to adapt models trained on the base dataset to noveltasks where the categories were not seen by the model before. This often leadsto a relatively uniform distribution of feature values across channels on novelclasses, posing challenges in determining channel importance for novel tasks.Standard few-shot learning methods employ geometric similarity metrics such ascosine similarity and negative Euclidean distance to gauge the semanticrelatedness between two features. However, features with high geometricsimilarities may carry distinct semantics, especially in the context offew-shot learning. In this paper, we demonstrate that the importance ranking offeature channels is a more reliable indicator for few-shot learning thangeometric similarity metrics. We observe that replacing the geometricsimilarity metric with Kendall's rank correlation only during inference is ableto improve the performance of few-shot learning across a wide range of methodsand datasets with different domains. Furthermore, we propose a carefullydesigned differentiable loss for meta-training to address thenon-differentiability issue of Kendall's rank correlation. By replacinggeometric similarity with differentiable Kendall's rank correlation, our methodcan integrate with numerous existing few-shot approaches and is ready forintegrating with future state-of-the-art methods that rely on geometricsimilarity metrics. Extensive experiments validate the efficacy of therank-correlation-based approach, showcasing a significant improvement infew-shot learning.

DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation