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

The goal of few-shot classification is to learn a model that can classifynovel classes using only a few training examples. Despite the promising resultsshown by existing meta-learning algorithms in solving the few-shotclassification problem, there still remains an important challenge: how togeneralize to unseen domains while meta-learning on multiple seen domains? Inthis paper, we propose an optimization-based meta-learning method, calledCombining Domain-Specific Meta-Learners (CosML), that addresses thecross-domain few-shot classification problem. CosML first trains a set ofmeta-learners, one for each training domain, to learn prior knowledge (i.e.,meta-parameters) specific to each domain. The domain-specific meta-learners arethen combined in the \emph{parameter space}, by taking a weighted average oftheir meta-parameters, which is used as the initialization parameters of a tasknetwork that is quickly adapted to novel few-shot classification tasks in anunseen domain. Our experiments show that CosML outperforms a range ofstate-of-the-art methods and achieves strong cross-domain generalizationability.

Combining Domain-Specific Meta-Learners in the Parameter Space for Cross-Domain Few-Shot Classification