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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In modern classification tasks, the number of labels is getting larger andlarger, as is the size of the datasets encountered in practice. As the numberof classes increases, class ambiguity and class imbalance become more and moreproblematic to achieve high top-1 accuracy. Meanwhile, Top-K metrics (metricsallowing K guesses) have become popular, especially for performance reporting.Yet, proposing top-K losses tailored for deep learning remains a challenge,both theoretically and practically. In this paper we introduce a stochastictop-K hinge loss inspired by recent developments on top-K calibrated losses.Our proposal is based on the smoothing of the top-K operator building on theflexible "perturbed optimizer" framework. We show that our loss functionperforms very well in the case of balanced datasets, while benefiting from asignificantly lower computational time than the state-of-the-art top-K lossfunction. In addition, we propose a simple variant of our loss for theimbalanced case. Experiments on a heavy-tailed dataset show that our lossfunction significantly outperforms other baseline loss functions.

Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification