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

Classification on long-tailed distributed data is a challenging problem,which suffers from serious class-imbalance and hence poor performance on tailclasses with only a few samples. Owing to this paucity of samples, learning onthe tail classes is especially challenging for the fine-tuning whentransferring a pretrained model to a downstream task. In this work, we presenta simple modification of standard fine-tuning to cope with these challenges.Specifically, we propose a two-stage fine-tuning: we first fine-tune the finallayer of the pretrained model with class-balanced reweighting loss, and then weperform the standard fine-tuning. Our modification has several benefits: (1) itleverages pretrained representations by only fine-tuning a small portion of themodel parameters while keeping the rest untouched; (2) it allows the model tolearn an initial representation of the specific task; and importantly (3) itprotects the learning of tail classes from being at a disadvantage during themodel updating. We conduct extensive experiments on synthetic datasets of bothtwo-class and multi-class tasks of text classification as well as a real-worldapplication to ADME (i.e., absorption, distribution, metabolism, and excretion)semantic labeling. The experimental results show that the proposed two-stagefine-tuning outperforms both fine-tuning with conventional loss and fine-tuningwith a reweighting loss on the above datasets.

Two-Stage Fine-Tuning: A Novel Strategy for Learning Class-Imbalanced Data