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

Semi-supervised Fine-Grained Recognition is a challenge task due to thedifficulty of data imbalance, high inter-class similarity and domain mismatch.Recent years, this field has witnessed great progress and many methods hasgained great performance. However, these methods can hardly generalize to thelarge-scale datasets, such as Semi-iNat, as they are prone to suffer from noisein unlabeled data and the incompetence for learning features from imbalancedfine-grained data. In this work, we propose Bilateral-Branch Self-TrainingFramework (BiSTF), a simple yet effective framework to improve existingsemi-supervised learning methods on class-imbalanced and domain-shiftedfine-grained data. By adjusting the update frequency through stochastic epochupdate, BiSTF iteratively retrains a baseline SSL model with a labeled setexpanded by selectively adding pseudo-labeled samples from an unlabeled set,where the distribution of pseudo-labeled samples are the same as the labeleddata. We show that BiSTF outperforms the existing state-of-the-art SSLalgorithm on Semi-iNat dataset.

BiSTF: Bilateral-Branch Self-Training Framework for Semi-Supervised Large-scale Fine-Grained Recognition