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

Class-imbalanced datasets are known to cause the problem of model beingbiased towards the majority classes. In this project, we set up two researchquestions: 1) when is the class-imbalance problem more prevalent inself-supervised pre-training? and 2) can offline clustering of featurerepresentations help pre-training on class-imbalanced data? Our experimentsinvestigate the former question by adjusting the degree of {\itclass-imbalance} when training the baseline models, namely SimCLR and SimSiamon CIFAR-10 database. To answer the latter question, we train each expert modelon each subset of the feature clusters. We then distill the knowledge of expertmodels into a single model, so that we will be able to compare the performanceof this model to our baselines.

Offline Clustering Approach to Self-supervised Learning for Class-imbalanced Image Data