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

Long-tailed (LT) classification is an unavoidable and challenging problem inthe real world. Most existing long-tailed classification methods focus only onsolving the class-wise imbalance while ignoring the attribute-wise imbalance.The deviation of a classification model is caused by both class-wise andattribute-wise imbalance. Due to the fact that attributes are implicit in mostdatasets and the combination of attributes is complex, attribute-wise imbalanceis more difficult to handle. For this purpose, we proposed a novel long-tailedclassification framework, aiming to build a multi-granularity classificationmodel by means of invariant feature learning. This method first unsupervisedlyconstructs Coarse-Grained forest (CLF) to better characterize the distributionof attributes within a class. Depending on the distribution of attributes, onecan customize suitable sampling strategies to construct different imbalanceddatasets. We then introduce multi-center loss (MCL) that aims to graduallyeliminate confusing attributes during feature learning process. The proposedframework does not necessarily couple to a specific LT classification modelstructure and can be integrated with any existing LT method as an independentcomponent. Extensive experiments show that our approach achievesstate-of-the-art performance on both existing benchmarks ImageNet-GLT andMSCOCO-GLT and can improve the performance of existing LT methods. Our codesare available on GitHub: \url{https://github.com/jinyery/cognisance}

Long-Tailed Classification Based on Coarse-Grained Leading Forest and Multi-Center Loss