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

Real-world data often follows a long-tailed distribution, which makes theperformance of existing classification algorithms degrade heavily. A key issueis that samples in tail categories fail to depict their intra-class diversity.Humans can imagine a sample in new poses, scenes, and view angles with theirprior knowledge even if it is the first time to see this category. Inspired bythis, we propose a novel reasoning-based implicit semantic data augmentationmethod to borrow transformation directions from other classes. Since thecovariance matrix of each category represents the feature transformationdirections, we can sample new directions from similar categories to generatedefinitely different instances. Specifically, the long-tailed distributed datais first adopted to train a backbone and a classifier. Then, a covariancematrix for each category is estimated, and a knowledge graph is constructed tostore the relations of any two categories. Finally, tail samples are adaptivelyenhanced via propagating information from all the similar categories in theknowledge graph. Experimental results on CIFAR-100-LT, ImageNet-LT, andiNaturalist 2018 have demonstrated the effectiveness of our proposed methodcompared with the state-of-the-art methods.

Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification