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

Imbalanced datasets widely exist in practice and area great challenge fortraining deep neural models with agood generalization on infrequent classes. Inthis work, wepropose a new rare-class sample generator (RSG) to solvethisproblem. RSG aims to generate some new samplesfor rare classes during training,and it has in particularthe following advantages: (1) it is convenient to useandhighly versatile, because it can be easily integrated intoany kind ofconvolutional neural network, and it works wellwhen combined with differentloss functions, and (2) it isonly used during the training phase, andtherefore, no ad-ditional burden is imposed on deep neural networks duringthetesting phase. In extensive experimental evaluations, weverify theeffectiveness of RSG. Furthermore, by leveragingRSG, we obtain competitiveresults on Imbalanced CIFARand new state-of-the-art results on Places-LT,ImageNet-LT, and iNaturalist 2018. The source code is available athttps://github.com/Jianf-Wang/RSG.

RSG: A Simple but Effective Module for Learning Imbalanced Datasets