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

Random data augmentation is a critical technique to avoid overfitting intraining deep neural network models. However, data augmentation and networktraining are usually treated as two isolated processes, limiting theeffectiveness of network training. Why not jointly optimize the two? We proposeadversarial data augmentation to address this limitation. The main idea is todesign an augmentation network (generator) that competes against a targetnetwork (discriminator) by generating `hard' augmentation operations online.The augmentation network explores the weaknesses of the target network, whilethe latter learns from `hard' augmentations to achieve better performance. Wealso design a reward/penalty strategy for effective joint training. Wedemonstrate our approach on the problem of human pose estimation and carry outa comprehensive experimental analysis, showing that our method cansignificantly improve state-of-the-art models without additional data efforts.

Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation