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

This paper investigates methods for improving generative data augmentationfor deep learning. Generative data augmentation leverages the synthetic samplesproduced by generative models as an additional dataset for classification withsmall dataset settings. A key challenge of generative data augmentation is thatthe synthetic data contain uninformative samples that degrade accuracy. This isbecause the synthetic samples do not perfectly represent class categories inreal data and uniform sampling does not necessarily provide useful samples fortasks. In this paper, we present a novel strategy for generative dataaugmentation called meta generative regularization (MGR). To avoid thedegradation of generative data augmentation, MGR utilizes synthetic samples inthe regularization term for feature extractors instead of in the loss function,e.g., cross-entropy. These synthetic samples are dynamically determined tominimize the validation losses through meta-learning. We observed that MGR canavoid the performance degradation of na\"ive generative data augmentation andboost the baselines. Experiments on six datasets showed that MGR is effectiveparticularly when datasets are smaller and stably outperforms baselines.

Regularizing Neural Networks with Meta-Learning Generative Models