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

Despite significant advances in deep learning, models often struggle togeneralize well to new, unseen domains, especially when training data islimited. To address this challenge, we propose a novel approach fordistribution-aware latent augmentation that leverages the relationships acrosssamples to guide the augmentation procedure. Our approach first degrades thesamples stochastically in the latent space, mapping them to augmented labels,and then restores the samples from their corrupted versions during training.This process confuses the classifier in the degradation step and restores theoverall class distribution of the original samples, promoting diverseintra-class/cross-domain variability. We extensively evaluate our approach on adiverse set of datasets and tasks, including domain generalization benchmarksand medical imaging datasets with strong domain shift, where we show ourapproach achieves significant improvements over existing methods for latentspace augmentation. We further show that our method can be flexibly adapted tolong-tail recognition tasks, demonstrating its versatility in building moregeneralizable models. Code is available athttps://github.com/nerdslab/LatentDR.

LatentDR: Improving Model Generalization Through Sample-Aware Latent Degradation and Restoration