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/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

It is widely known that very small datasets produce overfitting in DeepNeural Networks (DNNs), i.e., the network becomes highly biased to the data ithas been trained on. This issue is often alleviated using transfer learning,regularization techniques and/or data augmentation. This work presents a newapproach, independent but complementary to the previous mentioned techniques,for improving the generalization of DNNs on very small datasets in which theinvolved classes share many visual features. The proposed methodology, calledFuCiTNet (Fusion Class inherent Transformations Network), inspired by GANs,creates as many generators as classes in the problem. Each generator, $k$,learns the transformations that bring the input image into the k-class domain.We introduce a classification loss in the generators to drive the leaning ofspecific k-class transformations. Our experiments demonstrate that the proposedtransformations improve the generalization of the classification model in threediverse datasets.

FuCiTNet: Improving the generalization of deep learning networks by the fusion of learned class-inherent transformations