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

The Variational Autoencoder (VAE) is known to suffer from the phenomenon of\textit{posterior collapse}, where the latent representations generated by themodel become independent of the inputs. This leads to degeneratedrepresentations of the input, which is attributed to the limitations of theVAE's objective function. In this work, we propose a novel solution to thisissue, the Contrastive Regularization for Variational Autoencoders (CR-VAE).The core of our approach is to augment the original VAE with a contrastiveobjective that maximizes the mutual information between the representations ofsimilar visual inputs. This strategy ensures that the information flow betweenthe input and its latent representation is maximized, effectively avoidingposterior collapse. We evaluate our method on a series of visual datasets anddemonstrate, that CR-VAE outperforms state-of-the-art approaches in preventingposterior collapse.

CR-VAE: Contrastive Regularization on Variational Autoencoders for Preventing Posterior Collapse