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

We propose a combined generative and contrastive neural architecture forlearning latent representations of 3D volumetric shapes. The architecture usestwo encoder branches for voxel grids and multi-view images from the sameunderlying shape. The main idea is to combine a contrastive loss between theresulting latent representations with an additional reconstruction loss. Thathelps to avoid collapsing the latent representations as a trivial solution forminimizing the contrastive loss. A novel switching scheme is used tocross-train two encoders with a shared decoder. The switching scheme alsoenables the stop gradient operation on a random branch. Further classificationexperiments show that the latent representations learned with ourself-supervised method integrate more useful information from the additionalinput data implicitly, thus leading to better reconstruction and classificationperformance.

Generative-Contrastive Learning for Self-Supervised Latent Representations of 3D Shapes from Multi-Modal Euclidean Input