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 present a simple neural rendering architecture that helps variationalautoencoders (VAEs) learn disentangled representations. Instead of thedeconvolutional network typically used in the decoder of VAEs, we tile(broadcast) the latent vector across space, concatenate fixed X- andY-"coordinate" channels, and apply a fully convolutional network with 1x1stride. This provides an architectural prior for dissociating positional fromnon-positional features in the latent distribution of VAEs, yet withoutproviding any explicit supervision to this effect. We show that thisarchitecture, which we term the Spatial Broadcast decoder, improvesdisentangling, reconstruction accuracy, and generalization to held-out regionsin data space. It provides a particularly dramatic benefit when applied todatasets with small objects. We also emphasize a method for visualizing learnedlatent spaces that helped us diagnose our models and may prove useful forothers aiming to assess data representations. Finally, we show the SpatialBroadcast Decoder is complementary to state-of-the-art (SOTA) disentanglingtechniques and when incorporated improves their performance.

Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs