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 locality-aware method for interpreting the latent space ofwavelet-based Generative Adversarial Networks (GANs), that can well capture thelarge spatial and spectral variability that is characteristic to satelliteimagery. By focusing on preserving locality, the proposed method is able todecompose the weight-space of pre-trained GANs and recover interpretabledirections that correspond to high-level semantic concepts (such asurbanization, structure density, flora presence) - that can subsequently beused for guided synthesis of satellite imagery. In contrast to typically usedapproaches that focus on capturing the variability of the weight-space in areduced dimensionality space (i.e., based on Principal Component Analysis,PCA), we show that preserving locality leads to vectors with different angles,that are more robust to artifacts and can better preserve class information.Via a set of quantitative and qualitative examples, we further show that theproposed approach can outperform both baseline geometric augmentations, as wellas global, PCA-based approaches for data synthesis in the context of dataaugmentation for satellite scene classification.

Locality-preserving Directions for Interpreting the Latent Space of Satellite Image GANs