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

Generative Adversarial Networks (GANs) are notoriously difficult to trainespecially for complex distributions and with limited data. This has driven theneed for tools to audit trained networks in human intelligible format, forexample, to identify biases or ensure fairness. Existing GAN audit tools arerestricted to coarse-grained, model-data comparisons based on summarystatistics such as FID or recall. In this paper, we propose an alternativeapproach that compares a newly developed GAN against a prior baseline. To thisend, we introduce Cross-GAN Auditing (xGA) that, given an established"reference" GAN and a newly proposed "client" GAN, jointly identifiesintelligible attributes that are either common across both GANs, novel to theclient GAN, or missing from the client GAN. This provides both users and modeldevelopers an intuitive assessment of similarity and differences between GANs.We introduce novel metrics to evaluate attribute-based GAN auditing approachesand use these metrics to demonstrate quantitatively that xGA outperformsbaseline approaches. We also include qualitative results that illustrate thecommon, novel and missing attributes identified by xGA from GANs trained on avariety of image datasets.

Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences between Pretrained Generative Models