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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Despite significant improvements on the image generation performance ofGenerative Adversarial Networks (GANs), generations with low visual fidelitystill have been observed. As widely used metrics for GANs focus more on theoverall performance of the model, evaluation on the quality of individualgenerations or detection of defective generations is challenging. While recentstudies try to detect featuremap units that cause artifacts and evaluateindividual samples, these approaches require additional resources such asexternal networks or a number of training data to approximate the real datamanifold. In this work, we propose the concept of local activation, and devisea metric on the local activation to detect artifact generations withoutadditional supervision. We empirically verify that our approach can detect andcorrect artifact generations from GANs with various datasets. Finally, wediscuss a geometrical analysis to partially reveal the relation between theproposed concept and low visual fidelity.

An Unsupervised Way to Understand Artifact Generating Internal Units in Generative Neural Networks