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 study the problem of learning conditional generators from noisy labeledsamples, where the labels are corrupted by random noise. A standard training ofconditional GANs will not only produce samples with wrong labels, but alsogenerate poor quality samples. We consider two scenarios, depending on whetherthe noise model is known or not. When the distribution of the noise is known,we introduce a novel architecture which we call Robust Conditional GAN (RCGAN).The main idea is to corrupt the label of the generated sample before feeding tothe adversarial discriminator, forcing the generator to produce samples withclean labels. This approach of passing through a matching noisy channel isjustified by corresponding multiplicative approximation bounds between the lossof the RCGAN and the distance between the clean real distribution and thegenerator distribution. This shows that the proposed approach is robust, whenused with a carefully chosen discriminator architecture, known as projectiondiscriminator. When the distribution of the noise is not known, we provide anextension of our architecture, which we call RCGAN-U, that learns the noisemodel simultaneously while training the generator. We show experimentally onMNIST and CIFAR-10 datasets that both the approaches consistently improve uponbaseline approaches, and RCGAN-U closely matches the performance of RCGAN.

Robustness of Conditional GANs to Noisy Labels