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

Unsupervised domain adaptation (UDA) aims to train a target classifier withlabeled samples from the source domain and unlabeled samples from the targetdomain. Classical UDA learning bounds show that target risk is upper bounded bythree terms: source risk, distribution discrepancy, and combined risk. Based onthe assumption that the combined risk is a small fixed value, methods based onthis bound train a target classifier by only minimizing estimators of thesource risk and the distribution discrepancy. However, the combined risk mayincrease when minimizing both estimators, which makes the target riskuncontrollable. Hence the target classifier cannot achieve ideal performance ifwe fail to control the combined risk. To control the combined risk, the keychallenge takes root in the unavailability of the labeled samples in the targetdomain. To address this key challenge, we propose a method named E-MixNet.E-MixNet employs enhanced mixup, a generic vicinal distribution, on the labeledsource samples and pseudo-labeled target samples to calculate a proxy of thecombined risk. Experiments show that the proxy can effectively curb theincrease of the combined risk when minimizing the source risk and distributiondiscrepancy. Furthermore, we show that if the proxy of the combined risk isadded into loss functions of four representative UDA methods, their performanceis also improved.

How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?