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

We propose an approach for unsupervised domain adaptation for the task ofestimating someone's age from a given face image. In order to avoid thepropagation of racial bias in most publicly available face image datasets intothe inefficacy of models trained on them, we perform domain adaptation tomotivate the predictor to learn features that are invariant to ethnicity,enhancing the generalization performance across faces of people from differentethnic backgrounds. Exploiting the ordinality of age, we also impose rankingconstraints on the prediction of the model and design our model such that ittakes as input a pair of images, and outputs both the relative age differenceand the rank of the first identity with respect to the other in terms of theirages. Furthermore, we implement Multi-Dimensional Scaling to retrieve absoluteages from the predicted age differences from as few as two labeled images fromthe domain to be adapted to. We experiment with a publicly available datasetwith age labels, dividing it into subsets based on the ethnicity labels, andevaluating the performance of our approach on the data from an ethnicitydifferent from the one that the model is trained on. Additionally, we impose aconstraint to preserve the sanity of the predictions with respect to relativeand absolute ages, and another to ensure the smoothness of the predictions withrespect to the input. We experiment extensively and compare various domainadaptation approaches for the task of regression.

Reducing Racial Bias in Facial Age Prediction using Unsupervised Domain Adaptation in Regression