Global ETD Search

Domain Adaptation with a Classifier Trained by Robust Pseudo-Labels

Zhou, YunkeVirginia Tech2022

… strategy (EMA) is used to ensure we can form robust source and target centroids. A Gaussian-uniform mixture model is trained using an Expectation-Maximization (EM) algorithm to infer the robustness of the target pseudo-labels. With the help of target pseudo-labels, I propose two novel types of …

vt Repository record for Domain Adaptation with a Classifier Trained by Robust Pseudo-Labels (opens in a new tab)