Not logged in.

Quick Search - Contribution

Contribution Details

Type Master's Thesis
Scope Discipline-based scholarship
Title Improved Facial Attribute Classification through Selective Test Data Augmentation
Organization Unit
Authors
  • Yuang Cheng
Supervisors
  • Manuel Günther
Language
  • English
Institution University of Zurich
Faculty Faculty of Business, Economics and Informatics
Date 2021
Abstract Text Applying data augmentation on test images can improve facial attribute classifications. The Alignment-Free Facial Attribute Classification Technique (AFFAT) shows that performing 162 transformations on test images can improve the prediction of facial attributes on the CelebA dataset. However, this process costs a substantial amount of time, and the effectiveness of each transformation is not considered. This research aims to find the best combination of transformations that will be applied as test-time data augmentation, such that the prediction results of the AFFACT model can be improved. Genetic algorithms are employed for the optimization task. As a result, even though the overall prediction accuracy does not improve, the number of transformations applied as test-time data augmentation has been decreased dramatically.
PDF File Download
Export BibTeX