A Mixture of Personalized Experts for Human Affect Estimation
Name
personalized-mixture-supervised_final_tYWcW0Y.pdf
Description
Accepted version
Size
575.44 KB
Format
Adobe PDF
Checksum (MD5)
2881baf9307a8d52ac888677eb438591
Author(s)
Feffer, Michael
Rudovic, Ognjen
Picard, Rosalind W.
Date Issued
July 2018
Journal
Lecture Notes in Computer Science
Publisher
Springer International Publishing
Citation
Feffer, Michael et al. "A Mixture of Personalized Experts for Human Affect Estimation." MLDM 2018: Machine Learning and Data Mining in Pattern Recognition, Lecture Notes in Computer Science, 10935, Springer International Publishing, 2018, 316-330. © 2018 Springer International Publishing AG
Version
Author's final manuscript
Abstract
We investigate the personalization of deep convolutional neural networks for facial expression analysis from still images. While prior work has focused on population-based (“one-size-fits-all”) approaches, we formulate and construct personalized models via a mixture of experts and supervised domain adaptation approach, showing that it improves greatly upon non-personalized models. Our experiments demonstrate the ability of the model personalization to quickly and effectively adapt to limited amounts of target data. We also provide a novel training methodology and architecture for creating personalized machine learning models for more effective analysis of emotion state.
MIT Department
Massachusetts Institute of Technology. Media Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/978-3-319-96133-0_24
