Unsupervised Domain Adaptation for Facial Expression Recognition Using Generative Adversarial Networks

Table 5

Comparison with two other methods using GAN generated images, FER-2013JAFFE.

Method	Recognition Accuracy on Target Dataset
	Alexnet	VGG11
Baseline	50.70%	44.60%
Pseudo-label	51.17%	42.72%
LSRO	53.99%	57.75%
DPL	54.46%	59.62%