Unsupervised Domain Adaptation for Facial Expression Recognition Using Generative Adversarial Networks

Table 2

Comparison with other published methods.

Method	Source Dataset	Target Dataset	Recognition Accuracy on The Target Dataset
Meguid et al. [13]	Bu-3DFE	JAFFE	41.96%
Wen et al. [14]	FER2013	JAFFE	50.70%
Gu et al. [15]	CK	JAFFE	55.87%
Zhu et al. [16]	FEED	JAFFE	61.97%
Our Method	CK+	JAFFE	51.64%
Our Method	FER2013	JAFFE	59.62%
Mayer et al. [17]	CK	MMI	60.30%
Mayer et al. [17]	FEED	MMI	58.90%
Our Method	FER2013	MMI	61.86%
Gu et al. [15]	JAFFE	CK+	54.05%
Mayer et al. [17]	FEED	CK+	56.60%
Wen et al. [14]	FER2013	CK+	76.05%
Our Method	JAFFE	CK+	65.01%
Our Method	FER2013	CK+	76.58%