A Distinguishable Pseudo-Feature Synthesis Method for Generalized Zero-Shot Learning

Table 1

Statistics of the four benchmark datasets.

Dataset	Number of classes			Attribute	Number of samples
	Seen	Unseen	Total		Training	Seen testing	Unseen testing	Total
AWA2	40	10	50	85	23527	5882	7913	37322
APY	20	12	32	64	5932	1483	7924	15339
CUB	150	50	200	312	7057	1764	2967	11788
SUN	645	72	717	102	10320	2580	1440	14340