F

~

s

+

u

ilde{F}_{s+u}

F~s+u? represents the result of two-layer network activation

extracted classifier weights for seen-class (denoted with W

i

_i

i?)

CNN is used to extract the visual representations for seen-classes, denoted as F

C

s

_{C_s}

Cs??.generative adversarial network (GDAN)，visual representations of all classes F

s

+

u

_{s+u}

s+u?

额外信息

作者未提供代码