Transductive Zero-Shot Learning with Visual Structure Constraint

Understand

To recognize objects of the unseen classes, most existing Zero-Shot Learning(ZSL) methods first learn a compatible projection function between the common semantic space and the visual space based on the data of source seen classes, then directly apply it to the target unseen classes.

• However, in real scenarios, the data distribution between the source and target domain might not match well, thus causing the well-known \textbf{domain shift} problem.
• Based on the observation that visual features of test instances can be separated into different clusters, we propose a new visual structure constraint on class centers for transductive ZSL, to improve the generality of the projection function (i.e.
• alleviate the above domain shift problem).