Learning the Compositional Spaces for Generalized Zero-shot Learning

Understand

This paper studies the problem of Generalized Zero-shot Learning (G-ZSL), whose goal is to classify instances belonging to both seen and unseen classes at the test time.

• We propose a novel space decomposition method to solve G-ZSL.
• Some previous models with space decomposition operations only calibrate the confident prediction of source classes (W-SVM [46]) or take target-class instances as outliers [49].
• In contrast, we propose to directly estimate and fine-tune the decision boundary between the source and the target classes.