Zero-Shot Learning Based on Knowledge Sharing
This work addresses classification challenges with limited training data, but it appears incremental as it builds on existing ZSL methods.
The paper tackles the problem of inadequate semantic feature representation and domain drift in Zero-Shot Learning by introducing knowledge sharing and using a generative adversarial network to generate pseudo visual features, resulting in consistent improvements on two benchmark datasets.
Zero-Shot Learning (ZSL) is an emerging research that aims to solve the classification problems with very few training data. The present works on ZSL mainly focus on the mapping of learning semantic space to visual space. It encounters many challenges that obstruct the progress of ZSL research. First, the representation of the semantic feature is inadequate to represent all features of the categories. Second, the domain drift problem still exists during the transfer from semantic space to visual space. In this paper, we introduce knowledge sharing (KS) to enrich the representation of semantic features. Based on KS, we apply a generative adversarial network to generate pseudo visual features from semantic features that are very close to the real visual features. Abundant experimental results from two benchmark datasets of ZSL show that the proposed approach has a consistent improvement.