Transductive Multi-class and Multi-label Zero-shot Learning

Recently, zero-shot learning (ZSL) has received increasing interest. The key idea underpinning existing ZSL approaches is to exploit knowledge transfer via an intermediate-level semantic representation which is assumed to be shared between the auxiliary/source dataset and the target/test dataset and re-used as a bridge between the source and target domains for knowledge transfer. The semantic representation used in existing approaches varies from visual attributes [10,2,12,6] to semantic word vectors [3,18] and semantic relatedness [16]. However, the overall pipeline is similar: a projection function mapping low-level features to the semantic representation is learned from the auxiliary dataset by either classification or regression models and applied directly to map each instance into the same semantic representation space where a zero-shot classifier is used to recognise the unseen target class instances with a single known ‘prototype’ of each target class.