Abstract
Zero-shot recognition (ZSR) deals with the problem ofpredicting class labels for target domain instances based onsource domain side information (e.g. attributes) of unseenclasses. We formulate ZSR as a binary prediction problem.Our resulting classifier is class-independent. It takes an ar-bitrary pair of source and target domain instances as in-put and predicts whether or not they come from the sameclass, i.e. whether there is a match. We model the posterior probability of a match since it is a sufficient statistic and propose a latent probabilistic model in this context. We develop a joint discriminative learning framework based on dictionary learning to jointly learn the parameters of our model for both domains, which ultimately leads to our class-independent classifier. Many of the existing embed-ding methods can be viewed as special cases of our probabilistic model. On ZSR our method shows 4.90% improvement over the state-of-the-art in accuracy averaged across four benchmark datasets. We also adapt ZSR method for zero-shot retrieval and show 22.45% improvement accordingly in mean average precision (mAP).