Zero-Shot Learning via Joint Latent Similarity Embedding
This work addresses the problem of recognizing unseen classes in computer vision for researchers and practitioners, offering incremental improvements over existing methods.
The paper tackles zero-shot recognition by formulating it as a binary prediction problem to create a class-independent classifier, achieving a 4.90% improvement in accuracy over state-of-the-art methods on benchmark datasets and a 22.45% improvement in mean average precision for zero-shot retrieval.
Zero-shot recognition (ZSR) deals with the problem of predicting class labels for target domain instances based on source domain side information (e.g. attributes) of unseen classes. We formulate ZSR as a binary prediction problem. Our resulting classifier is class-independent. It takes an arbitrary pair of source and target domain instances as input and predicts whether or not they come from the same class, 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 embedding 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).