Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning
This work addresses the problem of recognizing unseen object classes without training examples, which is crucial for scalable computer vision applications, and it represents an incremental advance by refining existing zero-shot learning approaches.
The paper tackles zero-shot learning by imposing structural constraints in the semantic embedding space to predict visual exemplars, resulting in significant performance improvements over existing methods on benchmarks like ImageNet with over 20,000 unseen categories.
Leveraging class semantic descriptions and examples of known objects, zero-shot learning makes it possible to train a recognition model for an object class whose examples are not available. In this paper, we propose a novel zero-shot learning model that takes advantage of clustering structures in the semantic embedding space. The key idea is to impose the structural constraint that semantic representations must be predictive of the locations of their corresponding visual exemplars. To this end, this reduces to training multiple kernel-based regressors from semantic representation-exemplar pairs from labeled data of the seen object categories. Despite its simplicity, our approach significantly outperforms existing zero-shot learning methods on standard benchmark datasets, including the ImageNet dataset with more than 20,000 unseen categories.