# Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning Source: [Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning]() Collection index: [llms.txt]() Data updated: 2025-10-27T05:52:51.558Z Authors: Soravit Changpinyo, Wei-Lun Chao, Fei Sha Published: 2016-05-26T05:50:09.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()