Due to the dramatic expanse of data cat-egories and the lack of labeled instances, zero-shot learning, which transfers knowledge from observed classes to recognize unseen classes, has started drawing a lot of attention from the research community. In this paper, we propose a semi-supervised max-margin learning framework that integrates the semi-supervised classification problem over ob-served classes and the unsupervised cluster-ing problem over unseen classes together to tackle zero-shot multi-class classification. By further integrating label embedding into this framework, we produce a dual formulation that permits convenient incorporation of aux-iliary label semantic knowledge to improve zero-shot learning. We conduct extensive ex-periments on three standard image data sets to evaluate the proposed approach by com-paring to two state-of-the-art methods. Our results demonstrate the efficacy of the pro-posed framework.

Journal of Machine Learning Research
School of Computer Science

Li, X. (Xin), & Guo, Y. (2015). Max-margin zero-shot learning for multi-class classification. In Journal of Machine Learning Research (Vol. 38, pp. 626–634).