Using Gaussian Processes to Improve Zero-Shot Learning with Relative Attributes

Abstract

Relative attributes can serve as a very useful method for zero-shot learning of images. This was shown by the work of Parikh and Grauman [1] where an image is expressed in terms of attributes that are relatively specified between different class pairs. However, for zero-shot learning the authors had assumed a simple Gaussian Mixture Model (GMM) that used the GMM based clustering to obtain the label for an unknown target test example. In this paper, we contribute a principled approach that uses Gaussian Process based classification to obtain the posterior probability for each sample of an unknown target class, in terms of Gaussian process classification and regression for nearest sample images. We analyse different variants of this approach and show that such a principled approach yields improved performance and a better understanding in terms of probabilistic estimates. The method is evaluated on standard Pubfig and Shoes with Attributes benchmarks.