Zero-Shot Learning via Semantic Similarity Embedding

TL;DR

This paper introduces a zero-shot learning approach that maps source and target data into a shared semantic space using learned embeddings, enabling accurate classification of unseen classes based on semantic similarity.

Contribution

It proposes a novel max-margin framework for learning source and target embeddings that measure semantic similarity, improving zero-shot recognition accuracy.

Findings

Significant accuracy improvements on benchmark datasets.

Effective semantic space mapping for unseen classes.

Robust similarity measurement via max-margin learning.

Abstract

In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided. The goal during test-time is to accurately predict the class label of an unseen target domain instance based on revealed source domain side information (\eg attributes) for unseen classes. Our method is based on viewing each source or target data as a mixture of seen class proportions and we postulate that the mixture patterns have to be similar if the two instances belong to the same unseen class. This perspective leads us to learning source/target embedding functions that map an arbitrary source/target domain data into a same semantic space where similarity can be readily measured. We develop a max-margin framework to learn these similarity functions and jointly optimize parameters by means of cross validation. Our test results are compelling, leading to significant improvement in terms of accuracy on most benchmark datasets for zero-shot recognition.