Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classiffication

Abstract

This paper addresses the task of zero-shot image classification. The key contribution of the proposed approach is to control the semantic embedding of images – one of the main ingredients of zero-shot learning – by formulating it as a metric learning problem. The optimized empirical criterion associates two types of sub-task constraints: metric… (More)
DOI: 10.1007/978-3-319-46454-1_44

Topics

4 Figures and Tables

Statistics

0204060201620172018
Citations per Year

52 Citations

Semantic Scholar estimates that this publication has 52 citations based on the available data.

See our FAQ for additional information.

Slides referencing similar topics