---
title: "WSABIE: Scaling Up to Large Vocabulary Image Annotation"
authors:
  - "Jason Weston"
  - "Samy Bengio"
  - "Nicolas Usunier"
doi: "10.5591/978-1-57735-516-8/IJCAI11-460"
url: "https://ijcai.org/proceedings/2011/460"
pdf: "https://ijcai.org/proceedings/2011/0460.pdf"
venue: "Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence"
year: 2011
pages: "2764-2769"
track: ""
keywords:
---

# WSABIE: Scaling Up to Large Vocabulary Image Annotation

Jason Weston, Samy Bengio, Nicolas Usunier

*Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence*, pages 2764-2769. DOI: [10.5591/978-1-57735-516-8/IJCAI11-460](https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-460)

## Abstract

Image annotation datasets are becoming larger and larger, with tens of millions of images and tens of thousands of possible annotations. We propose a strongly performing method that scales to such datasets by simultaneously learning to optimize precision at the top of the ranked list of annotations for a given image and learning a low-dimensional joint embedding space for both images and annotations. Our method, called Wsabie, both outperforms several baseline methods and is faster and consumes less memory.