WSABIE: Scaling Up to Large Vocabulary Image Annotation

Jason Weston, Samy Bengio, Nicolas Usunier

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.
BibTeX
@inproceedings{weston2011wsabie,
  author = {Jason Weston and Samy Bengio and Nicolas Usunier},
  title = {{WSABIE: Scaling Up to Large Vocabulary Image Annotation}},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year = {2011},
}

Loading related content...

Figure