Journal
MACHINE LEARNING
Volume 81, Issue 1, Pages 21-35Publisher
SPRINGER
DOI: 10.1007/s10994-010-5198-3
Keywords
Large scale; Image annotation; Learning to rank; Embedding
Categories
Ask authors/readers for more resources
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 k 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 both outperforms several baseline methods and, in comparison to them, is faster and consumes less memory. We also demonstrate how our method learns an interpretable model, where annotations with alternate spellings or even languages are close in the embedding space. Hence, even when our model does not predict the exact annotation given by a human labeler, it often predicts similar annotations, a fact that we try to quantify by measuring the newly introduced sibling precision metric, where our method also obtains excellent results.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available