English

Discriminability objective for training descriptive captions

Computer Vision and Pattern Recognition 2018-06-12 v2

Abstract

One property that remains lacking in image captions generated by contemporary methods is discriminability: being able to tell two images apart given the caption for one of them. We propose a way to improve this aspect of caption generation. By incorporating into the captioning training objective a loss component directly related to ability (by a machine) to disambiguate image/caption matches, we obtain systems that produce much more discriminative caption, according to human evaluation. Remarkably, our approach leads to improvement in other aspects of generated captions, reflected by a battery of standard scores such as BLEU, SPICE etc. Our approach is modular and can be applied to a variety of model/loss combinations commonly proposed for image captioning.

Keywords

Cite

@article{arxiv.1803.04376,
  title  = {Discriminability objective for training descriptive captions},
  author = {Ruotian Luo and Brian Price and Scott Cohen and Gregory Shakhnarovich},
  journal= {arXiv preprint arXiv:1803.04376},
  year   = {2018}
}

Comments

CVPR2018

R2 v1 2026-06-23T00:50:09.280Z