Self-Critical Sequence Training for Image Captioning

  title={Self-Critical Sequence Training for Image Captioning},
  author={Steven J. Rennie and Etienne Marcheret and Youssef Mroueh and Jarret Ross and Vaibhava Goel},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
Recently it has been shown that policy-gradient methods for reinforcement learning can be utilized to train deep end-to-end systems directly on non-differentiable metrics for the task at hand. In this paper we consider the problem of optimizing image captioning systems using reinforcement learning, and show that by carefully optimizing our systems using the test metrics of the MSCOCO task, significant gains in performance can be realized. Our systems are built using a new optimization approach… CONTINUE READING
Highly Influential
This paper has highly influenced 38 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 234 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 102 times over the past 90 days. VIEW TWEETS


Publications citing this paper.
Showing 1-10 of 163 extracted citations

234 Citations

Citations per Year
Semantic Scholar estimates that this publication has 234 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 21 references

Similar Papers

Loading similar papers…