2000 character limit reached
A Better Variant of Self-Critical Sequence Training (2003.09971v2)
Published 22 Mar 2020 in cs.CV and cs.CL
Abstract: In this work, we present a simple yet better variant of Self-Critical Sequence Training. We make a simple change in the choice of baseline function in REINFORCE algorithm. The new baseline can bring better performance with no extra cost, compared to the greedy decoding baseline.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.