SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning
Abstract
A reinforcement learning framework, SC-Captioner, improves image caption accuracy by refining captions through a reward function based on scene-graph parsing and set operations, outperforming direct preference optimization.
We propose SC-Captioner, a reinforcement learning framework that enables the self-correcting capability of image caption models. Our crucial technique lies in the design of the reward function to incentivize accurate caption corrections. Specifically, the predicted and reference captions are decomposed into object, attribute, and relation sets using scene-graph parsing algorithms. We calculate the set difference between sets of initial and self-corrected captions to identify added and removed elements. These elements are matched against the reference sets to calculate correctness bonuses for accurate refinements and mistake punishments for wrong additions and removals, thereby forming the final reward. For image caption quality assessment, we propose a set of metrics refined from CAPTURE that alleviate its incomplete precision evaluation and inefficient relation matching problems. Furthermore, we collect a fine-grained annotated image caption dataset, RefinedCaps, consisting of 6.5K diverse images from COCO dataset. Experiments show that applying SC-Captioner on large visual-language models can generate better image captions across various scenarios, significantly outperforming the direct preference optimization training strategy.
Models citing this paper 0
No model linking this paper
Datasets citing this paper 1
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper