FLEUR：一种基于大型多模态模型的可解释无参考图像描述评价指标
FLEUR: An Explainable Reference-Free Evaluation Metric for Image Captioning Using a Large Multimodal Model
AI总结：
本文提出FLEUR，一种基于大型多模态模型的可解释无参考图像描述评价指标，无需参考描述即可评分并给出解释，在多个基准上达到最先进水平。
摘要：
现有的大多数图像描述评价指标侧重于通过将描述与参考描述进行比较来为其分配单一数值分数。然而，这些方法并不为所分配的分数提供解释。此外，参考描述的获取成本很高。在本文中，我们提出FLEUR，一种可解释的无参考指标，旨在将可解释性引入图像描述评价指标。通过利用大型多模态模型，FLEUR能够直接根据图像评价描述，而无需参考描述，并为所分配的分数提供解释。我们引入分数平滑技术，以尽可能与人类判断保持一致，并对用户定义的评分标准具有鲁棒性。FLEUR在多个图像描述评价基准上与人类判断取得了高相关性，并在无参考评价指标领域内在Flickr8k-CF、COMPOSITE和Pascal-50S上达到了最先进的结果。我们的源代码和结果已公开，地址为：https://github.com/Yebin46/FLEUR。
英文摘要：
Most existing image captioning evaluation metrics focus on assigning a single numerical score to a caption by comparing it with reference captions. However, these methods do not provide an explanation for the assigned score. Moreover, reference captions are expensive to acquire. In this paper, we propose FLEUR, an explainable reference-free metric to introduce explainability into image captioning evaluation metrics. By leveraging a large multimodal model, FLEUR can evaluate the caption against the image without the need for reference captions, and provide the explanation for the assigned score. We introduce score smoothing to align as closely as possible with human judgment and to be robust to user-defined grading criteria. FLEUR achieves high correlations with human judgment across various image captioning evaluation benchmarks and reaches state-of-the-art results on Flickr8k-CF, COMPOSITE, and Pascal-50S within the domain of reference-free evaluation metrics. Our source code and results are publicly available at: https://github.com/Yebin46/FLEUR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
