CCCaption：面向完整与正确图像描述的双奖励强化学习
CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning
提出基于双奖励强化学习的图像描述训练框架，利用多个LVLM分解视觉查询来评估完整性和正确性，可复用于其他视觉语言生成任务的奖励设计。
原文依据 we introduce CCCaption: a dual-reward reinforcement learning framework with a dedicated fine-tuning corpus that explicitly optimizes these properties
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论图像描述仍然是视觉语言理解的基础任务，然而真实监督仍然主要依赖于人工标注的参考描述。由于人工标注反映主观偏好和专业知识，真实描述往往不完整甚至不正确，这反过来限制了描述模型。我们认为描述质量应该通过两个客观方面来评估：完整性（描述是否覆盖所有显著视觉事实？）和正确性（描述相对于图像是否真实？）。为此，我们引入了CCCaption：一个双奖励强化学习框架，配备专门的微调语料库，显式优化这些属性以生成完整且正确的描述。对于完整性，我们使用多样化的LVLM将图像分解为一组视觉查询，并奖励回答更多这些查询的描述，同时采用动态查询采样策略以提高训练效率。对于正确性，我们通过验证从描述分解中得到的子描述查询的真实性来惩罚包含幻觉的描述。我们的对称双奖励优化联合最大化完整性和正确性，引导模型生成更好地满足这些客观标准的描述。在标准描述基准上的大量实验显示出一致的改进，为训练超越人类标注模仿的描述模型提供了一条原则性路径。
英文原文摘要 1481 字符
Image captioning remains a fundamental task for vision-language understanding, yet ground-truth supervision still relies predominantly on human-annotated references.Because human annotations reflect subjective preferences and expertise, ground-truth captions are often incomplete or even incorrect, which in turn limits caption models.We argue that caption quality should be assessed by two objective aspects: completeness (does the caption cover all salient visual facts?) and correctness (are the descriptions true with respect to the image?).To this end, we introduce CCCaption: a dual-reward reinforcement learning framework with a dedicated fine-tuning corpus that explicitly optimizes these properties to generate Complete and Correct Captions.For completeness, we use diverse LVLMs to disentangle the image into a set of visual queries, and reward captions that answer more of these queries, with a dynamic query sampling strategy to improve training efficiency.For correctness, we penalize captions that contain hallucinations by validating the authenticity of sub-caption queries, which are derived from the caption decomposition.Our symmetric dual-reward optimization jointly maximizes completeness and correctness, guiding models toward captions that better satisfy these objective criteria. Extensive experiments across standard captioning benchmarks show consistent improvements, offering a principled path to training caption models beyond human-annotation imitation.