视觉-语言模型的不确定性感知评估
Uncertainty-Aware Evaluation for Vision-Language Models
AI总结：
本文提出将不确定性量化纳入视觉-语言模型评估的基准，通过在 20 多个 VLM 和 5 个 VQA 数据集上使用共形预测，发现模型准确率与不确定性并不一致，且不确定性与其语言模型部分相关。
摘要：
GPT-4、LLaVA 和 CogVLM 等视觉-语言模型（VLM）近期因在多项视觉-语言任务中表现出色而迅速流行。然而，当前的评估方法忽视了一个关键要素：不确定性，而这对全面评估 VLM 至关重要。针对这一疏漏，我们提出了一个将不确定性量化纳入 VLM 评估的基准。我们的分析涵盖 20 多个 VLM，重点关注多项选择视觉问答（VQA）任务。我们在 5 个数据集上考察模型，以评估其不同的视觉-语言能力。使用共形预测作为不确定性估计方法，我们证明模型的不确定性与其准确率并不一致。具体而言，我们表明准确率最高的模型也可能具有最高的不确定性，这证实了为 VLM 测量不确定性的重要性。我们的实证发现还揭示了模型不确定性与其语言模型部分之间的相关性。
英文摘要：
Vision-Language Models like GPT-4, LLaVA, and CogVLM have surged in popularity recently due to their impressive performance in several vision-language tasks. Current evaluation methods, however, overlook an essential component: uncertainty, which is crucial for a comprehensive assessment of VLMs. Addressing this oversight, we present a benchmark incorporating uncertainty quantification into evaluating VLMs. Our analysis spans 20+ VLMs, focusing on the multiple-choice Visual Question Answering (VQA) task. We examine models on 5 datasets that evaluate various vision-language capabilities. Using conformal prediction as an uncertainty estimation approach, we demonstrate that the models' uncertainty is not aligned with their accuracy. Specifically, we show that models with the highest accuracy may also have the highest uncertainty, which confirms the importance of measuring it for VLMs. Our empirical findings also reveal a correlation between model uncertainty and its language model part.
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。
