评测大模型的色觉能力，发现其在颜色识别上的不足并提出改进方法。
Assessing Color Vision Test in Large Vision-language Models
- 构建多类别、多难度的颜色视觉测试数据集
- 分析大模型在颜色任务中的错误类型
- 通过微调提升模型颜色识别能力，适合视觉-语言研究者
随着大型视觉-语言模型的广泛应用，其色觉能力至关重要。然而，这些模型的色觉表现尚未得到充分探索。为填补这一空白，我们定义了一项针对大型视觉-语言模型的颜色视觉测试任务，并构建了一个涵盖多种题型和难度级别的数据集。此外，我们分析了大型视觉-语言模型在颜色任务中的错误类型，并提出了针对性的微调策略，以提升其在颜色视觉测试中的表现。
原文摘要 · Abstract (English)
With the widespread adoption of large vision-language models, the capacity for color vision in these models is crucial. However, the color vision abilities of large visual-language models have not yet been thoroughly explored. To address this gap, we define a color vision testing task for large vision-language models and construct a dataset \footnote{Anonymous Github Showing some of the data https://anonymous.4open.science/r/color-vision-test-dataset-3BCD} that covers multiple categories of test questions and tasks of varying difficulty levels. Furthermore, we analyze the types of errors made by large vision-language models and propose fine-tuning strategies to enhance their performance in color vision tests.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。