一种利用视觉-语言模型自动化解释视觉模型的新型框架
A Novel Framework for Automated Explain Vision Model Using Vision-Language Models
AI总结：
本文提出基于Vision-Language Models的样本级与数据集级视觉模型解释流水线，以低成本发现失败案例并揭示模型整体行为模式。
摘要：
许多视觉模型的开发主要侧重于利用准确率、IoU和mAP等指标提升其性能，而由于应用xAI方法对训练后的模型提供有意义的解释具有复杂性，可解释性受到的关注较少。尽管许多现有xAI方法旨在逐样本解释视觉模型，但解释视觉模型一般行为的方法仍未得到充分探索，而这种一般行为只有在大型数据集上运行后才能被捕捉到。此外，理解视觉模型在一般图像上的行为，对于防止带有偏见的判断并帮助识别模型的趋势和模式可能非常重要。借助Vision-Language Models（视觉-语言模型）的应用，本文提出了一条在样本级和数据集级解释视觉模型的流水线。所提出的流水线可用于发现失败案例，并以最少的工作量获得对视觉模型的洞察，从而将视觉模型开发与xAI分析相结合，推进图像分析。
英文摘要：
The development of many vision models mainly focuses on improving their performance using metrics such as accuracy, IoU, and mAP, with less attention to explainability due to the complexity of applying xAI methods to provide a meaningful explanation of trained models. Although many existing xAI methods aim to explain vision models sample-by-sample, methods explaining the general behavior of vision models, which can only be captured after running on a large dataset, are still underexplored. Furthermore, understanding the behavior of vision models on general images can be very important to prevent biased judgments and help identify the model's trends and patterns. With the application of Vision-Language Models, this paper proposes a pipeline to explain vision models at both the sample and dataset levels. The proposed pipeline can be used to discover failure cases and gain insights into vision models with minimal effort, thereby integrating vision model development with xAI analysis to advance image analysis.
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。
