arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.03786cs.CV
收藏

提升计算机视觉可解释性:面向复杂场景的透明两级分类

Improving Computer Vision Interpretability: Transparent Two-level Classification for Complex Scenes

University of Konstanz(康斯坦茨大学);University of California, Los Angeles(加利福尼亚大学洛杉矶分校)

Stefan Scholz, Nils B. Weidmann, Zachary C. Steinert-Threlkeld, Eda Keremoğlu, Bastian Goldlücke

AI总结:

针对图像分类器缺乏可解释性的问题,本文提出分割检测物体并构建特征向量的两级分类方法,在14万余张政治抗议图像上验证其透明性、特征区分与跨国比较价值。

摘要:

将图像作为数据处理在政治学中已变得日益流行。尽管现有图像分类器达到了很高的准确率,但很难系统地评估它们进行分类所依据的视觉特征。本文提出一种解决这一透明度问题的两级分类方法。在第一阶段,图像分割器检测图像中存在的物体,并根据这些物体创建特征向量。在第二阶段,该特征向量被用作标准机器学习分类器的输入,以区分不同图像。我们将该方法应用于一个包含超过140000张图像的新数据集,以检测哪些图像展示了政治抗议。该分析证明了本文方法的三个优势。第一,识别图像中的物体通过为图像所示物体提供人类可理解的标签来提高透明度。第二,了解这些物体使得分析哪些物体能够区分抗议图像与非抗议图像成为可能。第三,比较不同国家中物体的重要性揭示了抗议行为如何变化。这些洞察无法通过传统计算机视觉分类器获得,并为比较研究提供了新的机会。

英文摘要:

Treating images as data has become increasingly popular in political science. While existing classifiers for images reach high levels of accuracy, it is difficult to systematically assess the visual features on which they base their classification. This paper presents a two-level classification method that addresses this transparency problem. At the first stage, an image segmenter detects the objects present in the image and a feature vector is created from those objects. In the second stage, this feature vector is used as input for standard machine learning classifiers to discriminate between images. We apply this method to a new dataset of more than 140,000 images to detect which ones display political protest. This analysis demonstrates three advantages to this paper's approach. First, identifying objects in images improves transparency by providing human-understandable labels for the objects shown on an image. Second, knowing these objects enables analysis of which distinguish protest images from non-protest ones. Third, comparing the importance of objects across countries reveals how protest behavior varies. These insights are not available using conventional computer vision classifiers and provide new opportunities for comparative research.

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。

↑