arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.07972cs.CV
收藏

图像空间中的稀疏视觉反事实描述

Sparse Visual Counterfactual Explanations in Image Space

University of Tübingen(图宾根大学)

Valentyn Boreiko, Maximilian Augustin, Francesco Croce, Philipp Berens, Matthias Hein

摘要:

图像空间中的视觉反事实解释(VCE)是理解图像分类器决策的重要工具,因为它们显示了在图像的哪些变化下分类器的决策会改变。它们在图像空间中的生成具有挑战性,并且由于对抗性示例的问题而需要鲁棒的模型。在图像空间中生成VCE的现有技术遭受背景中的虚假变化。我们的新的扰动模型的VCE连同其有效的优化,通过我们的新的自动弗兰克-沃尔夫计划产生稀疏的VCE,导致特定的目标类的细微变化。此外,我们还证明了VCE可以用于检测ImageNet分类器由于ImageNet数据集中的虚假特征而产生的不期望行为。

英文摘要:

Visual counterfactual explanations (VCEs) in image space are an important tool to understand decisions of image classifiers as they show under which changes of the image the decision of the classifier would change. Their generation in image space is challenging and requires robust models due to the problem of adversarial examples. Existing techniques to generate VCEs in image space suffer from spurious changes in the background. Our novel perturbation model for VCEs together with its efficient optimization via our novel Auto-Frank-Wolfe scheme yields sparse VCEs which lead to subtle changes specific for the target class. Moreover, we show that VCEs can be used to detect undesired behavior of ImageNet classifiers due to spurious features in the ImageNet dataset.

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。

↑