arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.09094cs.CV
收藏

STEEX:用语义引导反事实推理

STEEX: Steering Counterfactual Explanations with Semantics

Sorbonne University(索邦大学)

Paul Jacob, Éloi Zablocki, Hédi Ben-Younes, Mickaël Chen, Patrick Pérez, Matthieu Cord

摘要:

随着深度学习模型越来越多地用于安全关键型应用,可解释性和可信度成为主要问题。对于简单的图像,例如低分辨率的人脸肖像,最近提出了合成视觉反事实解释的方法来揭示训练分类模型的决策机制。在这项工作中,我们解决了高质量的图像和复杂的场景产生反事实的解释的问题。利用最近的语义到图像模型,我们提出了一个新的生成反事实的解释框架,产生合理的和稀疏的修改,保持整体场景结构。此外,我们引入了“区域为目标的反事实解释”的概念,和相应的框架,用户可以通过指定一组语义区域的查询图像的解释必须是关于指导反事实的生成。在具有挑战性的数据集上进行了广泛的实验,包括高质量的肖像(CelebAMask-HQ)和驾驶场景(BDD 100 k)。代码可在https://github.com/valeoai/STEEX上获得

英文摘要:

As deep learning models are increasingly used in safety-critical applications, explainability and trustworthiness become major concerns. For simple images, such as low-resolution face portraits, synthesizing visual counterfactual explanations has recently been proposed as a way to uncover the decision mechanisms of a trained classification model. In this work, we address the problem of producing counterfactual explanations for high-quality images and complex scenes. Leveraging recent semantic-to-image models, we propose a new generative counterfactual explanation framework that produces plausible and sparse modifications which preserve the overall scene structure. Furthermore, we introduce the concept of "region-targeted counterfactual explanations", and a corresponding framework, where users can guide the generation of counterfactuals by specifying a set of semantic regions of the query image the explanation must be about. Extensive experiments are conducted on challenging datasets including high-quality portraits (CelebAMask-HQ) and driving scenes (BDD100k). Code is available at https://github.com/valeoai/STEEX

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。

↑