DeCoDEx：用于改进基于扩散的反事实解释的混杂因素检测器引导
DeCoDEx: Confounder Detector Guidance for Improved Diffusion-based Counterfactual Explanations
AI总结：
针对深度学习分类器依赖混杂因素导致偏差的问题，提出DeCoDEx框架，用预训练二分类伪影检测器引导扩散反事实图像生成，在CheXpert数据集验证有效，可提升分类器在分布外弱势群的表现。
摘要：
深度学习分类器倾向于依赖数据集中存在的主导混杂因素，而非与目标类别相关的因果标记，这会导致泛化能力差和预测存在偏差。尽管通过反事实图像生成进行可解释性已成功揭示了该问题，但在存在主导且多样的伪影时，能实现精准可解释性的偏差缓解策略仍未得到解决。在本研究中，我们提出DeCoDEx（混杂因素检测器引导的反事实解释）框架，并说明如何在推理阶段利用外部预训练的二分类伪影检测器，引导基于扩散的反事实图像生成器实现精准可解释性。我们在CheXpert数据集上开展了实验，同时使用合成伪影和真实视觉伪影（支撑装置），结果表明所提方法成功合成了反事实图像：这些图像改变了与胸腔积液相关的因果病理标记，同时保留或忽略视觉伪影。用DeCoDEx生成的图像增强ERM（经验风险最小化）和Group-DRO（组分布鲁棒优化）分类器后，在各类别分布外的代表性不足群体上的结果得到了显著提升。代码已公开在https://github.com/NimaFathi/DeCoDEx。
英文摘要：
Deep learning classifiers are prone to latching onto dominant confounders present in a dataset rather than on the causal markers associated with the target class, leading to poor generalization and biased predictions. Although explainability via counterfactual image generation has been successful at exposing the problem, bias mitigation strategies that permit accurate explainability in the presence of dominant and diverse artifacts remain unsolved. In this work, we propose the DeCoDEx framework and show how an external, pre-trained binary artifact detector can be leveraged during inference to guide a diffusion-based counterfactual image generator towards accurate explainability. Experiments on the CheXpert dataset, using both synthetic artifacts and real visual artifacts (support devices), show that the proposed method successfully synthesizes the counterfactual images that change the causal pathology markers associated with Pleural Effusion while preserving or ignoring the visual artifacts. Augmentation of ERM and Group-DRO classifiers with the DeCoDEx generated images substantially improves the results across underrepresented groups that are out of distribution for each class. The code is made publicly available at https://github.com/NimaFathi/DeCoDEx.
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。
