There exists an apparent negative correlation between performance and interpretability of deep learning models. In an effort to reduce this negative correlation, we propose a Born Identity Network (BIN), which is a post-hoc approach for producing multi-way counterfactual maps. A counterfactual map transforms an input sample to be conditioned and classified as a target label, which is similar to how humans process knowledge through counterfactual thinking. For example, a counterfactual map can localize hypothetical abnormalities from a normal brain image that may cause it to be diagnosed with a disease. Specifically, our proposed BIN consists of two core components: Counterfactual Map Generator and Target Attribution Network. The Counterfactual Map Generator is a variation of conditional GAN which can synthesize a counterfactual map conditioned on an arbitrary target label. The Target Attribution Network provides adequate assistance for generating synthesized maps by conditioning a target label into the Counterfactual Map Generator. We have validated our proposed BIN in qualitative and quantitative analysis on MNIST, 3D Shapes, and ADNI datasets, and showed the comprehensibility and fidelity of our method from various ablation studies.
翻译:深层学习模型的性能和可解释性之间存在明显的负相关关系。 为了减少这种负相关关系,我们提议建立一个生化身份网络(BIN),这是制作多路反事实地图的后热方法。反事实地图将输入样本转换成一个要附加条件和分类的目标标签,这与人类通过反事实思维处理知识的方式相似。例如,反事实地图可以将假设异常与正常大脑图像相适应的地方化,从而可能导致诊断出疾病。具体地说,我们提议的BIN由两个核心部分组成:反事实地图生成器和目标定位网络。反事实地图生成器是有条件的GAN的变异,可以将反事实地图合成为任意的目标标签。目标定位网络为制作综合地图提供了充分协助,将目标标签调整为反事实地图生成器。我们已经在对MNIST、3D Shape和ADNI数据集的定性和定量分析中验证了我们提议的BIN,并显示我们方法在各种通货膨胀研究中的精确性和准确性。