论文标题
天生的身份网络：多路反事实地图生成以解释分类器的决定
Born Identity Network: Multi-way Counterfactual Map Generation to Explain a Classifier's Decision
论文作者
论文摘要
深度学习模型的性能与可解释性之间存在明显的负相关。为了减少这种负相关性，我们提出了一个天生的身份网络（BIN），这是生成多路反事实地图的事后方法。反事实映射会转换要条件和归类为目标标签的输入样本，这与人类通过反事实思维处理知识的方式相似。例如，反事实图可以从正常的大脑形象中定位假设异常，这可能导致其被诊断出患有疾病。具体而言，我们提出的垃圾箱由两个核心组件组成：反事实地图生成器和目标归因网络。反事实映射发生器是有条件的gan的变体，可以合成在任意目标标签上的反事实映射。目标归因网络通过将目标标签调节到反事实地图生成器中，为生成合成的地图提供了足够的帮助。我们已经在对MNIST，3D形状和ADNI数据集的定性和定量分析中验证了我们提出的垃圾箱，并从各种消融研究中展示了我们方法对我们方法的可理解性和保真度。
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.
