论文标题
循环一致的反事实通过潜在转化
Cycle-Consistent Counterfactuals by Latent Transformations
论文作者
论文摘要
反事实（CF）的视觉解释试图找到类似于将视觉系统决定更改为指定结果的查询图像的图像。现有方法要么需要推理时间优化，也需要具有生成对抗模型的联合培训，这使它们既耗时又难以在实践中使用。我们提出了一种通过潜在转化（C3LT）的新方法，循环矛盾的反事实，该方法学习了一种潜在转化，该转化会通过在生成模型的潜在空间中转向自动生成视觉CFS。我们的方法使用查询和CF潜在表示之间的周期一致性，这有助于我们的培训找到更好的解决方案。 C3LT可以轻松地插入任何最先进的生成网络中。这使我们的方法能够以高分辨率（例如Imagenet中的图像）生成高质量和可解释的CF图像。除了评估CF解释的几个既定指标外，我们还引入了一种量身定制的新型指标，以评估生成的CF示例的质量，并验证我们在大量实验集中我们方法的有效性。
CounterFactual (CF) visual explanations try to find images similar to the query image that change the decision of a vision system to a specified outcome. Existing methods either require inference-time optimization or joint training with a generative adversarial model which makes them time-consuming and difficult to use in practice. We propose a novel approach, Cycle-Consistent Counterfactuals by Latent Transformations (C3LT), which learns a latent transformation that automatically generates visual CFs by steering in the latent space of generative models. Our method uses cycle consistency between the query and CF latent representations which helps our training to find better solutions. C3LT can be easily plugged into any state-of-the-art pretrained generative network. This enables our method to generate high-quality and interpretable CF images at high resolution such as those in ImageNet. In addition to several established metrics for evaluating CF explanations, we introduce a novel metric tailored to assess the quality of the generated CF examples and validate the effectiveness of our method on an extensive set of experiments.
