通过重标注生成合成图像，解释深度网络的分类逻辑。
Interpret the Predictions of Deep Networks via Re-Label Distillation
- 用VAE潜空间扰动生成合成图像，自动标注标签变化。
- 训练线性模型拟合网络对合成图像的预测，揭示局部决策机制。
- 无需人工标注，适合想理解黑箱模型的开发者使用。
解释黑箱深度网络的预测结果有助于提升其部署可靠性。本文提出一种重标注蒸馏方法，在自监督框架下学习从输入到预测的直接映射。将图像投影至VAE子空间，通过随机扰动其潜向量生成合成图像，并根据标签是否变化判断其类别。利用深度网络对这些合成图像的预测作为教师标签，训练一个线性学生模型，将其映射到对应类别。该方法能有效描述深度网络的局部分类机制，所学学生模型可提供更直观的预测解释。大量实验验证了该方法在定性和定量层面的有效性。
原文摘要 · Abstract (English)
Interpreting the predictions of a black-box deep network can facilitate the reliability of its deployment. In this work, we propose a re-label distillation approach to learn a direct map from the input to the prediction in a self-supervision manner. The image is projected into a VAE subspace to generate some synthetic images by randomly perturbing its latent vector. Then, these synthetic images can be annotated into one of two classes by identifying whether their labels shift. After that, using the labels annotated by the deep network as teacher, a linear student model is trained to approximate the annotations by mapping these synthetic images to the classes. In this manner, these re-labeled synthetic images can well describe the local classification mechanism of the deep network, and the learned student can provide a more intuitive explanation towards the predictions. Extensive experiments verify the effectiveness of our approach qualitatively and quantitatively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。