arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.13137cs.CVcs.AIcs.CR
收藏

通过重标签蒸馏解释深度网络的预测

Interpret the Predictions of Deep Networks via Re-Label Distillation

Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)

Yingying Hua, Shiming Ge, Daichi Zhang

AI总结:

本文提出一种基于重标签蒸馏的自监督方法,通过在 VAE 子空间生成合成图像并训练线性学生模型近似深度网络标注,直观解释黑盒网络预测的局部分类机制。

摘要:

解释黑盒深度网络的预测可以促进其部署的可靠性。在本工作中,我们提出了一种重标签蒸馏方法,以自监督的方式学习从输入到预测的直接映射。图像被投影到 VAE 子空间中,通过随机扰动其潜在向量来生成一些合成图像。然后,通过识别这些合成图像的标签是否发生改变,将它们标注为两个类别之一。此后,以深度网络标注的标签作为教师,训练一个线性学生模型,通过将这些合成图像映射到相应类别来近似这些标注。通过这种方式,这些重标签的合成图像能够很好地描述深度网络的局部分类机制,并且学习到的学生模型能够对预测提供更直观的解释。大量实验定性和定量地验证了我们方法的有效性。

英文摘要:

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.

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。

↑