论文标题
HUDD：调试DNN的工具进行安全分析
HUDD: A tool to debug DNNs for safety analysis
论文作者
论文摘要
我们提出了HUDD，该工具通过自动识别DNN错误的根本原因并重新训练DNN来支持由深神经网络（DNN）启用的系统的安全分析实践。 HUDD代表基于热图的无监督调试DNN，它会自动簇诱发错误的图像，其结果是由于DNN神经元的常见子集引起的。目的是用于生成的群集，以分组具有共同特征的误差图像，即具有共同的根本原因。 HUDD通过将聚类算法应用于矩阵（即热图）捕获每个DNN神经元在DNN结果上的相关性来识别根本原因。同样，HUDD重新培训DNN具有根据与已识别图像簇的相关性自动选择的图像。我们对来自汽车域的DNN进行的经验评估表明，HUDD自动识别DNN错误的所有不同根本原因，从而支持安全分析。同样，与现有方法相比，我们的再培训方法已显示出比现有方法更有效地提高DNN的准确性。可以在https://youtu.be/drjvakp7jdu上获得HUDD的演示视频。
We present HUDD, a tool that supports safety analysis practices for systems enabled by Deep Neural Networks (DNNs) by automatically identifying the root causes for DNN errors and retraining the DNN. HUDD stands for Heatmap-based Unsupervised Debugging of DNNs, it automatically clusters error-inducing images whose results are due to common subsets of DNN neurons. The intent is for the generated clusters to group error-inducing images having common characteristics, that is, having a common root cause. HUDD identifies root causes by applying a clustering algorithm to matrices (i.e., heatmaps) capturing the relevance of every DNN neuron on the DNN outcome. Also, HUDD retrains DNNs with images that are automatically selected based on their relatedness to the identified image clusters. Our empirical evaluation with DNNs from the automotive domain have shown that HUDD automatically identifies all the distinct root causes of DNN errors, thus supporting safety analysis. Also, our retraining approach has shown to be more effective at improving DNN accuracy than existing approaches. A demo video of HUDD is available at https://youtu.be/drjVakP7jdU.
