论文标题
映射DNN嵌入网络泛化预测的歧管
Mapping DNN Embedding Manifolds for Network Generalization Prediction
论文作者
论文摘要
在不断变化的条件下了解深度神经网络（DNN）的性能对于在具有无约束的环境的安全关键应用中部署DNN至关重要。最近，提出了网络泛化预测（NGP）的任务，以预测DNN将如何在新的操作域中概括。以前的NGP方法依赖于新操作域的标记的元数据和已知分布。在这项研究中，我们提出了第一种NGP方法，该方法仅基于DNN嵌入空间中外部操作域图的未标记图像来预测DNN性能。我们为行人，黑色素瘤和动物分类任务展示了这种技术，并在15个NGP任务中的13个中显示了最先进的NGP状态，而无需领域知识。此外，我们表明，当DNN性能较差时，我们的NGP嵌入地图可用于识别错误分类的图像。
Understanding Deep Neural Network (DNN) performance in changing conditions is essential for deploying DNNs in safety critical applications with unconstrained environments, e.g., perception for self-driving vehicles or medical image analysis. Recently, the task of Network Generalization Prediction (NGP) has been proposed to predict how a DNN will generalize in a new operating domain. Previous NGP approaches have relied on labeled metadata and known distributions for the new operating domains. In this study, we propose the first NGP approach that predicts DNN performance based solely on how unlabeled images from an external operating domain map in the DNN embedding space. We demonstrate this technique for pedestrian, melanoma, and animal classification tasks and show state of the art NGP in 13 of 15 NGP tasks without requiring domain knowledge. Additionally, we show that our NGP embedding maps can be used to identify misclassified images when the DNN performance is poor.
