一句话：提出 DeepSample，用采样选择小而代表性强的 DNN 测试输入，兼顾准确率估计可信度与误预测暴露。
DNN 已成为许多软件系统分类与回归任务的核心组件。企业若要用能代表实际运行输入的数据集测试 DNN，需承担高昂的人工标注成本。核心挑战在于选取尽可能小但仍具代表性的测试输入集，以降低标注代价，同时得到对 DNN 预期准确率无偏且高置信的估计；此外，测试者还希望尽可能多地暴露 DNN 的误预测，以便改进模型。DeepSample 面向这一三重要求——小数据集、可信估计、误预测暴露——提出基于采样的 DNN 测试方法，用于运行准确率评估。摘要未报告具体实验数值。
Deep Neural Networks (DNN) are core components for classification and regression tasks of many software systems. Companies incur in high costs for testing DNN with datasets representative of the inputs expected in operation, as these need to be manually labelled. The challenge is to select a representative set of test inputs as small as possible to reduce the labelling cost, while sufficing to yield unbiased high-confidence estimates of the expected DNN accuracy. At the same time, testers are interested in exposing as many DNN mispredictions as possible to improve the DNN, ending up in the need for techniques pursuing a threefold aim: small dataset size, trustworthy estimates, mispredictions exposure.