一句话:提出通过条件化提升 DNN 运行测试效率,在有限标注预算下获得更精确的测试结果。
随着 DNN 被广泛集成到软件系统中,如何在实际现场条件下对 DNN 进行高效运行测试成为迫切需求。核心挑战在于:现场收集的数据标注预算非常有限,但测试又需要产生足够精确的结果。论文标题表明其思路是采用 conditioning(条件化)来提升运行测试效率,使有限标注预算得到更有效的利用。不过,给出的摘要只交代了动机与挑战,未具体说明条件化的技术机制、理论性质以及实验评估设置和结果。
With the increasing adoption of Deep Neural Network (DNN) models as integral parts of software systems, efficient operational testing of DNNs is much in demand to ensure these models' actual performance in field conditions. A challenge is that the testing often needs to produce precise results with a very limited budget for labeling data collected in field.