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 1805.06962cs.LGcs.AIstat.ML
收藏

反例引导的数据增强

Counterexample-Guided Data Augmentation

University of California, Berkeley(加州大学伯克利分校)

Tommaso Dreossi, Shromona Ghosh, Xiangyu Yue, Kurt Keutzer, Alberto Sangiovanni-Vincentelli, Sanjit A. Seshia

摘要:

我们提出了一个新的框架,用于增加数据集的机器学习的基础上的反例。反例是错误分类的例子,对重新训练和改进模型具有重要的性质。我们的框架的关键组件包括一个反例生成器,它产生的数据项被错误分类的模型和错误表,一种新的数据结构,存储有关错误分类的信息。错误表可用于解释模型的漏洞,并用于有效地生成用于增强的反例。我们通过将其与基于深度神经网络的自动驾驶目标检测案例研究中的经典增强技术进行比较,展示了所提出的框架的有效性。

英文摘要:

We present a novel framework for augmenting data sets for machine learning based on counterexamples. Counterexamples are misclassified examples that have important properties for retraining and improving the model. Key components of our framework include a counterexample generator, which produces data items that are misclassified by the model and error tables, a novel data structure that stores information pertaining to misclassifications. Error tables can be used to explain the model's vulnerabilities and are used to efficiently generate counterexamples for augmentation. We show the efficacy of the proposed framework by comparing it to classical augmentation techniques on a case study of object detection in autonomous driving based on deep neural networks.

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。

↑