Counterexample-Guided Data Augmentation
This work addresses the challenge of enhancing model robustness in domain-specific applications like autonomous driving, though it appears incremental as it builds on existing data augmentation methods.
The authors tackled the problem of improving machine learning models by introducing a counterexample-guided data augmentation framework, which uses misclassified examples to generate new training data and achieved better performance compared to classical augmentation techniques in an object detection case study for autonomous driving.
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.