MixBoost: Improving the Robustness of Deep Neural Networks by Boosting Data Augmentation
This work addresses robustness challenges for AI models in real-world applications, offering an incremental improvement over existing data augmentation methods.
The paper tackled the problem of improving the robustness of deep neural networks in open-set environments by analyzing the internal mechanisms of data augmentation methods and proposing a mask-based boosting technique. The result is a method that significantly enhances several robustness metrics and outperforms state-of-the-art approaches while also improving test accuracy.
As more and more artificial intelligence (AI) technologies move from the laboratory to real-world applications, the open-set and robustness challenges brought by data from the real world have received increasing attention. Data augmentation is a widely used method to improve model performance, and some recent works have also confirmed its positive effect on the robustness of AI models. However, most of the existing data augmentation methods are heuristic, lacking the exploration of their internal mechanisms. We apply the explainable artificial intelligence (XAI) method, explore the internal mechanisms of popular data augmentation methods, analyze the relationship between game interactions and some widely used robustness metrics, and propose a new proxy for model robustness in the open-set environment. Based on the analysis of the internal mechanisms, we develop a mask-based boosting method for data augmentation that comprehensively improves several robustness measures of AI models and beats state-of-the-art data augmentation approaches. Experiments show that our method can be widely applied to many popular data augmentation methods. Different from the adversarial training, our boosting method not only significantly improves the robustness of models, but also improves the accuracy of test sets. Our code is available at \url{https://github.com/Anonymous_for_submission}.