Understanding Data Augmentation from a Robustness Perspective
This provides a theoretical and empirical foundation for evaluating model safety and robustness in visual recognition, though it is incremental in advancing understanding rather than introducing a new method.
The paper tackles the problem of understanding data augmentation's mechanisms for improving model robustness in visual recognition, by framing it within game theory and showing that augmentation techniques primarily stimulate mid- and high-order game interactions, with experiments across multiple datasets and techniques.
In the realm of visual recognition, data augmentation stands out as a pivotal technique to amplify model robustness. Yet, a considerable number of existing methodologies lean heavily on heuristic foundations, rendering their intrinsic mechanisms ambiguous. This manuscript takes both a theoretical and empirical approach to understanding the phenomenon. Theoretically, we frame the discourse around data augmentation within game theory's constructs. Venturing deeper, our empirical evaluations dissect the intricate mechanisms of emblematic data augmentation strategies, illuminating that these techniques primarily stimulate mid- and high-order game interactions. Beyond the foundational exploration, our experiments span multiple datasets and diverse augmentation techniques, underscoring the universal applicability of our findings. Recognizing the vast array of robustness metrics with intricate correlations, we unveil a streamlined proxy. This proxy not only simplifies robustness assessment but also offers invaluable insights, shedding light on the inherent dynamics of model game interactions and their relation to overarching system robustness. These insights provide a novel lens through which we can re-evaluate model safety and robustness in visual recognition tasks.