MoireDB: Formula-generated Interference-fringe Image Dataset
This addresses robustness issues in image recognition models for practical applications, but it is incremental as it builds on existing data augmentation methods.
The paper tackles the problem of image recognition robustness to real-world degradations by proposing MoireDB, a formula-generated interference-fringe image dataset for augmentation. The result shows that MoireDB outperforms traditional Fractal arts and feature visualizations-based augmentations in enhancing model robustness.
Image recognition models have struggled to treat recognition robustness to real-world degradations. In this context, data augmentation methods like PixMix improve robustness but rely on generative arts and feature visualizations (FVis), which have copyright, drawing cost, and scalability issues. We propose MoireDB, a formula-generated interference-fringe image dataset for image augmentation enhancing robustness. MoireDB eliminates copyright concerns, reduces dataset assembly costs, and enhances robustness by leveraging illusory patterns. Experiments show that MoireDB augmented images outperforms traditional Fractal arts and FVis-based augmentations, making it a scalable and effective solution for improving model robustness against real-world degradations.