MiAMix: Enhancing Image Classification through a Multi-stage Augmented Mixed Sample Data Augmentation Method

TL;DR

MiAMix is a novel multi-stage augmented mixup technique that enhances image classification by integrating diverse augmentation methods into the mixup framework, improving performance and efficiency.

Contribution

Introduces MiAMix, a multi-stage augmented mixup method that combines multiple augmentation strategies for improved model generalization in image classification.

Findings

MiAMix outperforms existing MSDA methods on four benchmarks.

MiAMix achieves better accuracy with lower computational overhead.

The method integrates seamlessly into existing training pipelines.

Abstract

Despite substantial progress in the field of deep learning, overfitting persists as a critical challenge, and data augmentation has emerged as a particularly promising approach due to its capacity to enhance model generalization in various computer vision tasks. While various strategies have been proposed, Mixed Sample Data Augmentation (MSDA) has shown great potential for enhancing model performance and generalization. We introduce a novel mixup method called MiAMix, which stands for Multi-stage Augmented Mixup. MiAMix integrates image augmentation into the mixup framework, utilizes multiple diversified mixing methods concurrently, and improves the mixing method by randomly selecting mixing mask augmentation methods. Recent methods utilize saliency information and the MiAMix is designed for computational efficiency as well, reducing additional overhead and offering easy integration into existing training pipelines. We comprehensively evaluate MiaMix using four image benchmarks and pitting it against current state-of-the-art mixed sample data augmentation techniques to demonstrate that MIAMix improves performance without heavy computational overhead.