IEEE Trans Cybern. 2022 Jun;52(6):4935-4948. doi: 10.1109/TCYB.2020.3025757. Epub 2022 Jun 16.
Image classification is a fundamental component in modern computer vision systems, where sparse representation-based classification has drawn a lot of attention due to its robustness. However, on the optimization of sparse learning systems, regularization and data augmentation are both powerful, but currently isolated. We believe that regularization and data augmentation can cooperate to generate a breakthrough in robust image classification. In this article, we propose a novel framework, regularization on augmented data (READ), which creates diversification in the data using the generic augmentation techniques to implement robust sparse representation-based image classification. When the training data are augmented, READ applies a distinct regularizer, l or l , in particular, on the augmented training data apart from the original data, so that regularization and data augmentation are utilized and enhanced synchronously. We introduce an elaborate theoretical analysis on how to optimize the sparse representation by both l -norm and l -norm with the generic data augmentation and demonstrate its performance in extensive experiments. The results obtained on several facial and object datasets show that READ outperforms many state-of-the-art methods when using deep features.
图像分类是现代计算机视觉系统的基本组成部分，基于稀疏表示的分类由于其鲁棒性而受到了广泛关注。然而，在稀疏学习系统的优化方面，正则化和数据增强都是强大的手段，但目前是相互孤立的。我们相信正则化和数据增强可以协同工作，为鲁棒的图像分类带来突破。在本文中，我们提出了一种新颖的框架，即基于增强数据的正则化（READ），该框架使用通用的增强技术在数据中创建多样性，以实现鲁棒的基于稀疏表示的图像分类。当训练数据被增强时，READ 会在原始数据之外的增强训练数据上应用一个独特的正则化器 l 或 l ，以便同时利用和增强正则化和数据增强。我们详细分析了如何通过通用的数据增强来优化 l -范数和 l -范数的稀疏表示，并在广泛的实验中展示了其性能。在几个面部和物体数据集上的结果表明，当使用深度特征时，READ 优于许多最先进的方法。
