Neural networks are prone to overfitting and memorizing data patterns. To avoid over-fitting and enhance their generalization and performance, various methods have been suggested in the literature, including dropout, regularization, label smoothing, etc. One such method is augmentation which introduces different types of corruption in the data to prevent the model from overfitting and to memorize patterns present in the data. A sub-area of data augmentation is image mixing and deleting. This specific type of augmentation either deletes image regions or mixes two images to hide or make particular characteristics of images confusing for the network, forcing it to emphasize the overall structure of the object in an image. Models trained with this approach have proven to perform and generalize well compared to those trained without image mixing or deleting. An added benefit that comes with this method of training is robustness against image corruption. Due to its low computational cost and recent success, researchers have proposed many image mixing and deleting techniques. We furnish an in-depth survey of image mixing and deleting techniques and provide categorization via their most distinguishing features. We initiate our discussion with some fundamental relevant concepts. Next, we present essentials, such as each category's strengths and limitations, describing their working mechanism, basic formulations, and applications. We also discuss the general challenges and recommend possible future research directions for image mixing and deleting data augmentation techniques. Datasets and codes for evaluation are publicly available here.
翻译:为避免过分适应和提高其一般化和性能,文献中提出了各种方法,包括辍学、正规化、标签平滑等。 一种方法是增加数据,在数据中引入不同类型的腐败,以防止模型过度适应和记忆数据中存在的模式。数据增强的子领域是图像混合和删除。这种特定的增强方式要么删除图像区域,要么混合图像,或者混合两种图像,以掩盖或混淆网络图像的特殊特征,迫使它强调图像中对象的整体结构。经过这种方式培训的模型已证明能够与经过培训的模型相比很好地运行和普及。这种培训方法带来的额外好处是稳健防止图像腐败。由于计算成本低和最近的成功,研究人员提出了许多图像混合和删除技术。我们提供了对图像混合和删除技术的深入调查,并通过其最显著的特征提供分类。我们开始讨论一些基本的相关概念。接下来,我们介绍基本原理,例如每个类别的基本优势和标准,以及未来评估方法,我们在这里讨论如何进行基本的研究和升级,我们还要讨论其基本的方法。