Normalization is a pre-processing step that converts the data into a more usable representation. As part of the deep neural networks (DNNs), the batch normalization (BN) technique uses normalization to address the problem of internal covariate shift. It can be packaged as general modules, which have been extensively integrated into various DNNs, to stabilize and accelerate training, presumably leading to improved generalization. However, the effect of BN is dependent on the mini-batch size and it does not take into account any groups or clusters that may exist in the dataset when estimating population statistics. This study proposes a new normalization technique, called context normalization, for image data. This approach adjusts the scaling of features based on the characteristics of each sample, which improves the model's convergence speed and performance by adapting the data values to the context of the target task. The effectiveness of context normalization is demonstrated on various datasets, and its performance is compared to other standard normalization techniques.

翻译：归一化是一种预处理步骤，旨在将数据转换为更易用的表示形式。作为深度神经网络（DNN）的组成部分，批归一化（BN）技术利用归一化解决内部协变量偏移问题。该技术可封装为通用模块，已广泛集成于各类DNN中，用以稳定并加速训练过程，理论上可提升泛化能力。然而，BN的效果依赖于小批量大小，且在估计总体统计量时未考虑数据集中可能存在的分组或聚类现象。本研究针对图像数据提出一种新型归一化技术——上下文归一化。该方法基于每个样本的特征调整特征缩放，通过使数据值适配目标任务的情境，提升模型的收敛速度与性能。我们已在多个数据集上验证了上下文归一化的有效性，并将其性能与其他标准归一化技术进行了对比。