Be Like Water：通过自适应特征归一化对外部变量的鲁棒性
Be Like Water: Robustness to Extraneous Variables Via Adaptive Feature Normalization
摘要：
外部变量是与特定任务无关的变量，但严重影响可用数据的分布。在这项工作中，我们证明了这些变量的存在会降低深度学习模型的性能。我们研究了三个数据集，其中有一个强大的影响，已知的外来变量：分类中风患者的上身运动，手术活动的注释，并识别损坏的图像。用批量归一化训练的模型学习高度依赖于无关变量的特征。在批量归一化中，用于归一化特征的统计量是从训练集学习的，并在测试时固定，这在存在变化的无关变量的情况下会产生不匹配。我们证明了在推理过程中自适应地估计特征统计，如在实例归一化中，解决了这个问题，产生了对无关变量的变化更鲁棒的归一化特征。这导致不同网络架构和特征统计选择的性能显著提高。
英文摘要：
Extraneous variables are variables that are irrelevant for a certain task, but heavily affect the distribution of the available data. In this work, we show that the presence of such variables can degrade the performance of deep-learning models. We study three datasets where there is a strong influence of known extraneous variables: classification of upper-body movements in stroke patients, annotation of surgical activities, and recognition of corrupted images. Models trained with batch normalization learn features that are highly dependent on the extraneous variables. In batch normalization, the statistics used to normalize the features are learned from the training set and fixed at test time, which produces a mismatch in the presence of varying extraneous variables. We demonstrate that estimating the feature statistics adaptively during inference, as in instance normalization, addresses this issue, producing normalized features that are more robust to changes in the extraneous variables. This results in a significant gain in performance for different network architectures and choices of feature statistics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
