论文标题
研究和解释图像分类的频率偏差
Investigating and Explaining the Frequency Bias in Image Classification
论文作者
论文摘要
CNN表现出与人类不同的许多行为，其中之一是采用高频组成部分的能力。本文讨论了图像分类任务中的频率偏差现象：高频组件实际上比低频和中间频率组件的利用要少得多。我们首先通过提出有关特征歧视和学习优先级的两个观察结果来研究频率偏差现象。此外，我们假设（i）光谱密度，（ii）类一致性直接影响频率偏差。具体而言，我们的研究验证数据集的光谱密度主要影响学习优先级，而课程一致性主要影响特征歧视。
CNNs exhibit many behaviors different from humans, one of which is the capability of employing high-frequency components. This paper discusses the frequency bias phenomenon in image classification tasks: the high-frequency components are actually much less exploited than the low- and mid-frequency components. We first investigate the frequency bias phenomenon by presenting two observations on feature discrimination and learning priority. Furthermore, we hypothesize that (i) the spectral density, (ii) class consistency directly affect the frequency bias. Specifically, our investigations verify that the spectral density of datasets mainly affects the learning priority, while the class consistency mainly affects the feature discrimination.
