论文标题
注意垫子 - CNN可以发展盲点
Mind the Pad -- CNNs can Develop Blind Spots
论文作者
论文摘要
我们展示了卷积网络中的特征图如何容易受到空间偏差的影响。由于结构选择的结合，某些位置的激活被系统地升高或削弱。这种偏见的主要来源是填充机制。根据卷积算术的几个方面，该机制可能会不均匀地应用填充物，从而导致学习重量的不对称性。我们证明了这种偏见如何损害某些任务，例如小物体检测：如果刺激位于受影响的区域，会抑制激活，从而导致盲点和误导。我们提出解决方案来减轻空间偏见，并演示它们如何提高模型准确性。
We show how feature maps in convolutional networks are susceptible to spatial bias. Due to a combination of architectural choices, the activation at certain locations is systematically elevated or weakened. The major source of this bias is the padding mechanism. Depending on several aspects of convolution arithmetic, this mechanism can apply the padding unevenly, leading to asymmetries in the learned weights. We demonstrate how such bias can be detrimental to certain tasks such as small object detection: the activation is suppressed if the stimulus lies in the impacted area, leading to blind spots and misdetection. We propose solutions to mitigate spatial bias and demonstrate how they can improve model accuracy.
