Convolutional networks are considered shift invariant, but it was demonstrated that their response may vary according to the exact location of the objects. In this paper we will demonstrate that most commonly investigated datasets have a bias, where objects are over-represented at the center of the image during training. This bias and the boundary condition of these networks can have a significant effect on the performance of these architectures and their accuracy drops significantly as an object approaches the boundary. We will also demonstrate how this effect can be mitigated with data augmentation techniques.

翻译：卷积网络被认为是平移不变的，但研究表明其响应可能因物体的精确位置而变化。本文将证明，大多数常见研究的数据集存在偏差，即训练过程中物体在图像中心过度呈现。这种偏差以及网络的边界条件会显著影响这些架构的性能，当物体靠近边界时，其准确性大幅下降。我们还将展示如何通过数据增强技术缓解这一影响。