Zero padding is widely used in convolutional neural networks to prevent the size of feature maps diminishing too fast. However, it has been claimed to disturb the statistics at the border. As an alternative, we propose a context-aware (CA) padding approach to extend the image. We reformulate the padding problem as an image extrapolation problem and illustrate the effects on the semantic segmentation task. Using context-aware padding, the ResNet-based segmentation model achieves higher mean Intersection-Over-Union than the traditional zero padding on the Cityscapes and the dataset of DeepGlobe satellite imaging challenge. Furthermore, our padding does not bring noticeable overhead during training and testing.

翻译：零覆盖被广泛用于进化神经网络,以防止地貌图的大小缩小过快,然而,据称它扰乱了边境的统计数据。作为一种替代办法,我们建议采用环境觉悟(CA)覆盖法来扩展图像。我们重新将铺设问题作为一个图像外推问题,并演示对语系分解任务的影响。使用环境觉悟模式,ResNet的分割模型比城市景象上传统的零覆盖法和DeepGlobe卫星成像挑战数据集的中间切换率更高。此外,我们的铺设在培训和测试期间并没有带来明显的间接影响。