Partial Convolution based Padding
This addresses padding inefficiencies in CNNs for computer vision tasks, offering an incremental improvement.
The paper tackles the problem of padding in convolutional neural networks by introducing partial convolution based padding, which re-weights convolution results near borders based on padded area ratios, and it consistently outperforms standard zero padding with better accuracy on ImageNet classification and semantic segmentation.
In this paper, we present a simple yet effective padding scheme that can be used as a drop-in module for existing convolutional neural networks. We call it partial convolution based padding, with the intuition that the padded region can be treated as holes and the original input as non-holes. Specifically, during the convolution operation, the convolution results are re-weighted near image borders based on the ratios between the padded area and the convolution sliding window area. Extensive experiments with various deep network models on ImageNet classification and semantic segmentation demonstrate that the proposed padding scheme consistently outperforms standard zero padding with better accuracy.