Partial Convolution based Padding
Abstract
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.
Cite
@article{arxiv.1811.11718,
title = {Partial Convolution based Padding},
author = {Guilin Liu and Kevin J. Shih and Ting-Chun Wang and Fitsum A. Reda and Karan Sapra and Zhiding Yu and Andrew Tao and Bryan Catanzaro},
journal= {arXiv preprint arXiv:1811.11718},
year = {2018}
}
Comments
11 pages; code is available at https://github.com/NVIDIA/partialconv