Reducing the Feature Divergence of RGB and Near-Infrared Images Using Switchable Normalization
Abstract
Visual pattern recognition over agricultural areas is an important application of aerial image processing. In this paper, we consider the multi-modality nature of agricultural aerial images and show that naively combining different modalities together without taking the feature divergence into account can lead to sub-optimal results. Thus, we apply a Switchable Normalization block to our DeepLabV3+ segmentation model to alleviate the feature divergence. Using the popular symmetric Kullback–Leibler divergence measure, we show that our model can greatly reduce the divergence between RGB and near-infrared channels. Together with a hybrid loss function, our model achieves nearly 10% improvements in mean IoU over previously published baseline.
Cite
Text
Yang et al. "Reducing the Feature Divergence of RGB and Near-Infrared Images Using Switchable Normalization." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00031Markdown
[Yang et al. "Reducing the Feature Divergence of RGB and Near-Infrared Images Using Switchable Normalization." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/yang2020cvprw-reducing/) doi:10.1109/CVPRW50498.2020.00031BibTeX
@inproceedings{yang2020cvprw-reducing,
title = {{Reducing the Feature Divergence of RGB and Near-Infrared Images Using Switchable Normalization}},
author = {Yang, Siwei and Yu, Shaozuo and Zhao, Bingchen and Wang, Yin},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2020},
pages = {206-211},
doi = {10.1109/CVPRW50498.2020.00031},
url = {https://mlanthology.org/cvprw/2020/yang2020cvprw-reducing/}
}