Reducing the feature divergence of RGB and near-infrared images using Switchable Normalization
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)(2020)
摘要
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.
更多查看译文
关键词
switchable normalization block,symmetric Kullback-Leibler divergence measure,DeepLabV3+ segmentation model,agricultural aerial images,multimodality nature,aerial image processing,agricultural areas,visual pattern recognition,RGB,feature divergence
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要