期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 60, 期 -, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2022.3225843
关键词
Category-wise enhancement learning (CEL); category-wise fusion; imbalance learning; multimodal remote sensing; semantic segmentation
类别
资金
- National Natural Science Foundation of China [61976002, 61976003, 61860206004, U20B2068]
This article introduces a method called CaFE, which leverages category priors to achieve effective feature fusion and imbalance learning in multimodal remote sensing image semantic segmentation. The method disentangles the feature fusion process and assigns weights to category regions based on sample proportions, leading to improved segmentation results.
This article presents a simple yet effective method called Category-wise Fusion and Enhancement learning (CaFE), which leverages the category priors to achieve effective feature fusion and imbalance learning, for multimodal remote sensing image semantic segmentation. In particular, we disentangle the feature fusion process via the categories to achieve the category-wise fusion based on the fact that the feature fusion in the same category regions tends to have similar characteristics. The disentangled fusion would also increase the fusion capacity with a small number of parameters while reducing the dependence on large-scale training data. For the sample imbalance problem, we design a simple yet effective category-wise enhancement learning scheme. In particular, we assign the weight for each category region based on the proportion of samples in this region over the whole image. By this way, the learning algorithm would focus more on the regions with smaller proportion. Note that both category-wise feature fusion and imbalance learning are only performed in the training stage, and the segmentation efficiency is thus not affected. Experimental results on two benchmark datasets demonstrate the effectiveness of our CaFE against other state-of-the-art methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据