Learning to Predict Context-adaptive Convolution for Semantic Segmentation

european conference on computer vision(2020)

引用 37|浏览180
暂无评分
摘要
Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods demonstrate that using global context for re-weighting feature channels can effectively improve the accuracy of semantic segmentation. However, the globally-sharing feature re-weighting vector might not be optimal for regions of different classes in the input image. In this paper, we propose a Context-adaptive Convolution Network (CaC-Net) to predict a spatially-varying feature weighting vector for each spatial location of the semantic feature maps. In CaC-Net, a set of context-adaptive convolution kernels are predicted from the global contextual information in a parameter-efficient manner. When used for convolution with the semantic feature maps, the predicted convolutional kernels can generate the spatially-varying feature weighting factors capturing both global and local contextual information. Comprehensive experimental results show that our CaC-Net achieves superior segmentation performance on three public datasets, PASCAL Context, PASCAL VOC 2012 and ADE20K.
更多
查看译文
关键词
segmentation,learning,semantic,context-adaptive
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