Spatialising uncertainty in image segmentation using weakly supervised convolutional neural networks: a case study from historical map processing.
IET Image Processing(2018)
摘要
Convolutional neural networks (CNNs) such as encoder-decoder CNNs have increasingly been employed for semantic image segmentation at the pixel-level requiring pixel-level training labels, which are rarely available in real-world scenarios. In practice, weakly annotated training data at the image patch level are often used for pixel-level segmentation tasks, requiring further processing to obtain a...
更多查看译文
关键词
cartography,data visualisation,document image processing,feature extraction,feedforward neural nets,history,image classification,image resolution,image segmentation,inference mechanisms
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