Scene Segmentation with DAG-Recurrent Neural Networks.
IEEE Transactions on Pattern Analysis and Machine Intelligence(2018)
摘要
In this paper, we address the challenging task of scene segmentation. In order to capture the rich contextual dependencies over image regions, we propose Directed Acyclic Graph-Recurrent Neural Networks (DAG-RNN) to perform context aggregation over locally connected feature maps. More specifically, DAG-RNN is placed on top of pre-trained CNN (feature extractor) to embed context into local features...
更多查看译文
关键词
Context,Image segmentation,Object segmentation,Semantics,Context modeling,Neural networks,Training
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