Pyramidal Region Context Module for Semantic Segmentation
Context modeling is widely exploited to enhance seman-tic correlation in semantic segmentation task.Recent ap-proaches(e.g.,OCNet,CCNet and DANet)apply non-local type of network to capture the context information.However,they are not accurate enough for handling scale-varying ob-jects due to that they consider very little local dependencies of the adjacent pixels.In this work,we address the complex scene segmentation problem by combining region depen-dencies and global contextual information.Motivated by the fact that scale of objects largely varies on images,we design the Pyramidal Region Context Module(PRCM)to handle the neighbor relationship of multi-scale regions.In addition,we adopt a depth-to-space layer(PixelShuffle)to form the Scale Transfer Classifier(STC).Based on the two newly proposed modules,we introduce an end-to-end segmentation network-Pyramidal Region Network(PRNet).We empirically demon-strate the effectiveness of our approach on Cityscapes dataset,the results have shown impressive improvement compared with baselines.Notably,PRNet obtains mean IoU of 81.3 on test set of Cityscapes.
Neural Networks Semantic Segmentation Self-Attention
Tingting Liang Qijie Zhao Zhuoying Wang Kaiyu Shan Huan Zhang Yongtao Wang Zhi Tang
Institute of Computer Science and Technology,Peking University Beijing,P.R.China
国际会议
2019国图灵大会(ACM Turing Celebration conference-China 2019 )
成都
英文
237-242
2019-05-17（万方平台首次上网日期，不代表论文的发表时间）