IMPROVING HUMAN PARSING BY EXTRACTING GLOBAL INFORMATION USING THE NON-LOCAL OPERATION

被引：0

作者：

Li, Tianpeng ^{[1
]}

Wan, Weitao ^{[1
]}

Huang, Yiqing ^{[1
]}

Chen, Jiansheng ^{[1
]}

Hu, Chunhua ^{[2
]}

Ma, Yu ^{[3
]}

机构：

[1] Tsinghua Univ, Dept Elect Engn, Beijing 100084, Peoples R China

[2] Tsinghua Univ, Sch Aerosp Engn, Beijing 100084, Peoples R China

[3] Tsinghua Univ, Yuquan Hosp, Beijing 100084, Peoples R China

来源：

2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2019年

基金：

中国国家自然科学基金;

关键词：

Deep Learning; Human Parsing; Semantic Segmentation; Non-local Operation;

D O I：

10.1109/icip.2019.8804412

中图分类号：

TB8 [摄影技术];

学科分类号：

0804 ;

摘要：

Human parsing has recently attracted considerable interests due to its wide application potentials. However, developing an accurate human parsing system is still a challenge for researchers. In this paper, we demonstrate that global information are critical for accurate prediction by applying a non-local operation for effectively extracting global information. Meanwhile several training data refinement methodologies are proposed to further boost the performance. Benefiting from all the approaches, the proposed single human parsing model NLGINet achieves the state-of-the-art segmentation accuracy on two human parsing benchmark datasets LIP and Pascal-Person-Parts.

引用

页码：2961 / 2965

页数：5