Feature context learning for human parsing
Feature context learning for human parsing作者机构：School of Electronic Information and Communications Huazhong University of Science and Technology Alibaba Group
出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))
年 卷 期：2019年第62卷第12期
页 面：6-19页
核心收录：
学科分类：0808[工学-电气工程] 08[工学] 081104[工学-模式识别与智能系统] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）]
基 金：supported in part by National Key Research and Development Program of China(Grant No.2018YFB1004600) National Natural Science Foundation of China(Grant No.61703171) Natural Science Foundation of Hubei Province of China(Grant No.2018CFB199) supported by Alibaba Group through Alibaba Innovative Research(AIR)Program supported by Young Elite Scientists Sponsorship Program by CAST supported by National Program for Support of Top-Notch Young Professionals in part by Program for HUST Academic Frontier Youth Team
主 题：human parsing context learning fully convolutional networks graph convolutional network semantic segmentation
摘 要：Parsing inconsistency, referring to the scatters and speckles in the parsing results as well as imprecise contours, is a long-standing problem in human parsing. It results from the fact that the pixel-wise classification loss independently considers each pixel. To address the inconsistency issue, we propose in this paper an end-to-end trainable, highly flexible and generic module called feature context module(FCM).FCM explores the correlation of adjacent pixels and aggregates the contextual information embedded in the real topology of the human body. Therefore, the feature representations are enhanced and thus quite robust in distinguishing semantically related parts. Extensive experiments are done with three different backbone models and four benchmark datasets, suggesting that FCM can be an effective and efficient plug-in to consistently improve the performance of existing algorithms without sacrificing the inference speed too much.
同方期刊数据库