Self-Supervised Neural Aggregation Networks for Human Parsing

Jian Zhao, Jianshu Li, Xuecheng Nie, Fang Zhao, Yunpeng Chen, Zhecan Wang, Jiashi Feng, Shuicheng Yan
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this paper, we present a Self-Supervised Neural Aggregation Network (SS-NAN) for human parsing. SS-NAN adaptively learns to aggregate the multi-scale features at each pixel "address". In order to further improve the feature discriminative capacity, a self-supervised joint loss is adopted as an auxiliary learning strategy, which imposes human joint structures into parsing results without resorting to extra supervision. The proposed SS-NAN is endto-end trainable. SS-NAN can be integrated into
more » ... be integrated into any advanced neural networks to help aggregate features regarding the importance at different positions and scales and incorporate rich high-level knowledge regarding human joint structures from a global perspective, which in turn improve the parsing results. Comprehensive evaluations on the recent Look into Person (LIP) and the PASCAL-Person-Part benchmark datasets demonstrate the significant superiority of our method over other state-of-the-arts.
doi:10.1109/cvprw.2017.204 dblp:conf/cvpr/ZhaoLNZCWFY17 fatcat:2xxnsmfmnnd7tkuc7flednsnc4