Blended Grammar Network for Human Parsing

Xiaomei Zhang, Yingying Chen, Bingke Zhu, Jinqiao Wang, Ming Tang

Abstract:

Although human parsing has made great progress, it still
faces a challenge, i.e., how to extract the whole foreground from simi-
lar or cluttered scenes effectively. In this paper, we propose a Blended
Grammar Network (BGNet), to deal with the challenge. BGNet exploits
the inherent hierarchical structure of a human body and the relationship
of different human parts by means of grammar rules in both cascaded
and paralleled manner. In this way, conspicuous parts, which are easily
distinguished from the background, can amend the segmentation of in-
conspicuous ones, improving the foreground extraction. We also design a
Part-aware Convolutional Recurrent Neural Network (PCRNN) to pass
messages which are generated by grammar rules. To train PCRNNs effectively, we present a blended grammar loss to supervise the training
of PCRNNs. We conduct extensive experiments to evaluate BGNet on
PASCAL-Person-Part, LIP, and PPSS datasets. BGNet obtains state-of-
the-art performance on these human parsing datasets.