Correlating Edge, Pose with Parsing

• URL: http://arxiv.org/abs/2005.01431v1
• Date: Mon, 4 May 2020 12:39:13 GMT
• Title: Correlating Edge, Pose with Parsing
• Authors: Ziwei Zhang, Chi Su, Liang Zheng, Xiaodong Xie
• Abstract summary: This paper studies how human semantic boundaries and keypoint locations can jointly improve human parsing. We propose a Correlation Parsing Machine (CorrPM) employing a heterogeneous non-local block to discover the spatial affinity among feature maps from the edge, pose and parsing.
• Score: 35.27973063976257
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: According to existing studies, human body edge and pose are two beneficial factors to human parsing. The effectiveness of each of the high-level features (edge and pose) is confirmed through the concatenation of their features with the parsing features. Driven by the insights, this paper studies how human semantic boundaries and keypoint locations can jointly improve human parsing. Compared with the existing practice of feature concatenation, we find that uncovering the correlation among the three factors is a superior way of leveraging the pivotal contextual cues provided by edges and poses. To capture such correlations, we propose a Correlation Parsing Machine (CorrPM) employing a heterogeneous non-local block to discover the spatial affinity among feature maps from the edge, pose and parsing. The proposed CorrPM allows us to report new state-of-the-art accuracy on three human parsing datasets. Importantly, comparative studies confirm the advantages of feature correlation over the concatenation.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.