Correlating Edge, Pose with Parsing
This work addresses human parsing for computer vision applications, but it is incremental as it builds on known benefits of edge and pose features.
The paper tackled the problem of improving human parsing by jointly leveraging human semantic boundaries and keypoint locations, and found that modeling correlations among edge, pose, and parsing features outperforms simple concatenation, achieving new state-of-the-art accuracy on three datasets.
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.