CDGNet: Class Distribution Guided Network for Human Parsing

TL;DR

CDGNet leverages class distribution guidance based on positional priors to improve human parsing accuracy by explicitly modeling the spatial distribution of body parts, leading to superior results on standard benchmarks.

Contribution

The paper introduces a novel class distribution guidance mechanism that encodes positional priors for each human part, enhancing parsing performance.

Findings

Significant improvement on LIP, ATR, and CIHP benchmarks.

Effective utilization of position distribution as supervision.

Outperforms existing methods in human parsing accuracy.

Abstract

The objective of human parsing is to partition a human in an image into constituent parts. This task involves labeling each pixel of the human image according to the classes. Since the human body comprises hierarchically structured parts, each body part of an image can have its sole position distribution characteristic. Probably, a human head is less likely to be under the feet, and arms are more likely to be near the torso. Inspired by this observation, we make instance class distributions by accumulating the original human parsing label in the horizontal and vertical directions, which can be utilized as supervision signals. Using these horizontal and vertical class distribution labels, the network is guided to exploit the intrinsic position distribution of each class. We combine two guided features to form a spatial guidance map, which is then superimposed onto the baseline network by multiplication and concatenation to distinguish the human parts precisely. We conducted extensive experiments to demonstrate the effectiveness and superiority of our method on three well-known benchmarks: LIP, ATR, and CIHP databases.