Graph-Boosted Attentive Network for Semantic Body Parsing

TL;DR

This paper introduces a novel CNN architecture with semantic and contour attention mechanisms, combined with pose encoding in a graphical model, to improve semantic body parsing in complex scenes, achieving state-of-the-art results.

Contribution

It presents a new graph-boosted attentive network that integrates pose information with semantic cues for enhanced body part segmentation.

Findings

Achieves state-of-the-art performance on Pascal Person-Part dataset.

Effective in resolving semantic ambiguities and boundary localization.

Recursively updates semantic cues with pose context.

Abstract

Human body parsing remains a challenging problem in natural scenes due to multi-instance and inter-part semantic confusions as well as occlusions. This paper proposes a novel approach to decomposing multiple human bodies into semantic part regions in unconstrained environments. Specifically we propose a convolutional neural network (CNN) architecture which comprises of novel semantic and contour attention mechanisms across feature hierarchy to resolve the semantic ambiguities and boundary localization issues related to semantic body parsing. We further propose to encode estimated pose as higher-level contextual information which is combined with local semantic cues in a novel graphical model in a principled manner. In this proposed model, the lower-level semantic cues can be recursively updated by propagating higher-level contextual information from estimated pose and vice versa across the graph, so as to alleviate erroneous pose information and pixel level predictions. We further propose an optimization technique to efficiently derive the solutions. Our proposed method achieves the state-of-art results on the challenging Pascal Person-Part dataset.