Hierarchical Pyramid Representations for Semantic Segmentation

TL;DR

This paper introduces a hierarchical pyramid framework for semantic segmentation that captures multiscale and contextual information through recursive region-based aggregation, improving scene understanding in complex images.

Contribution

It proposes a novel hierarchical, multiscale pyramid representation that models object structures and their relationships without extra supervision.

Findings

Achieves state-of-the-art performance on PASCAL Context dataset

Demonstrates effective modeling of hierarchical and contextual scene properties

Improves segmentation accuracy in complex, cluttered scenes

Abstract

Understanding the context of complex and cluttered scenes is a challenging problem for semantic segmentation. However, it is difficult to model the context without prior and additional supervision because the scene's factors, such as the scale, shape, and appearance of objects, vary considerably in these scenes. To solve this, we propose to learn the structures of objects and the hierarchy among objects because context is based on these intrinsic properties. In this study, we design novel hierarchical, contextual, and multiscale pyramidal representations to capture the properties from an input image. Our key idea is the recursive segmentation in different hierarchical regions based on a predefined number of regions and the aggregation of the context in these regions. The aggregated contexts are used to predict the contextual relationship between the regions and partition the regions in the following hierarchical level. Finally, by constructing the pyramid representations from the recursively aggregated context, multiscale and hierarchical properties are attained. In the experiments, we confirmed that our proposed method achieves state-of-the-art performance in PASCAL Context.