Spatial Pyramid Based Graph Reasoning for Semantic Segmentation

TL;DR

This paper introduces a lightweight graph reasoning module using a spatial pyramid and an improved Laplacian for semantic segmentation, capturing long-range context efficiently in feature space.

Contribution

It proposes a data-dependent Laplacian with attention for graph reasoning directly in feature space, enhancing spatial context modeling without complex projections.

Findings

Achieves competitive accuracy on Cityscapes, COCO Stuff, PASCAL Context, and PASCAL VOC.

Reduces computational and memory overhead compared to existing methods.

Effectively captures multi-scale long-range contextual information.

Abstract

The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such as semantic segmentation. In this paper, we apply graph convolution into the semantic segmentation task and propose an improved Laplacian. The graph reasoning is directly performed in the original feature space organized as a spatial pyramid. Different from existing methods, our Laplacian is data-dependent and we introduce an attention diagonal matrix to learn a better distance metric. It gets rid of projecting and re-projecting processes, which makes our proposed method a light-weight module that can be easily plugged into current computer vision architectures. More importantly, performing graph reasoning directly in the feature space retains spatial relationships and makes spatial pyramid possible to explore multiple long-range contextual patterns from different scales. Experiments on Cityscapes, COCO Stuff, PASCAL Context and PASCAL VOC demonstrate the effectiveness of our proposed methods on semantic segmentation. We achieve comparable performance with advantages in computational and memory overhead.