Channel and Spatial Relation-Propagation Network for RGB-Thermal Semantic Segmentation

TL;DR

This paper introduces CSRPNet, a novel RGB-T semantic segmentation network that effectively propagates shared modality information while reducing contamination, leading to improved segmentation performance in challenging conditions.

Contribution

The paper proposes a relation-propagation mechanism in channel and spatial domains to better leverage shared features between RGB and thermal images, addressing modality contamination issues.

Findings

CSRPNet outperforms state-of-the-art methods on benchmark datasets.

The relation-propagation approach effectively captures shared features.

The dual-path feature refinement improves segmentation accuracy.

Abstract

RGB-Thermal (RGB-T) semantic segmentation has shown great potential in handling low-light conditions where RGB-based segmentation is hindered by poor RGB imaging quality. The key to RGB-T semantic segmentation is to effectively leverage the complementarity nature of RGB and thermal images. Most existing algorithms fuse RGB and thermal information in feature space via concatenation, element-wise summation, or attention operations in either unidirectional enhancement or bidirectional aggregation manners. However, they usually overlook the modality gap between RGB and thermal images during feature fusion, resulting in modality-specific information from one modality contaminating the other. In this paper, we propose a Channel and Spatial Relation-Propagation Network (CSRPNet) for RGB-T semantic segmentation, which propagates only modality-shared information across different modalities and alleviates the modality-specific information contamination issue. Our CSRPNet first performs relation-propagation in channel and spatial dimensions to capture the modality-shared features from the RGB and thermal features. CSRPNet then aggregates the modality-shared features captured from one modality with the input feature from the other modality to enhance the input feature without the contamination issue. While being fused together, the enhanced RGB and thermal features will be also fed into the subsequent RGB or thermal feature extraction layers for interactive feature fusion, respectively. We also introduce a dual-path cascaded feature refinement module that aggregates multi-layer features to produce two refined features for semantic and boundary prediction. Extensive experimental results demonstrate that CSRPNet performs favorably against state-of-the-art algorithms.