Position-Aware Relation Learning for RGB-Thermal Salient Object Detection

TL;DR

This paper introduces PRLNet, a position-aware relation learning network based on swin transformer for RGB-Thermal salient object detection, which improves boundary clarity and region homogeneity by exploring pixel relationships.

Contribution

The paper proposes a novel position-aware relation learning network with a signed distance map module and directional feature refinement, enhancing multispectral feature representation for RGB-T SOD.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Generates salient object masks with clear boundaries

Enhances intra-class compactness and inter-class separation

Abstract

RGB-Thermal salient object detection (SOD) combines two spectra to segment visually conspicuous regions in images. Most existing methods use boundary maps to learn the sharp boundary. These methods ignore the interactions between isolated boundary pixels and other confident pixels, leading to sub-optimal performance. To address this problem,we propose a position-aware relation learning network (PRLNet) for RGB-T SOD based on swin transformer. PRLNet explores the distance and direction relationships between pixels to strengthen intra-class compactness and inter-class separation, generating salient object masks with clear boundaries and homogeneous regions. Specifically, we develop a novel signed distance map auxiliary module (SDMAM) to improve encoder feature representation, which takes into account the distance relation of different pixels in boundary neighborhoods. Then, we design a feature refinement approach with directional field (FRDF), which rectifies features of boundary neighborhood by exploiting the features inside salient objects. FRDF utilizes the directional information between object pixels to effectively enhance the intra-class compactness of salient regions. In addition, we constitute a pure transformer encoder-decoder network to enhance multispectral feature representation for RGB-T SOD. Finally, we conduct quantitative and qualitative experiments on three public benchmark datasets.The results demonstrate that our proposed method outperforms the state-of-the-art methods.