Boundary-Aware Cross-Level Multi-Scale Fusion Network for RGB-D Salient Object Detection

Abstract

Accurate salient object detection is of great importance in many computer vision applications. However, due to scale variation and complex backgrounds, achieving effective detection of objects at different scales in various scenes remains a challenging task. To address this, we propose a novel Boundary-Aware Cross-Level Multi-Scale Fusion Network (BCMNet), which enhances salient object detection by fully exploiting cross-level and multi-scale features. Specifically, we propose a Cross-Attention Fusion Module (CAFM) to fuse two modality features, generating modality fusion features. Next, a Boundary-Aware Module (BAM) combines low-level features with high-level features to learn boundary-aware features, which are integrated into each decoding unit during the decoding process. During the decoding stage, a Bidirectional Cross-Level Multi-Scale Module (BCMM) is introduced to effectively integrate cross-level features and perform multi-scale learning. Finally, the output of the BCMM, combined with boundary-aware features, generates saliency prediction maps. We conduct extensive experiments on six datasets, and the experimental results show that, compared to the state-of-the-art methods, the proposed model improves MAE, maxF, maxE, and S metrics by $0\sim 8$ %, $0\sim 1.34$ %, 0.11%~0.54%, and $0\sim 0.45$ %, respectively.