SLMSF-Net: A Semantic Localization and Multi-Scale Fusion Network for RGB-D Salient Object Detection
Open Access
Abstract
Salient Object Detection (SOD) in RGB-D images plays a crucial role in the field of computer vision, with its central aim being to identify and segment the most visually striking objects within a scene. However, optimizing the fusion of multi-modal and multi-scale features to enhance detection performance remains a challenge. To address this issue, we propose a network model based on semantic localization and multi-scale fusion (SLMSF-Net), specifically designed for RGB-D SOD. Firstly, we designed a Deep Attention Module (DAM), which extracts valuable depth feature information from both channel and spatial perspectives and efficiently merges it with RGB features. Subsequently, a Semantic Localization Module (SLM) is introduced to enhance the top-level modality fusion features, enabling the precise localization of salient objects. Finally, a Multi-Scale Fusion Module (MSF) is employed to perform inverse decoding on the modality fusion features, thus restoring the detailed information of the objects and generating high-precision saliency maps. Our approach has been validated across six RGB-D salient object detection datasets. The experimental results indicate an improvement of 0.20~1.80%, 0.09~1.46%, 0.19~1.05%, and 0.0002~0.0062, respectively in maxF, maxE, S, and MAE metrics, compared to the best competing methods (AFNet, DCMF, and C2DFNet).Keywords
Funding Information
- National Natural Science Foundation of China (61972357, LGF22F020017, GG21F010013, Y21F020030)
- Basic Public Welfare Research Program of Zhejiang Province (61972357, LGF22F020017, GG21F010013, Y21F020030)
- Natural Science Foundation of Zhejiang Province (61972357, LGF22F020017, GG21F010013, Y21F020030)
This publication has 57 references indexed in Scilit:
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- RGBD Salient Object Detection via Deep FusionIEEE Transactions on Image Processing, 2017
- V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation2016
- Salient object detection via global and local cuesPattern Recognition, 2015
- Depth saliency based on anisotropic center-surround difference2014
- Depth Enhanced Saliency Detection Method2014
- RGBD Salient Object Detection: A Benchmark and Algorithms2014
- Depth Matters: Influence of Depth Cues on Visual Saliency2012
- Frequency-tuned salient region detection2009
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998