RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images

Abstract

Salient object detection (SOD) for optical remote sensing images (RSIs) aims at locating and extracting visually distinctive objects/regions from the optical RSIs. Despite some saliency models were proposed to solve the intrinsic problem of optical RSIs (such as complex background and scale-variant objects), the accuracy and completeness are still unsatisfactory. To this end, we propose a relational reasoning network with parallel multi-scale attention for SOD in optical RSIs in this paper. The relational reasoning module that integrates the spatial and the channel dimensions is designed to infer the semantic relationship by utilizing high-level encoder features, thereby promoting the generation of more complete detection results. The parallel multi-scale attention module is proposed to effectively restore the detail information and address the scale variation of salient objects by using the low-level features refined by multi-scale attention. Extensive experiments on two datasets demonstrate that our proposed RRNet outperforms the existing state-of-the-art SOD competitors both qualitatively and quantitatively.

arXiv comment11 pages, 9 figures, Accepted by IEEE Transactions on Geoscience and Remote Sensing 2021, project: https://rmcong.github.io/proj_RRNet.html

References in corpus (13)

• Res2Net: A New Multi-scale Backbone Architecture
• Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
• Deep Convolutional Networks on Graph-Structured Data
• Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
• Review of Visual Saliency Detection with Comprehensive Information
• Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images
• Nested Network with Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images
• DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection
• ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features
• VSSA-NET: Vertical Spatial Sequence Attention Network for Traffic Sign Detection
• Co-saliency Detection for RGBD Images Based on Multi-constraint Feature Matching and Cross Label Propagation
• A Parallel Down-Up Fusion Network for Salient Object Detection in Optical Remote Sensing Images
• CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection