Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images

Abstract

Despite the remarkable advances in visual saliency analysis for natural scene images (NSIs), salient object detection (SOD) for optical remote sensing images (RSIs) still remains an open and challenging problem. In this paper, we propose an end-to-end Dense Attention Fluid Network (DAFNet) for SOD in optical RSIs. A Global Context-aware Attention (GCA) module is proposed to adaptively capture long-range semantic context relationships, and is further embedded in a Dense Attention Fluid (DAF) structure that enables shallow attention cues flow into deep layers to guide the generation of high-level feature attention maps. Specifically, the GCA module is composed of two key components, where the global feature aggregation module achieves mutual reinforcement of salient feature embeddings from any two spatial locations, and the cascaded pyramid attention module tackles the scale variation issue by building up a cascaded pyramid framework to progressively refine the attention map in a coarse-to-fine manner. In addition, we construct a new and challenging optical RSI dataset for SOD that contains 2,000 images with pixel-wise saliency annotations, which is currently the largest publicly available benchmark. Extensive experiments demonstrate that our proposed DAFNet significantly outperforms the existing state-of-the-art SOD competitors. https://github.com/rmcong/DAFNet_TIP20

Accepted by IEEE Transactions on Image Processing, EORSSD dataset: https://github.com/rmcong/EORSSD-dataset

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Res2Net: A New Multi-scale Backbone Architecture
• Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
• Deeply supervised salient object detection with short connections
• Salient Object Detection: A Survey
• Review of Visual Saliency Detection with Comprehensive Information
• Nested Network with Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images
• 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
• Video Salient Object Detection Using Spatiotemporal Deep Features
• Salient Object Detection in the Deep Learning Era: An In-Depth Survey
• CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection

Cited by in corpus (19)

• SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection
• EDN: Salient Object Detection via Extremely-Downsampled Network
• A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection
• Lightweight Salient Object Detection in Optical Remote Sensing Images via Feature Correlation
• Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment
• Salient Object Detection in Optical Remote Sensing Images Driven by Transformer
• Multi-Content Complementation Network for Salient Object Detection in Optical Remote Sensing Images
• Position-Aware Relation Learning for RGB-Thermal Salient Object Detection
• Salient Objects in Clutter
• Texture-Semantic Collaboration Network for ORSI Salient Object Detection
• Boundary-semantic collaborative guidance network with dual-stream feedback mechanism for salient object detection in optical remote sensing imagery
• An End-to-End Network for Co-Saliency Detection in One Single Image
• Hyperspectral Remote Sensing Images Salient Object Detection: The First Benchmark Dataset and Baseline
• ASOD60K: An Audio-Induced Salient Object Detection Dataset for Panoramic Videos
• Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection
• RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images
• Progressive Self-Guided Loss for Salient Object Detection
• Geographical Knowledge-driven Representation Learning for Remote Sensing Images
• Superpixel Segmentation Based on Spatially Constrained Subspace Clustering