Litcius/Paper detail

SCAR-Net: A Selective Channel Attention with Residuals Network for High-Resolution Remote Sensing Scene Classification

Ahmed Gomaa, Omar M. Saad

20257 citationsDOI

Abstract

Accurate classification of high-resolution remote sensing images is a critical task in Earth observation, with wide-ranging applications in urban planning. However, challenges such as high intra-class variability, and complex spatial arrangements of small objects within large background regions often hinder traditional convolutional neural networks (CNNs). To address these limitations, we propose a novel Selective Channel Attention Residuals network (SCAR-Net) that integrates lightweight residual blocks with a channel attention mechanism based on squeeze-and-excitation (SE) units. This new architecture enables the network to selectively emphasize discriminative feature channels while maintaining robust multi-scale spatial feature extraction. By recalibrating channel-wise responses and leveraging residual learning, the proposed SCAR network effectively suppresses irrelevant background information and enhances class-specific features. The proposed SCAR network was evaluated on three widely used remote sensing datasets, and consistently outperformed several advanced CNN-based models. Furthermore, Grad-CAM++ visualizations confirm that SCAR accurately focuses on semantically meaningful regions in the images.

Topics & Concepts

Discriminative modelComputer scienceFeature (linguistics)Channel (broadcasting)ResidualConvolutional neural networkRemote sensingArtificial intelligenceTask (project management)Pattern recognition (psychology)Spatial analysisFeature extractionFeature learningAttention networkData miningEarth observationKey (lock)Representation (politics)Deep learningTask analysisNetwork architectureComputer visionArtificial neural networkRemote sensing applicationMachine learningRemote-Sensing Image ClassificationAdvanced Neural Network ApplicationsAutomated Road and Building Extraction