Survey on Remote Sensing Scene Classification: From Traditional Methods to Large Generative AI Models

2026-03-23

AI Summary

This study addresses key challenges in remote sensing scene classification, including high annotation costs, complex multimodal fusion, limited cross-domain generalization, and insufficient interpretability. It systematically reviews the technical evolution of the field—from traditional handcrafted features through deep learning, Vision Transformers, and graph neural networks, to emerging self-supervised foundation models and generative AI. Notably, this work provides the first comprehensive synthesis of generative AI applications in remote sensing, emphasizing zero-shot and few-shot learning, synthetic data generation, and sustainable AI practices. The paper clarifies the developmental trajectory, identifies critical bottlenecks, and proposes future research directions such as standardized evaluation protocols and enhanced cross-domain generalization, thereby offering a structured reference framework and prioritized pathways for subsequent studies.

Abstract

Remote sensing scene classification has experienced a paradigmatic transformation from traditional handcrafted feature methods to sophisticated artificial intelligence systems that now form the backbone of modern Earth observation applications. This comprehensive survey examines the complete methodological evolution, systematically tracing development from classical texture descriptors and machine learning classifiers through the deep learning revolution to current state-of-the-art foundation models and generative AI approaches. We chronicle the pivotal shift from manual feature engineering to automated hierarchical representation learning via convolutional neural networks, followed by advanced architectures including Vision Transformers, graph neural networks, and hybrid frameworks. The survey provides in-depth coverage of breakthrough developments in self-supervised foundation models and vision-language systems, highlighting exceptional performance in zero-shot and few-shot learning scenarios. Special emphasis is placed on generative AI innovations that tackle persistent challenges through synthetic data generation and advanced feature learning strategies. We analyze contemporary obstacles including annotation costs, multimodal data fusion complexities, interpretability demands, and ethical considerations, alongside current trends in edge computing deployment, federated learning frameworks, and sustainable AI practices. Based on comprehensive analysis of recent advances and gaps, we identify key future research priorities: advancing hyperspectral and multi-temporal analysis capabilities, developing robust cross-domain generalization methods, and establishing standardized evaluation protocols to accelerate scientific progress in remote sensing scene classification systems.

Problem

• remote sensing scene classification
• annotation costs
• multimodal data fusion
• cross-domain generalization
• standardized evaluation protocols

Innovation

• Generative AI
• Foundation Models
• Self-supervised Learning
• Vision-Language Systems
• Synthetic Data Generation