Land Use Classification in Remote Sensing Images by Convolutional Neural Networks

Abstract

We explore the use of convolutional neural networks for the semantic classification of remote sensing scenes. Two recently proposed architectures, CaffeNet and GoogLeNet, are adopted, with three different learning modalities. Besides conventional training from scratch, we resort to pre-trained networks that are only fine-tuned on the target data, so as to avoid overfitting problems and reduce design time. Experiments on two remote sensing datasets, with markedly different characteristics, testify on the effectiveness and wide applicability of the proposed solution, which guarantees a significant performance improvement over all state-of-the-art references.

References in corpus (3)

• Improving neural networks by preventing co-adaptation of feature detectors
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Return of the Devil in the Details: Delving Deep into Convolutional Nets

Cited by in corpus (31)

• Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities
• Detecting Mammals in UAV Images: Best Practices to address a substantially Imbalanced Dataset with Deep Learning
• Diversity in Machine Learning
• Land cover mapping at very high resolution with rotation equivariant CNNs: towards small yet accurate models
• An Attention-Fused Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Imagery
• Image Forgery Localization Based on Multi-Scale Convolutional Neural Networks
• Understanding urban landuse from the above and ground perspectives: a deep learning, multimodal solution
• Discovering state-parameter mappings in subsurface models using generative adversarial networks
• From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data
• Deep-Learning Convolutional Neural Networks for scattered shrub detection with Google Earth Imagery
• Convolutional Neural Networks for Multispectral Image Cloud Masking
• A global method to identify trees outside of closed-canopy forests with medium-resolution satellite imagery
• In-domain representation learning for remote sensing
• Adversarial Example in Remote Sensing Image Recognition
• Forensic Dental Age Estimation Using Modified Deep Learning Neural Network
• DML-GANR: Deep Metric Learning With Generative Adversarial Network Regularization for High Spatial Resolution Remote Sensing Image Retrieval
• Adaptive Deep Pyramid Matching for Remote Sensing Scene Classification
• Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scale
• Land Use and Land Cover Classification Using Deep Learning Techniques
• Spatio-temporal crop classification of low-resolution satellite imagery with capsule layers and distributed attention
• Monitoring spatial sustainable development: Semi-automated analysis of satellite and aerial images for energy transition and sustainability indicators
• Cross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition
• Fine-Grained Land Use Classification at the City Scale Using Ground-Level Images
• DDIPNet and DDIPNet+: Discriminant Deep Image Prior Networks for Remote Sensing Image Classification
• Deep Discriminative Representation Learning with Attention Map for Scene Classification
• Temporal Interpolation of Geostationary Satellite Imagery with Task Specific Optical Flow
• Geometry-Aware Segmentation of Remote Sensing Images via Implicit Height Estimation
• Satellite Image Classification with Deep Learning
• Land Use Classification Using Multi-neighborhood LBPs
• On the Selective and Invariant Representation of DCNN for High-Resolution Remote Sensing Image Recognition
• Solar Power Plant Detection on Multi-Spectral Satellite Imagery using Weakly-Supervised CNN with Feedback Features and m-PCNN Fusion