Unsupervised Deep Feature Extraction for Remote Sensing Image Classification

Abstract

This paper introduces the use of single layer and deep convolutional networks for remote sensing data analysis. Direct application to multi- and hyper-spectral imagery of supervised (shallow or deep) convolutional networks is very challenging given the high input data dimensionality and the relatively small amount of available labeled data. Therefore, we propose the use of greedy layer-wise unsupervised pre-training coupled with a highly efficient algorithm for unsupervised learning of sparse features. The algorithm is rooted on sparse representations and enforces both population and lifetime sparsity of the extracted features, simultaneously. We successfully illustrate the expressive power of the extracted representations in several scenarios: classification of aerial scenes, as well as land-use classification in very high resolution (VHR), or land-cover classification from multi- and hyper-spectral images. The proposed algorithm clearly outperforms standard Principal Component Analysis (PCA) and its kernel counterpart (kPCA), as well as current state-of-the-art algorithms of aerial classification, while being extremely computationally efficient at learning representations of data. Results show that single layer convolutional networks can extract powerful discriminative features only when the receptive field accounts for neighboring pixels, and are preferred when the classification requires high resolution and detailed results. However, deep architectures significantly outperform single layers variants, capturing increasing levels of abstraction and complexity throughout the feature hierarchy.

References in corpus (3)

• Improving neural networks by preventing co-adaptation of feature detectors
• No More Pesky Learning Rates
• Iterative Gaussianization: from ICA to Random Rotations

Cited by in corpus (48)

• Deep learning in remote sensing: a review
• Remote Sensing Image Scene Classification: Benchmark and State of the Art
• Deep Learning for Hyperspectral Image Classification: An Overview
• Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities
• Three dimensional Deep Learning approach for remote sensing image classification
• Deep Learning for Classification of Hyperspectral Data: A Comparative Review
• A Comprehensive Survey of Deep Learning in Remote Sensing: Theories, Tools and Challenges for the Community
• PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval
• Dense semantic labeling of sub-decimeter resolution images with convolutional neural networks
• Building Instance Classification Using Street View Images
• Binary Patterns Encoded Convolutional Neural Networks for Texture Recognition and Remote Sensing Scene Classification
• Image Forgery Localization Based on Multi-Scale Convolutional Neural Networks
• Convolutional Neural Networks for Global Human Settlements Mapping from Sentinel-2 Satellite Imagery
• Machine learning based hyperspectral image analysis: A survey
• Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works
• Unsupervised Feature Learning by Autoencoder and Prototypical Contrastive Learning for Hyperspectral Classification
• Infrastructure Quality Assessment in Africa using Satellite Imagery and Deep Learning
• Convolutional Neural Networks for Multispectral Image Cloud Masking
• Self-supervised Audiovisual Representation Learning for Remote Sensing Data
• A CNN-based Spatial Feature Fusion Algorithm for Hyperspectral Imagery Classification
• Convolutional Sparse Kernel Network for Unsupervised Medical Image Analysis
• Selection of contributing factors for predicting landslide susceptibility using machine learning and deep learning models
• Non-convex regularization in remote sensing
• A General Destriping Framework for Remote Sensing Images Using Flatness Constraint
• Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scale
• Unsupervised ore/waste classification on open-cut mine faces using close-range hyperspectral data
• LULC classification methodology based on simple Convolutional Neural Network to map complex urban forms at finer scale: Evidence from Mumbai
• A scalable saliency-based Feature selection method with instance level information
• A generic self-supervised learning (SSL) framework for representation learning from spectra-spatial feature of unlabeled remote sensing imagery
• Active Reward Learning for Co-Robotic Vision Based Exploration in Bandwidth Limited Environments
• Land Use and Land Cover Classification Using Deep Learning Techniques
• A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery
• Advances in Deep Learning for Hyperspectral Image Analysis--Addressing Challenges Arising in Practical Imaging Scenarios
• On Creating Benchmark Dataset for Aerial Image Interpretation: Reviews, Guidances and Million-AID
• Perceptual Visual Interactive Learning
• Airplane Detection Based on Mask Region Convolution Neural Network
• Detailed Investigation of Deep Features with Sparse Representation and Dimensionality Reduction in CBIR: A Comparative Study
• Using Wavelets and Spectral Methods to Study Patterns in Image-Classification Datasets
• Land Cover Mapping in Limited Labels Scenario: A Survey
• Deep Clustering With Intra-class Distance Constraint for Hyperspectral Images
• Active Deep Learning for Classification of Hyperspectral Images
• An End-to-End Joint Unsupervised Learning of Deep Model and Pseudo-Classes for Remote Sensing Scene Representation
• Label Consistent Transform Learning for Hyperspectral Image Classification
• Row-Sparse Discriminative Deep Dictionary Learning for Hyperspectral Image Classification
• Discriminative Robust Deep Dictionary Learning for Hyperspectral Image Classification
• Deep Blind Compressed Sensing
• Online Sensor Hallucination via Knowledge Distillation for Multimodal Image Classification
• Handcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends