Journal ArticleDOI
Artificial Intelligence for Remote Sensing Data Analysis: A review of challenges and opportunities
Lefei Zhang,Liangpei Zhang +1 more
TLDR
This work aims to provide a comprehensive review of the recent achievements of AI algorithms and applications in RS data analysis, covering the following major aspects of AI innovation for RS: machine learning, computational intelligence, AI explicability, data mining, natural language processing (NLP), and AI security.Abstract:
Artificial intelligence (AI) plays a growing role in remote sensing (RS). Applications of AI, particularly machine learning algorithms, range from initial image processing to high-level data understanding and knowledge discovery. AI techniques have emerged as a powerful strategy for analyzing RS data and led to remarkable breakthroughs in all RS fields. Given this period of breathtaking evolution, this work aims to provide a comprehensive review of the recent achievements of AI algorithms and applications in RS data analysis. The review includes more than 270 research papers, covering the following major aspects of AI innovation for RS: machine learning, computational intelligence, AI explicability, data mining, natural language processing (NLP), and AI security. We conclude this review by identifying promising directions for future research.read more
Citations
More filters
Journal ArticleDOI
Rotation-Invariant Attention Network for Hyperspectral Image Classification
TL;DR: Wang et al. as mentioned in this paper proposed a rotation-invariant attention network (RIAN) for hyperspectral image (HSI) classification, where a center spectral attention (CSpeA) module is designed to avoid the influence of other categories of pixels to suppress redundant spectral bands.
Journal ArticleDOI
EMTCAL: Efficient Multiscale Transformer and Cross-Level Attention Learning for Remote Sensing Scene Classification
TL;DR: A new model named efficient multiscale transformer and cross-level attention learning (EMTCAL) for RS scene classification in this article, which can achieve superior classification performance and outperform many state-of-the-art methods.
Journal ArticleDOI
Exploring Nonlocal Group Sparsity Under Transform Learning for Hyperspectral Image Denoising
TL;DR: A nonlocal group sparsifying transform learning (dubbed TLNLGS) method for HSI denoising motivated by the global spectral correlation in the HSI is proposed, which can improve the sparse representation ability of the image.
Journal ArticleDOI
Spectral–Spatial Feature Extraction With Dual Graph Autoencoder for Hyperspectral Image Clustering
TL;DR: Zhang et al. as discussed by the authors proposed a dual graph autoencoder (DGAE) to learn discriminative representations for hyperspectral image (HSI) analysis.
Journal ArticleDOI
Context-Aware Guided Attention Based Cross-Feedback Dense Network for Hyperspectral Image Super-Resolution
TL;DR: A two-branch cross-feedback dense network with context-aware guided attention (CFDcagaNet) for HS super-resolution (HSSR) for high-dimensional hyperspectral (HS) images outperforms state-of-the-art methods in terms of both quantitative values and visual qualities.
References
More filters
Journal ArticleDOI
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Journal ArticleDOI
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
Journal ArticleDOI
Learning representations by back-propagating errors
TL;DR: Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.
Journal ArticleDOI
A fast learning algorithm for deep belief nets
TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
Proceedings ArticleDOI
Learning Transferable Architectures for Scalable Image Recognition
TL;DR: NASNet as discussed by the authors proposes to search for an architectural building block on a small dataset and then transfer the block to a larger dataset, which enables transferability and achieves state-of-the-art performance.