The foundation model has recently garnered significant attention due to its potential to revolutionize the field of visual representation learning in a self-supervised manner. While most foundation models are tailored to effectively process RGB images for various visual tasks, there is a noticeable gap in research focused on spectral data, which offers valuable information for scene understanding, especially in remote sensing (RS) applications. To fill this gap, we created for the first time a universal RS foundation model, named SpectralGPT, which is purpose-built to handle spectral RS images using a novel 3D generative pretrained transformer (GPT). Compared to existing foundation models, SpectralGPT 1) accommodates input images with varying sizes, resolutions, time series, and regions in a progressive training fashion, enabling full utilization of extensive RS Big Data; 2) leverages 3D token generation for spatial-spectral coupling; 3) captures spectrally sequential patterns via multi-target reconstruction; 4) trains on one million spectral RS images, yielding models with over 600 million parameters. Our evaluation highlights significant performance improvements with pretrained SpectralGPT models, signifying substantial potential in advancing spectral RS Big Data applications within the field of geoscience across four downstream tasks: single/multi-label scene classification, semantic segmentation, and change detection.

Accurately distinguishing between background and anomalous objects within hyperspectral images poses a significant challenge. The primary obstacle lies in the inadequate modeling of prior knowledge, leading to a performance bottleneck in hyperspectral anomaly detection (HAD). In response to this challenge, we put forth a groundbreaking coupling paradigm that combines model-driven low-rank representation (LRR) methods with data-driven deep learning techniques by learning disentangled priors (LDP). LDP seeks to capture complete priors for effectively modeling the background, thereby extracting anomalies from hyperspectral images more accurately. LDP follows a model-driven deep unfolding architecture, where the prior knowledge is separated into the explicit low-rank prior formulated by expert knowledge and implicit learnable priors by means of deep networks. The internal relationships between explicit and implicit priors within LDP are elegantly modeled through a skip residual connection. Furthermore, we provide a mathematical proof of the convergence of our proposed model. Our experiments, conducted on multiple widely recognized datasets, demonstrate that LDP surpasses most of the current advanced HAD techniques, exceling in both detection performance and generalization capability.

Image fusion can be conducted at different levels, with pixel-level image fusion involving the direct combination of original information from source images. The objective of methods falling under this category is to generate a fused image that enhances both visual perception and subsequent processing tasks. This survey draws upon research findings in pixel-level image fusion for remote sensing, outlining primary research directions, such as image sharpening, multi-modal image fusion, and spatio-temporal image fusion. For each area, state-of-the-art deep learning solutions are deeply reviewed. Furthermore, this survey discusses open issues and potential future directions. It also examines common downstream image fusion tasks to underscore how they can benefit from image fusion techniques to achieve improved performance. This paper aims to extend beyond a conventional survey by not only reviewing existing methodologies but also providing practical insights such as assessment protocols, available datasets for training and testing deep learning models, and guidelines for deep learning remote sensing image fusion. This survey is geared towards students and professionals who want to approach pixel-level image fusion in remote sensing, offering valuable cues and tools for addressing specific challenges. The authors wish this work to contribute to reducing barriers to entry for interested scientists in adjacent research fields and aiding the growth of a new generation of image fusion researchers.

In the last decade, the rapid development of deep learning (DL) has made it possible to perform automatic, accurate, and robust change detection (CD) on large volumes of remote sensing images (RSIs). However, despite advances in CD methods, their practical application in real-world contexts remains limited because of diverse input data and the applicational context. For example, the collected RSIs can be time-series observations, and more informative results are required to indicate the time of change or the specific change category. Moreover, training a deep neural network (DNN) requires a massive amount of training samples, and in many cases these samples are difficult to collect. To address these challenges, various specific CD methods have been developed considering different application scenarios and training resources. Additionally, recent advancements in image generation, self-supervision, and visual foundation models (VFMs) have opened up new approaches to address the ”data-hungry” issue of DL-based CD. The development of these methods in broader application scenarios requires further investigation and discussion. Therefore, this article summarizes the literature methods for different CD tasks and the available strategies and techniques to train and deploy DL-based CD methods in sample-limited scenarios. We expect this survey to be able to provide new insights and inspiration for researchers in this field to develop more effective CD methods that can be applied in a wider range of contexts.