Unsupervised domain adaptation (UDA) is an important solution to reduce the bias between the labeled source domain and the unlabeled target domain. It has attracted more attention for optical remote sensing image scene classification and retrieval. Currently, most of the previous work is devoted to closed-set UDA. In fact, the target domain often contains unknown classes. Moreover, some open UDA methods mine structural information of the target domain directly from the type knowledge of the source domain, and less directly from the unlabeled data of the target domain. In this paper, we propose a new self-supervised-driven open-set UDA method combining contrastive self-supervised learning with consistency self-training for optical remote sensing scene classification and retrieval. Specifically, a contrastive self-supervised learning network is introduced to learn discriminative features from the unlabeled target domain data. Moreover, a novel open-set class learning module is developed based on two-level confidence rules and the consistency self-training strategy, which can obtain reliable unknown class samples for co-training. Finally, an open-set dataset including six cross-domain scenarios is constructed based on three public datasets and several experiments are conducted with eleven state-of-the-art domain adaptation methods. Experimental results demonstrate that our proposed method achieves superior performances on the six open-set cross-domain scenarios in both scene classification and retrieval. Especially, our method improves the overall classification accuracies by 9.72% to 24.06% and improve mean average retrieval precisions by 8.06% to 16.21% on the complex UCMD (source domain) → NWPU (target domain) scenario, compared with the other eleven state-of-the-art methods.

Change detection (CD) is one of the most important research areas in remote sensing. With the fast development of imaging techniques, CD using cross-domain remote sensing images (CDCD) has attracted extensive attention from the community. However, CDCD is quite challenging because of the different properties of the cross-domain remote sensing images (collected from different sensors or under different imaging conditions), which triggers difference in physical quantity, noise effect, illumination, seasonal conditions, geometric and visual appearance. In the past decades, although many attempts have been devoted to the above challenges,a review of CDCD is still lacking. To bridge this gap, this paper provides a systematic review on CDCD, with emphasis on image preprocessing (i.e., geometric registration et al.), feature representation (i.e., conventional methods and deep learning-based methods),and change detectors (i.e., similarity-based detector and joint feature-loss detector). Moreover, extensive experiments have also been conducted to compare the performance of 17 widely utilized CDCD methods. Based on this comparison, directions for future developments of CDCD, which include large-scale CDCD datasets, foundation models, and specialized models, are also discussed.

Recent advances in deep learning have dramatically improved the performance of content-based remote sensing image retrieval (CBRSIR) with the same distribution of training set (source domain) and test set (target domain). In fact, their distributions are inconsistent in most cases, which can lead to a dramatic decrease in retrieval performance. Currently, some unsupervised domain adaptation (DA) methods for other remote sensing applications have been proposed to eliminate the inconsistency. However, the current unsupervised DA methods do not make full use of the target domain’s distribution characteristics when delineating its decision boundary. This tends to degrade the cross-domain retrieval performance. In this paper, a pseudo-label consistency learning-based unsupervised DA method (PCLUDA) is proposed for cross-domain CBRSIR. Our PCLUDA method minimizes the difference in probability distribution between the target domain and its perturbed output by a pseudo-label self-training and consistency regularization strategy, followed by adjusting the target domain’s decision boundaries to the low-density region. Besides, minimize class confusion is introduced to reduce negative transfer caused by large intra-class variance of remote sensing images. Two cross-domain datasets with twelve cross-domain scenarios are constructed based on six open access datasets to measure DA methods. Experimental results show that our PCLUDA method achieves superior retrieval performances with average retrieval precision improvement by 4.9%-32.3% compared with eight state-of-the-art DA approaches in complex cross-domain scenarios. Furthermore, other experimental results indicate that our PCLUDA can also reach optimal retrieval performances in different kinds of deep learning networks (i.e., vision transformer and convolutional neural networks).

Benchmark datasets play an important role in evaluating remote sensing image retrieval (RSIR) methods. At present, several small-scale benchmark datasets for RSIR are publicly available on the web and are mostly collected through the Google Map API or other desktop tools. Because the Google Map API requires the users to have programming skills and other collection tools are not publicly available, this may limit the possibility for a wide range of volunteers to participate in generating large-scale benchmark datasets. To address this challenge, we develop an open access web-based tool V-RSIR that allows volunteers to easily participate in generating new benchmark datasets for RSIR. This web-based tool not only facilitates the remote sensing image label and cropping, but also provides image editing, review, quantity statistics, spatial distribution, sharing and so on. To validate this tool, we recruit 32 volunteers to label and crop remote sensing images by using the tool. Finally, a new benchmark dataset that contains 38 classes with at least 1500 images per class is created. Then, the new dataset is validated by five handcrafted low-level feature methods and four deep learning high-level feature methods. The experimental results show that the handcrafted low-level feature methods performs worse than the deep learning methods, in which the precision at top 5 can achieve 94%. The evaluation results are consistent with our theoretical understanding and experimental results on the PatternNet dataset. This indicates that our web-based tool can help users generating valid benchmark datasets with volunteers for RSIR.

Social networking and network socialization provide abundant text information and social relationships into our daily lives. Making full use of these data in the big data era is of great significance for us to better understand the changing world and the information-based society. Though politics have been integrally involved in the hyperlinked world issues since the 1990s, the text analysis and data visualization of geo-events faced the bottleneck of traditional manual analysis. Though automatic assembly of different geospatial web and distributed geospatial information systems utilizing service chaining have been explored and built recently, the data mining and information collection are not comprehensive enough because of the sensibility, complexity, relativity, timeliness, and unexpected characteristics of political events. Based on the framework of Heritrix and the analysis of web-based text, word frequency, sentiment tendency, and dissemination path of the Huangyan Island incident were studied by using web crawler technology and the text analysis. The results indicate that tag cloud, frequency map, attitudes pie, individual mention ratios, and dissemination flow graph, based on the crawled information and data processing not only highlight the characteristics of geo-event itself, but also implicate many interesting phenomenon and deep-seated problems behind it, such as related topics, theme vocabularies, subject contents, hot countries, event bodies, opinion leaders, high-frequency vocabularies, information sources, semantic structure, propagation paths, distribution of different attitudes, and regional difference of net citizens’ response in the Huangyan Island incident. Furthermore, the text analysis of network information with the help of focused web crawler is able to express the time-space relationship of crawled information and the information characteristic of semantic network to the geo-events. Therefore, it is a useful tool to collect information for understanding the formation and diffusion of web-based public opinions in political events.

The discriminative ability of image features plays a decisive role in content-based remote sensing image retrieval (CBRSIR). However, the widely-used convolutional neural networks cannot focus on the discriminative features of important scenes, resulting in unsatisfactory retrieval performance in complex contexts. In this article, an attention-enhanced end-to-end discriminative network with multiscale learning for CBRSIR is proposed to solve this issue. First, a multiscale dilated convolution module is embedded into some of ResNet50’s residual blocks to increase the perceptual field and capture the multiscale features of remote sensing image scenes. Then, a lightweight and efficient triplet attention module is added behind each residual block to capture the salient features of remote sensing images and establish the interdimensional dependencies using residual transform. In addition, the end-to-end training approach is performed using an online label smoothing loss to reduce the intraclass variance of features and enhance interclass differentiability. Experimental results on four publicly available remote sensing image datasets show that our network achieves state-of-the-art or competitive performance, especially on complex scene dataset UCMD with an average retrieval precision improvement of 3.23% to 29.35% compared to other new methods.