Building-change detection underpins many important applications, especially in the military and crisis-management domains. Recent methods used for change detection have shifted towards deep learning, which depends on the quality of its training data. The assembly of large-scale annotated satellite imagery datasets is therefore essential for global building-change surveillance. Existing datasets almost exclusively offer near-nadir viewing angles. This limits the range of changes that can be detected. By offering larger observation ranges, the scroll imaging mode of optical satellites presents an opportunity to overcome this restriction. This paper therefore introduces S2Looking, a building-change-detection dataset that contains large-scale side-looking satellite images captured at various off-nadir angles. The dataset consists of 5000 bitemporal image pairs of rural areas and more than 65,920 annotated instances of changes throughout the world. The dataset can be used to train deep-learning-based change-detection algorithms. It expands upon existing datasets by providing (1) larger viewing angles; (2) large illumination variances; and (3) the added complexity of rural images. To facilitate the use of the dataset, a benchmark task has been established, and preliminary tests suggest that deep-learning algorithms find the dataset significantly more challenging than the closest-competing near-nadir dataset, LEVIR-CD+. S2Looking may therefore promote important advances in existing building-change-detection algorithms.

Built-up areas and buildings are two main targets in remote sensing research; consequently, automatic extraction of built-up areas and buildings has attracted extensive attention. This task is usually difficult because of boundary blur, object occlusion, and intra-class inconsistency. In this paper, we propose the multi-attention feature fusion HRNet, MAFF-HRNet, which can retain more detailed features to achieve accurate semantic segmentation. The design of a pyramidal feature attention (PFA) hierarchy enhances the multilevel semantic representation of the model. In addition, we develop a mixed convolutional attention (MCA) block, which increases the capture range of receptive fields and overcomes the problem of intra-class inconsistency. To alleviate interference due to occlusion, a multiscale attention feature aggregation (MAFA) block is also proposed to enhance the restoration of the final prediction map. Our approach was systematically tested on the WHU (Wuhan University) Building Dataset and the Massachusetts Buildings Dataset. Compared with other advanced semantic segmentation models, our model achieved the best IoU results of 91.69% and 68.32%, respectively. To further evaluate the application significance of the proposed model, we migrated a pretrained model based on the World-Cover Dataset training to the Gaofen 16 m dataset for testing. Quantitative and qualitative experiments show that our model can accurately segment buildings and built-up areas from remote sensing images.

Remote sensing change detection involves detecting pixels that have changed from a bi-temporal image of the same location. Current mainstream change detection models use encoder-decoder structures as well as Siamese networks. However, there are still some challenges with this: (1) Existing change feature fusion approaches do not take into account the symmetry of change features, which leads to information loss; (2) The encoder is independent of the change detection task, and feature extraction is performed separately for dual-time images, which leads to underutilization of the encoder parameters; (3) There are problems of unbalanced positive and negative samples and bad edge region detection. To solve the above problems, a mutual feature-aware network (MFNet) is proposed in this paper. Three modules are proposed for the purpose: (1) A symmetric change feature fusion module (SCFM), which uses double-branch feature selection without losing feature information and focuses explicitly on focal spatial regions based on cosine similarity to introduce strong a priori information; (2) A mutual feature-aware module (MFAM), which introduces change features in advance at the encoder stage and uses a cross-type attention mechanism for long-range dependence modeling; (3) A loss function for edge regions. After detailed experiments, the F1 scores of MFNet on SYSU-CD and LEVIR-CD were 83.11% and 91.52%, respectively, outperforming several advanced algorithms, demonstrating the effectiveness of the proposed method.

Few-shot learning enables rapid generalization from extremely limited training examples. While previous efforts have utilized meta-learning or data augmentation methods to mitigate the problem of data scarcity, such approaches may struggle to maintain robustness and generalize effectively due to overfitting and noise sensitivity. In this article, we propose a novel approach, the semi-supervised label correction method for few-shot learning (SSLC-FSL), which leverages the data distribution of readily available and easily obtainable unlabeled data. SSLC-FSL iteratively corrects the labels of testing samples with alternating steps of pseudo-labeling and sample selection. The objective of pseudo-labeling is to repurpose graph-based semi-supervised learning for joint prediction of the entire testing set. We then introduce a modulation selection network (MSN) to rank testing samples by learning with noisy labels. The training set is expanded by selecting confident pseudo-labeled samples. In the MSN, a modulation aggregation layer is designed to encode support class information into each testing sample, thereby highlighting target category features and mitigating the negative impact of incorrect labels. The iterative label correction process is repeated until all testing samples are recalled to the expanded support set. To boost the SSLC-FSL algorithm, we pretrain a feature extractor to produce general-purpose representations. Particularly, we investigate two types of auxiliary tasks and their collaborative learning to acquire transferable visual information via an end-to-end multitask learning model. Our SSLC-FSL outperforms current state-of-the-art methods in any shot and all data settings, with up to +27.74% on standard remote sensing benchmarks and +5.70% on standard natural scene benchmarks.

Remote sensing image (RSI) analysis heavily relies on change detection (CD) to identify differences between bitemporal images. Although significant progress has been made in CD methods, it remains challenging to distinguish between pseudo-changes caused by imaging angles, weather conditions, seasonal variations, etc. This is because most existing networks cannot fully utilize multi-scale features to narrow the semantic gap between cross-scale features. To address this issue, we propose a cascade cross-scale network (CCSNet) with a Siamese structure for CD in RSIs. Our CCSNet uses cascade Siamese encoders to extract multi-scale bitemporal features. These extracted features are then fused using the proposed Diff-Conc combination at the encoding stage. Cross-scale skip connections are used to continuously transmit shallow features to the decoders, in which a cross-scale attention module is designed to fuse shallow and deep features. This network structure effectively bridges the semantic gap between cross-scale features and helps eliminate pseudo-changes. We evaluated our method on two popular benchmark CD datasets (LEVIR-CD and WHU-CD). The experimental results demonstrate that CCSNet outperforms the state-of-the-art methods.