Semantic change detection (SCD) has gradually emerged as a prominent research focus in remote sensing image processing due to its critical role in earth observation applications. In view of its powerful semantic-driven feature extraction capability, the Segment Anything Model (SAM) has demonstrated its suitability across various visual scenes. However, it suffers from significant performance degradation when confronted with remote sensing images, especially those containing various ground objects that possess significant inter-class similarity and substantial intra-class variations. To address the above issues, we propose SCD-SAM, aiming to leverage the potent visual recognition capabilities of SAM for enhanced accuracy and robustness in SCD. Specifically, we introduce a contextual semantic change-aware dual encoder that combines MobileSAM and CNN to extract progressive semantic change features in parallel, and inject local features into the MobileSAM encoder through depth feature interaction to compensate for the Transformer’s limitations in perceiving local semantic details. Besides, in order to utilize the strong visual feature extraction capability of MobileSAM in remote sensing images, we propose a semantic adaptor that aggregates semantic-oriented information about changing objects. To better integrate the extracted contextual semantic information, we devise a progressive feature aggregation dual decoder that aggregates binary change features and semantic change features respectively, alleviating the semantic gap across different scales. The quantitative and visual results show that SCD-SAM outperforms the state-of-the-art SCD methods on publicly open SCD datasets (e.g., SECOND-CD and Landsat-CD). The code will be made available at https://github.com/yzygit1230/SCD-SAM.

Small object detection in aerial imagery remains challenging due to sparse feature representation, limited spatial resolution, and complex background interference. Current deep learning approaches enhance detection performance through multi-scale feature fusion, leveraging convolutional operations to expand the receptive field or self-attention mechanisms for global context modeling. However, these methods primarily rely on spatial-domain features, while self-attention introduces high computational costs, and conventional fusion strategies (e.g., concatenation or addition) often result in weak feature correlation or boundary misalignment. To address these challenges, we propose a unified spatial-frequency modeling and multi-scale alignment fusion framework, termed USF-DETR, for small object detection. The framework comprises three key modules: the Spatial-Frequency Interaction Backbone (SFIB), the Dual Alignment and Balance Fusion FPN (DABF-FPN), and the Efficient Attention-AIFI (EA-AIFI). The SFIB integrates the Scharr operator for spatial edge and detail extraction and FFT/IFFT for capturing frequency-domain patterns, achieving a balanced fusion of global semantics and local details. The DABF-FPN employs bidirectional geometric alignment and adaptive attention to enhance the significance expression of the target area, suppress background noise, and improve feature asymmetry across scales. The EA-AIFI streamlines the Transformer attention mechanism by removing key-value interactions and encoding query relationships via linear projections, significantly boosting inference speed and contextual modeling. Experiments on the VisDrone and TinyPerson datasets demonstrate the effectiveness of USF-DETR, achieving improvements of 2.3% and 1.4% mAP over baselines, respectively, while balancing accuracy and computational efficiency. The framework outperforms state-of-the-art methods in small object detection.

Change detection (CD) signifies a pivotal domain within remote sensing image processing. The transformer has been introduced in the field of CD for its global perception capabilities. However, existing transformer-based methodologies serve primarily as mere direct feature extractors, rendering the attention mechanism within the decoder underutilized. To address this, we propose a symmetric transformer learning network (STLNet) specifically tailored for remote sensing image CD tasks, constructed entirely using transformers. STLNet is designed to leverage the intrinsic capability of transformers to model extensive long-range dependencies effectively. This approach significantly bolsters the extraction of distinctive globallevel features, thereby facilitating the accurate delineation of CD regions. Initially, we utilize an adaptive multigrain encoder to extract feature information from bitemporal images, thereby honing the focus on changing targets and providing deeper and more comprehensive information. Subsequently, we adopt an effective decoder architecture comprised of transformer structures, namely the local gather decoder (LGD). The LGD employs a multi-level semantic feature integration from the encoder to augment feature representation and inter dependencies, crucial for detailing small changed areas effectively via a hierarchical attentional fusion (HAF) block. Ultimately, the detection of changes is based on the rich semantic information provided by the LGD, enabling us to achieve enhanced precision in our remote sensing CD efforts. Results show that the proposed STLNet achieved F1 scores of 92.32% on LEVIR-CD, 90.01% on WHU-CD, and 82.15% on SYSU-CD, surpassing mainstream CD methods.

Fusing infrared and visible images taken by an unmanned aerial vehicle (UAV) is a challenging task, since infrared images distinguish the target from the background by the difference in infrared radiation, while the low resolution also produces a less pronounced effect. Conversely, the visible light spectrum has a high spatial resolution and rich texture; however, it is easily affected by harsh weather conditions like low light. Therefore, the fusion of infrared and visible light has the potential to provide complementary advantages. In this paper, we propose a multi-scale dense feature-aware network via integrated attention for infrared and visible image fusion, namely DFA-Net. Firstly, we construct a dual-channel encoder to extract the deep features of infrared and visible images. Secondly, we adopt a nested decoder to adequately integrate the features of various scales of the encoder so as to realize the multi-scale feature representation of visible image detail texture and infrared image salient target. Then, we present a feature-aware network via integrated attention to further fuse the feature information of different scales, which can focus on specific advantage features of infrared and visible images. Finally, we use unsupervised gradient estimation and intensity loss to learn significant fusion features of infrared and visible images. In addition, our proposed DFA-Net approach addresses the challenges of fusing infrared and visible images captured by a UAV. The results show that DFA-Net achieved excellent image fusion performance in nine quantitative evaluation indexes under a low-light environment.

Remote sensing (RS) image change detection (CD) methods based on deep learning, such as convolutional neural networks (CNNs) and transformers, are still spatial domain-based image processing methods by nature, and their detection accuracy is strongly affected by chromatic aberration due to imaging time, shadows caused by lighting conditions, and object confusion and other disturbances. In this study, we revisit CD from a signal processing perspective, framing it as the task of consistency detection of the distributional features of two 2-D signals. We aim to extract the primary components of the two signals while suppressing interfering noises. To address this, we propose a novel CD method called DFNet, which leverages a dual-frequency learnable encoder. First, we construct a dual-frequency feature encoder Siamese framework to capture local high-frequency signals and global low-frequency signals using CNN and attention mechanisms after dividing the input RS image signals into two channels. Second, we introduce the frequency explicit visual center module as a part of the multifrequency-domain dense interaction (MFDDI) module at the decoder stage, allowing long-distance dependency to be established between high–low frequency components in the same layer as well as signal aggregation in regions of small edge variations. In addition, the MFDDI module adopts a layer-by-layer interactive fusion approach to synthesize discriminative information in a wide frequency-domain range, enhancing the characterization capability of frequency-domain signals. We conduct comparison experiments with the current mainstream methods on the land cover dataset SYSU-CD and two building datasets, LEVIR-CD and WHU-CD, and the results show that our method is not only resistant to interference but also outperforms all the comparison methods.

Salient object detection (SOD) aims to accurately identify significant geographical objects in remote sensing images (RSI), providing reliable support and guidance for extensive geographical information analyses and decisions. However, SOD in RSI faces numerous challenges, including shadow interference, inter-class feature confusion, as well as unclear target edge contours. Therefore, we designed an effective Global Semantic-aware Aggregation Network (GSANet) to aggregate salient information in RSI. GSANet computes the information entropy of different regions, prioritizing areas with high information entropy as potential target regions, thereby achieving precise localization and semantic understanding of salient objects in remote sensing imagery. Specifically, we proposed a Semantic Detail Embedding Module (SDEM), which explores the potential connections among multi-level features, adaptively fusing shallow texture details with deep semantic features, efficiently aggregating the information entropy of salient regions, enhancing information content of salient targets. Additionally, we proposed a Semantic Perception Fusion Module (SPFM) to analyze map relationships between contextual information and local details, enhancing the perceptual capability for salient objects while suppressing irrelevant information entropy, thereby addressing the semantic dilution issue of salient objects during the up-sampling process. The experimental results on two publicly available datasets, ORSSD and EORSSD, demonstrated the outstanding performance of our method. The method achieved 93.91% S_α, 98.36% E_ξ, and 89.37% F_β on the EORSSD dataset.