Deep learning (DL) has been widely recognized for its strong feature representation capability, making it a promising technique to improve pansharpening methods. However, existing DL-based methods commonly extract the spectral information and spatial information from the high-resolution panchromatic (PAN) images and low-resolution multispectral (MS) images, respectively. This separation limits the effective extraction and integration of potential spectral-spatial information, ultimately reducing the quality of the generated high-resolution multispectral (HRMS) images. In this paper, we propose a novel spatialspectral dual guided network (SSDGN), aiming to fully capitalize on the spectral and spatial information contained in both the PAN and MS images. Firstly, to enhance feature extraction, we introduce two subnetworks: the progressive spectral feature extraction (PSpeFE) subnetwork and progressive spatial feature extraction (PSpaFE) for spatial features. These extract information from the PAN and MS images. Additionally, features from the frequency domain (FD) and intensity domain (ID) of both image types are leveraged to guide and enhance the efficiency of feature extraction. Then, a joint spatial-spectral attention feature fusion module and a multi-stage residual reconstruction module are devised to efficiently harness the extracted spatial and spectral information. Finally, extensive experiments are conducted to evaluate the performance and effectiveness of the proposed SSDGN. Compared to the second-best methods, our approach achieves an average reduction of 12.3% in ERGAS across three satellite datasets. The QNR metric improves by up to 2.1% and averages a 0.8% gain, demonstrating consistent advantages in spectral fidelity and fusion quality.

Deep learning methods have achieved outstanding performance in various signal tasks. However, due to degraded signals in real electromagnetic environment, it is crucial to seek methods that can improve the representation of signal features. In this paper, a Singular Value decomposition-based Attention, SVA is proposed to explore structure of signal data for adaptively enhancing intrinsic feature. Using a deep neural network as a base model, SVA performs feature semantic subspace learning through a decomposition layer and combines it with an attention layer to achieve adaptive enhancement of signal features. Moreover, we consider the gradient explosion problem brought by SVA and optimize SVA to improve the stability of training. Extensive experimental results demon-strate that applying SVA to a generalized classification model can significantly improve its ability in representations, making its recognition performance competitive with, or even better than, the state-of-the-art task-specific models.

Heterogeneous object-level change detection (CD) aims to detect the state of the objects and whether they have changed from multitemporal multimodal data. In this article, a new cross-modality interactive change detector (CICD) is proposed for object-level CD from multitemporal optical and synthetic aperture radar (SAR) images. The CICD consists of a backbone, cross-modal interactive module (CIM), neck, and head. CIM is designed to work with features extracted from modalities by the backbone network, enabling it to identify more changes in objects. Moreover, to address data imbalances in change categories caused by variations in satellite revisit cycles and aircraft flight plans, we introduce a heterogeneous class balanced module (HCBM). An eliminate adversarial network (EAN) is constructed as the main component of the HCBM. It is used to eliminate objects to augment images in which objects appear in only one temporal instant, thus reducing imbalances in the dataset. Extensive experiments are conducted on the multimodal object-level change dataset (MOCD), and the results show that CICD can achieve state-of-the-art performance.

In this paper, an Adaptive Fusion Transformer (AFT) is proposed for unsupervised pixel-level fusion of visible and infrared images. Different from the existing convolutional networks, transformer is adopted to model the relationship of multi-modality images and explore cross-modal interactions in AFT. The encoder of AFT uses a Multi-Head Self-attention (MSA) module and Feed Forward (FF) network for feature extraction. Then, a Multi-head Self-Fusion (MSF) module is designed for the adaptive perceptual fusion of the features. By sequentially stacking the MSF, MSA, and FF, a fusion decoder is constructed to gradually locate complementary features for recovering informative images. In addition, a structure-preserving loss is defined to enhance the visual quality of fused images. Extensive experiments are conducted on several datasets to compare our proposed AFT method with 21 popular approaches. The results show that AFT has state-of-the-art performance in both quantitative metrics and visual perception.

Autofocus plays a key role in synthetic aperture radar (SAR) imaging, especially for high-resolution imaging. In the literature, the minimum-entropy-based algorithms (MEA) have been proved to be robust and have been widely applied in SAR. However, this kind of method needs hundreds of iterations and is computationally expensive. In this paper, we proposed a non-iterative autofocus scheme based on deep learning and minimum-entropy criterion. It’s an unsupervised framework, which utilizes entropy as the loss function. In this scheme, deep neural networks are utilized for feature extraction and parameter estimation. Based on this scheme, two autofocus models (autofocus network and progressive autofocus network) are proposed. After training, the network learned the rules of autofocus from a large number of examples. Experimental results on real SAR data show that the proposed methods have focusing quality close to the state-of-the-art but with real-time focusing speed.