Limited-angle computed tomography (CT) image reconstruction is a challenging problem in the field of CT imaging. In some special applications, limited by the geometric space and mechanical structure of the imaging system, projections can only be collected with a scanning range of less than 90°. We call this kind of serious limited-angle problem the ultra-limited-angle problem, which is difficult to effectively alleviate by traditional iterative reconstruction algorithms. With the development of deep learning, the generative adversarial network (GAN) performs well in image inpainting tasks and can add effective image information to restore missing parts of an image. In this study, given the characteristic of GAN to generate missing information, the sinogram-inpainting-GAN (SI-GAN) is proposed to restore missing sinogram data to suppress the singularity of the truncated sinogram for ultra-limited-angle reconstruction. We propose the U-Net generator and patch-design discriminator in SI-GAN to make the network suitable for standard medical CT images. Furthermore, we propose a joint projection domain and image domain loss function, in which the weighted image domain loss can be added by the back-projection operation. Then, by inputting a paired limited-angle/180° sinogram into the network for training, we can obtain the trained model, which has extracted the continuity feature of sinogram data. Finally, the classic CT reconstruction method is used to reconstruct the images after obtaining the estimated sinograms. The simulation studies and actual data experiments indicate that the proposed method performed well to reduce the serious artifacts caused by ultra-limited-angle scanning.

Visual foundation models exhibit significant potential for extracting generalized characteristics from imagery, which is crucial for remote sensing image interpretation tasks. However, current approaches underutilize these capabilities for hyperspectral image semantic segmentation. To bridge this gap, this study establishes SAM-derived generalized feature fusion with a hierarchical network for hyperspectral image semantic segmentation (SAM-GFNet), which integrates generalized features with hierarchical task-specific spatial–spectral characteristics for the segmentation task. Specifically, hyperspectral images are partitioned into multiple spectral groups, and SAM-induced generalized features are extracted within each group’s corresponding spectral range. To leverage multi-scale contextual information, the hierarchical hyperspectral image semantic segmentation architecture fuses multi-scale spectral–spatial features with SAM-induced generalized visual characteristics through a hierarchical fusion pattern. Furthermore, an efficient feature fusion module is further developed to adaptively integrate encoded features with decoder-generated characteristics, further enhancing semantic segmentation performance. The proposed semantic segmentation scheme is evaluated on WHU-OHS and WHU-H2SR benchmark datasets, achieving overall accuracies of 79.60% and 86.92% on two datasets, surpassing representative baseline methods by over 2.94% and 1.56%, respectively.

Text-guided vision-language detectors provide a natural-language interface for remote sensing (RS) object detection, but their adaptation to RS imagery remains limited by degraded small-object performance and inefficient text-vision alignment. This paper presents a systematic study on adapting GroundingDINO to RS object detection through end-to-end training on DOTA v1.0 (Dataset for Object Detection in Aerial Images). We introduce Lightweight Feature Refinement GroundingDINO (LFR-GDINO), which integrates a lightweight feature-refinement module (v3)—combining Efficient Channel Attention (ECA) with InnerMPDIoU loss—and Remote Sensing Category-Aware Prompt Engineering (RS-CAPE), a concise prompt strategy appending minimal RS-relevant keywords. On DOTA v1.0, LFR-GDINO achieves 0.420 mAP (mean average precision) and 0.695 mAP50, attaining the highest mAP50 among compared methods under the text-guided horizontal bounding box (HBB) protocol. Prompt experiments point to a detection–precision trade-off: verbose prompts improve mAP50 but reduce mAP75, whereas concise 2–3-token prompts achieve the best balance, supported by a training-free Bidirectional Encoder Representations from Transformers (BERT) attention analysis. Transfer experiments on DIOR (Detection in Optical Remote-sensing images), DIOR-RSVG (DIOR remote sensing visual grounding), VisDrone-DET (VisDrone object detection), and a Swin-T backbone comparison further characterize the adaptation behavior. A Seen/Unseen split shows that short fine-tuning improves Seen-class adaptation but does not preserve Unseen-category transfer. These findings offer practical guidelines for adapting text-guided vision-language detectors to RS imagery.