Efficient image super-resolution (SR) models are essential for achieving high-quality image reconstruction with reduced computational complexity, particularly in resource-constrained environments. In this paper, we introduce a novel self-attention mechanism, Broadcast-Gated Attention with Identity Adaptive Integration (BGAI). Then, based on this mechanism, we design a lightweight super-resolution network that achieves state-of-the-art performance with minimal computational cost. By observing the sparsity and convergence properties of self-attention, BGAI optimizes computational resource utilization through the effective broadcasting of meaningful features across attention heads and network layers. A key innovation in BGAI is the Broadcast-Gated Multi-head Self-Attention (BGMSA) mechanism, which employs a dedicated head to capture and integrate long-range dependencies, broadcasting this broader contextual information to local attention heads. This design enhances long-range interaction modeling while minimizing redundant computations. Additionally, the Identity Attention Adaptive Integration (IAAI) mechanism facilitates efficient feature propagation by leveraging the continuity in dependencies across layers, with a focus on dynamic variations to improve representational efficiency and accelerate convergence. Comprehensive experiments on standard benchmarks demonstrate that BGAI achieves high-fidelity super-resolution while reducing the number of parameters and FLOPs by up to 35% compared with existing lightweight methods. These results establish BGAI as a robust and scalable solution for resource-efficient SR, with significant potential for deployment in real-world, high-resolution image processing applications. The code and trained models are publicly available at https://github.com/bbbolt/BGAI.

Aurora is the most visible manifestation of the sun’s effect on Earth. The ground-based all-sky imager (ASI) can observe a wealth of multiscale morphological features. Auroral image classification is an important tool for studying magnetospheric regimes and dynamic activities of aurora. Previous studies of automated auroral image classification focused more on auroral large-scale features across the entire image, ignoring small-scale auroral structures. In this letter, we introduce an object detection approach to investigate the small-scale features of auroral morphology. Since the small-scale auroral structures are nonrigid, morphologically diverse, and undefined boundaries, pixel-level labeling is labor-intensive and error-prone for human experts. Therefore, a weakly supervised object detection method for auroral vortexes is proposed in the absence of pixel-level annotations. We first perform global semantic identification and coarse localization using image-level labels as supervision. Considering the motion properties of vortexes, the global and local semantic information in a spatiotemporal volume is leveraged as semantic and location continuity constraints to generate high-confidence pseudo-labels. The experiments demonstrate that the proposed method can identify the vortexes more accurately. The method can retrieve small-scale auroral events in the aurora image dataset, allowing the study of the correlation of multiscale auroral events to be carried out.

In this paper, we propose a novel weakly supervised semantic segmentation (WSSS) method that uses image tags as supervision to achieve joint pixel-level localization of the key local structure (KLS) and image-level classification of the aurora images captured by the ground-based optical all-sky imager. First, a patch-scale model (PSM) based on the small-scale structure of aurora is designed to identify the type-specific regions for each training image. Second, a region-scale model is trained with the identified type-specific regions to coarsely localize the KLS from multiple sizes of field of view, based on which the aurora image is classified. Finally, given the predicted image type, the PSM further refines the KLS in a pixel level. By localizing KLS from coarse to fine, the proposed method captures both overall shape with a bottom-up processing and local structure details of aurora in a top-down manner. Extensive experiments on the expert labeled data sets have demonstrated the efficacy of the proposed method in benchmarking with the state-of-the-art WSSS methods.