Underwater images typically suffer from two main types of degradation: reduced visibility caused by scattering and color distortion due to color cast. Most existing deep learning-based enhancement methods adopt end-to-end architectures to address both issues simultaneously. However, this design not only limits the model’s generalization capability but also hinders practical deployment due to excessive computational overhead. To this end, this paper proposes a binarized Decoupled Synergistic Optimization Strategy (DSOS), which explicitly decouples scattering and color cast degradations and performs collaborative optimization through specialized subtask modules. Each subtask learns purer features under the guidance of independent supervised signals, while a cascaded architecture ensures effective global restoration. Furthermore, cross-module collaborative optimization effectively mitigates the performance degradation caused by binarization, achieving a favorable balance between efficiency and high accuracy. Experimental results on multiple publicly available underwater image datasets demonstrate that the proposed method significantly outperforms state-of-the-art approaches in both restoration quality and computational efficiency.

Hypergraph Neural Networks (HNNs) have recently gained attention as a powerful approach for capturing high-order correlations through hypergraph-structured encoding and learning techniques. However, despite their potential, existing HNN methods often encounter over-smoothing issues, which limit their ability to effectively integrate global information while maintaining high-order structural details. This limitation compromises the overall effectiveness of these models. To tackle this challenge, we introduce a novel HNN framework called Hypergraph Structural Fusion (HyperSF). HyperSF combines the structural characteristics of both hypergraphs and graphs to effectively integrate global and local information while preserving the complex high-order structures inherent in hypergraphs. This structural fusion mechanism significantly improves model performance by ensuring that both types of information are utilized in a balanced manner. Comprehensive evaluations show that our method outperforms state-of-the-art approaches, demonstrating its effectiveness in hypergraph representation learning.

Hypergraph representation learning has garnered increasing attention across various domains due to its capability to model high-order relationships. Traditional methods often rely on hypergraph neural networks (HNNs) employing messagepassing mechanisms to aggregate vertex and hyperedge features. However, these methods are constrained by their dependence on hypergraph topology, leading to the challenge of imbalanced information aggregation, where high-degree vertices tend to aggregate redundant features, while low-degree vertices often struggle to capture sufficient structural features. To overcome the above challenges, we introduce HyperKAN, a novel framework for hypergraph representation learning that transcends the limitations of message-passing techniques. Hyper- KAN begins by encoding features for each vertex and then leverages Kolmogorov-Arnold Networks (KANs) to capture complex nonlinear relationships. By adjusting structural features based on similarity, our approach generates refined vertex representations that effectively addresses the challenge of imbalanced information aggregation. Experiments conducted on the real-world datasets demonstrate that HyperKAN significantly outperforms stateof-the-art HNN methods, achieving nearly a 9% performance improvement on the Senate dataset.

Existing X-ray prohibited item detection methods primarily focus on boosting the detection performance of uniformly distributed items. However, in the real-world scenarios, various prohibited items exhibit the long-tailed distribution, thus posing the huge challenge to the detection task. To support this study, we introduce LTXRay, a dedicated X-ray benchmark that better assesses long-tailed prohibited item detection. LTXRay consists of 18,718 images from 12 common classes with an imbalance factor of 280.35. Meanwhile, we propose a novel Memory-Guided Learning Network(MGLNet) to develop baseline methods on LTXRay, which enhance the within-class diversity for the tail classes and consequentially improves long-tailed object detection. Specifically, we first introduce a frequency-based feature refinement module to extract discriminative contextual representations, then store the various instance features in the memory bank and dynamically generate the sample according to the historical features. Extensive experiments have been performed on the LTXRay to demonstrate the effectiveness of the proposed method. The experimental results indicate that the proposed method can consistently improve the performance of baseline methods.

Feature Pyramid Network (FPN) exploits multi-scale fusion representation to deal with scale variances in object detection. However, it ignores the context information gap across different levels. In this paper, we develop a plug-and-play detector, the multi-scale context-aware feature pyramid network to unleash the power of feature pyramid representation. Based on the dilated feature map at the highest level of the backbone, we propose the cross-scale context aggregation block to make full use of context information in the feature pyramid. Moreover, we extract discriminative features among different levels by the adaptive context aggregation block for robust object detection. Comprehensive experiments on MS-COCO demonstrate the effectiveness and efficiency of the proposed network, where about 1.0~3.0 AP improvements are achieved compared with existing FPN-based methods. In addition, we also conduct extensive experiments on pixel-level prediction tasks, i.e., instance segmentation, semantic segmentation, and panoptic segmentation, which further verify the effectiveness of the proposed method.

Automatic security inspection using computer vision technology is a challenging task in real-world scenarios due to various factors, including intra-class variance, class imbalance, and occlusion. Most of the previous methods rarely solve the cases that the prohibited items are deliberately hidden in messy objects due to the lack of large-scale datasets, restricted their applications in real-world scenarios. Towards real-world prohibited item detection, we collect a large-scale dataset, named as PIDray, which covers various cases in real-world scenarios for prohibited item detection, especially for deliberately hidden items. With an intensive amount of effort, our dataset contains 12 categories of prohibited items in 47, 677 X-ray images with high-quality annotated segmentation masks and bounding boxes. To the best of our knowledge, it is the largest prohibited items detection dataset to date. Meanwhile, we design the selective dense attention network (SDANet) to construct a strong baseline, which consists of the dense attention module and the dependency refinement module. The dense attention module formed by the spatial and channel-wise dense attentions, is designed to learn the discriminative features to boost the performance. The dependency refinement module is used to exploit the dependencies of multi-scale features. Extensive experiments conducted on the collected PIDray dataset demonstrate that the proposed method performs favorably against the state-of-the-art methods, especially for detecting the deliberately hidden items.