This study presents a novel multi-branch hybrid network framework based on structural re-parameterization for underwater small object detection, referred to as SRP-UOD. The developed framework employs multi-branch convolutions with ReBottleneck-ResNets, which are re-parameterized based on structural parameters, to facilitate more efficient feature extraction and fusion. Furthermore, the addition of SPD-Block enables the extraction of fine-grained information from images, thereby reducing the learning efficiency of low-quality feature representations. Specifically, we introduce a Distance-IoU Loss for the underwater target detection scenario, aiming to address the performance degradation caused by target occlusions. The resulting SRP-UOD model shows significant effectiveness in underwater target detection, achieving an average accuracy rate (mAP) of 83. 6% in the URPC2020 (Dalian) competition dataset.

Light traveling through water results in strong scattering across color channels, restricting visibility in underwater images. Many cutting-edge underwater image enhancement methods encounter limitations in color recovery accuracy and resilience against irrelevant feature interference. To tackle these degradation challenges, we propose an efficient and fully guided information flow network called UGIF-Net, for enhancing underwater images. Specifically, we propose a multi-color space-guided color estimation module that accurately approximates color information by incorporating features from two color spaces within a unified network. Subsequently, we employ a dense attention block to guide the network in thoroughly extracting color information from both color spaces while adaptively perceiving crucial color information. Moreover, we devise a color-guided map to steer the network’s focus toward color information and augment its response to color quality degradation. We incorporate the guided map into a guide color restoration module to achieve visually appealing enhancement results. Comprehensive experiments indicate that our approach surpasses state-of-the-art methods, showcasing favorable image restoration effects and their potential to aid other high-level vision tasks.

Object Relationship Notation (ORN) is a declarative scheme that allows a variety of common relationship types to be conveniently specified to a database management system (DBMS), thereby allowing their semantics to be automatically enforced by the DBMS. ORN can be integrated into any data model that represents binary associations or DBMS that implements them. We give a brief description of ORN syntax and semantics and provide algorithms that can be used to implement ORN. These algorithms must deal with the presence of association cycles in the database. We explore in detail the problems caused by such cycles and how ORN and its implementation deal with them, and we show that ORN semantics are noncircular and unambiguous.