RHCNet：面向鲁棒水下目标检测的残差引导分层校准网络
RHCNet: Residual-Guided Hierarchical Calibration Network for Robust Underwater Object Detection
针对水下图像前景-背景模糊、结构细节丢失的问题，在 ResNet-50 骨干中嵌入卷积+注意力的残差引导特征增强模块强化边缘纹理，并用自底向上语义增强与自顶向下细粒度补偿的双路径金字塔配合 K-means 引导的特征校准实现跨尺度语义一致，这套「增强+校准」组合可直接迁移到其他低对比度、模糊场景的检测器改进中。
原文依据 a residual-guided hierarchical calibration network (RHCNet) designed to achieve more efficient and robust UOD
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论水下图像普遍存在前景-背景模糊、结构细节丢失以及对比度严重下降的问题，这些问题共同使水下目标检测（UOD）成为一项本质上具有挑战性的任务。为解决该问题，本文提出残差引导分层校准网络（RHCNet），旨在实现更高效、更鲁棒的水下目标检测，该网络由残差引导特征增强模块（RGFE）和分层特征校准金字塔模块（HFCP）组成。具体而言，RHCNet 在标准 ResNet-50 骨干网络中嵌入 RGFE，通过联合利用卷积操作与注意力机制，有效增强模糊区域中边缘与纹理特征的表示，从而实现面向水下目标检测的更具判别性的特征提取。随后，HFCP 整合了自底向上的语义增强路径与自顶向下的细粒度特征补偿路径，并联合采用 K-means 聚类引导的特征校准模块，以确保多层级跨尺度语义一致性以及显著区域特征的精确对齐。在 DUO 与 UTDAC 基准数据集上的大量实验表明，RHCNet 分别取得了 70.53% 与 53.35% 的最高 AP 分数。此外，RHCNet 在面向陆地场景的 COCO 数据集上同样保持了优异的检测精度与强泛化能力。代码已发布于 https://github.com/YitengGuo/RHCNet。
英文原文摘要 1484 字符
Underwater images commonly suffer from foreground-background ambiguity, loss of structural details, and severely reduced contrast, which collectively make underwater object detection (UOD) an inherently challenging task. To handle this issue, we present a residual-guided hierarchical calibration network (RHCNet) designed to achieve more efficient and robust UOD, which comprises a residual-guided feature enhancement module (RGFE) and a hierarchical feature calibration pyramid module (HFCP). Concretely, RHCNet extends the standard ResNet-50 backbone by embedding the RGFE, which effectively strengthens the representation of edge and texture features in blurry regions by jointly leveraging convolutional operations and attention mechanisms to achieve more discriminative feature extraction for UOD. Subsequently, the HFCP integrates a bottom-up semantic enhancement path and a top-down fine-grained feature compensation path, while a K-means clustering-guided feature calibration module is jointly employed to ensure multi-level cross-scale semantic consistency and accurate alignment of salient region features. Extensive experiments on the DUO and UTDAC benchmark datasets demonstrated that our RHCNet attains the highest AP scores of 70.53% and 53.35%, respectively. Besides, our RHCNet also maintains excellent detection accuracy and strong generalization capability on the COCO dataset for terrestrial scenarios. The code is available at https://github.com/YitengGuo/RHCNet.