UADet: Redefining Marine Debris Detection in Degraded Underwater Scenes with Adaptive Feature and Boundary Refinement

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Underwater marine debris detection is important for marine environmental monitoring, robotic inspection, and debris removal. However, reliable detection remains challenging because underwater images often suffer from low illumination, color distortion, turbidity, cluttered backgrounds, and weak boundaries. These factors reduce feature reliability and hinder accurate localization, especially for small, occluded, or low-visibility debris. To address these challenges, this paper proposes UADet, an adaptive detector for marine debris detection in degraded underwater scenes. UADet integrates two complementary components: Underwater Degradation-aware Feature Modulation (UDFM) and Visibility-aware Boundary Distribution Refinement (VBDR). UDFM extracts lightweight image-level degradation cues and modulates multi-scale features to improve robustness under varying underwater conditions. VBDR incorporates object scale and an appearance-based proxy for local visual difficulty into boundary distribution learning and matching cost, providing adaptive localization supervision for small objects and objects with weak visual evidence. Experiments are conducted on TrashCan and J-Litter, and UADet is compared with representative real-time detectors, including YOLOv8s, YOLOv10s, YOLOv11s, and RT-DETR. The results show that UADet achieves the best performance on both datasets, with 72.74% mAP@0.5, 81.36% precision, and 69.36% recall on TrashCan, and 48.02% mAP@0.5, 70.13% precision, and 55.61% recall on J-Litter. Compared with the strongest baseline, UADet improves mAP@0.5 by 3.12 percentage points on TrashCan and 4.83 percentage points on J-Litter. Ablation and qualitative analyses demonstrate that UDFM and VBDR provide complementary improvements. These results indicate that modeling underwater degradation and boundary uncertainty improves the robustness and reliability of marine debris detection in challenging underwater environments.