# An Empirical Study on the Robustness of YOLO Models for Underwater Object Detection

arXiv: https://arxiv.org/abs/2509.17561 · HTML: https://mlsanity.com/paper/2509.17561/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 41 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 16 of 16)

- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [Not All Noises Are Created Equally:Diffusion Noise Selection and Optimization](https://mlsanity.com/paper/2407.14041/) (2024)
- [A Dataset And Benchmark Of Underwater Object Detection For Robot Picking](https://mlsanity.com/paper/2106.05681/) (2021)
- [Underwater Image Restoration Through a Prior Guided Hybrid Sense Approach and Extensive Benchmark Analysis](https://mlsanity.com/paper/2501.02701/) (2025)
- [FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection](https://mlsanity.com/paper/2504.20670/) (2025)
- [Texture image analysis and texture classification methods - A review](https://mlsanity.com/paper/1904.06554/) (2019)
- [MedYOLO: A Medical Image Object Detection Framework](https://mlsanity.com/paper/2312.07729/) (2023)
- [A systematic study of the foreground-background imbalance problem in deep learning for object detection](https://mlsanity.com/paper/2306.16539/) (2023)
- [Beneath the Surface: The Role of Underwater Image Enhancement in Object Detection](https://mlsanity.com/paper/2411.14626/) (2024)
- [Grey Level Co-occurrence Matrix (GLCM) Based Second Order Statistics for Image Texture Analysis](https://mlsanity.com/paper/2403.04038/) (2024)
- [Joint Perceptual Learning for Enhancement and Object Detection in Underwater Scenarios](https://mlsanity.com/paper/2307.03536/) (2023)
- [Agricultural Object Detection with You Look Only Once (YOLO) Algorithm: A Bibliometric and Systematic Literature Review](https://mlsanity.com/paper/2401.10379/) (2024)
- [YOLO-Vehicle-Pro: A Cloud-Edge Collaborative Framework for Object Detection in Autonomous Driving under Adverse Weather Conditions](https://mlsanity.com/paper/2410.17734/) (2024)
- [SCC-YOLO: An Improved Object Detector for Assisting in Brain Tumor Diagnosis](https://mlsanity.com/paper/2501.03836/) (2025)
- [Improve Underwater Object Detection through YOLOv12 Architecture and Physics-informed Augmentation](https://mlsanity.com/paper/2506.23505/) (2025)

## Abstract (arXiv)

Underwater object detection (UOD) remains a critical challenge in computer vision due to underwater distortions which degrade low-level features and compromise the reliability of even state-of-the-art detectors. While YOLO models have become the backbone of real-time object detection, little work has systematically examined their robustness under these uniquely challenging conditions. This raises a critical question: Are YOLO models genuinely robust when operating under the chaotic and unpredictable conditions of underwater environments? In this study, we present one of the first comprehensive evaluations of recent YOLO variants (YOLOv8-YOLOv12) across six simulated underwater environments. Using a unified dataset of 10,000 annotated images from DUO and Roboflow100, we not only benchmark model robustness but also analyze how distortions affect key low-level features such as texture, edges, and color. Our findings show that (1) YOLOv12 delivers the strongest overall performance but is highly vulnerable to noise, and (2) noise disrupts edge and texture features, explaining the poor detection performance in noisy images. Class imbalance is a persistent challenge in UOD. Experiments revealed that (3) image counts and instance frequency primarily drive detection performance, while object appearance exerts only a secondary influence. Finally, we evaluated lightweight training-aware strategies: noise-aware sample injection, which improves robustness in both noisy and real-world conditions, and fine-tuning with advanced enhancement, which boosts accuracy in enhanced domains but slightly lowers performance in original data, demonstrating strong potential for domain adaptation, respectively. Together, these insights provide practical guidance for building resilient and cost-efficient UOD systems.