# Why Domain Matters: A Preliminary Study of Domain Effects in Underwater Object Detection

arXiv: https://arxiv.org/abs/2604.26174 · HTML: https://mlsanity.com/paper/2604.26174/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Builds on (most cited first, 8 of 8)

- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [A Dataset And Benchmark Of Underwater Object Detection For Robot Picking](https://mlsanity.com/paper/2106.05681/) (2021)
- [Achieving Domain Generalization in Underwater Object Detection by Domain Mixup and Contrastive Learning](https://mlsanity.com/paper/2104.02230/) (2021)
- [Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection](https://mlsanity.com/paper/2206.13728/) (2022)
- [A Structured Review of Underwater Object Detection Challenges and Solutions: From Traditional to Large Vision Language Models](https://mlsanity.com/paper/2509.08490/) (2025)
- [Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection](https://mlsanity.com/paper/2508.18729/) (2025)
- [What Makes a Visualization Image Complex?](https://mlsanity.com/paper/2510.08332/) (2025)
- [Viewpoint Adaptation for Rigid Object Detection](https://mlsanity.com/paper/1702.07451/) (2017)

## Abstract (arXiv)

Domain shift, where deviations between training and deployment data distributions degrade model performance, is a key challenge in underwater environments. Existing benchmarks testing performance for underwater domain shift simulate variability through synthetic style transfer. This fails to capture intrinsic scene factors such as visibility, illumination, scene composition, or acquisition factors, limiting analysis of real-world effects. We propose a labeling framework that defines underwater domains using measurable image, scene, and acquisition characteristics. Unlike prior benchmarks, it captures physically meaningful factors, enabling semantically consistent image grouping and supporting domain-specific evaluation of detection performance including failure analysis. We validate this on public datasets, showing systematic variations across domain factors and revealing hidden failure modes.