Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection

TL;DR

This paper investigates why certain marine species are detected less accurately in underwater object detection, revealing that localization and intrinsic feature challenges are key factors, and suggests targeted algorithmic improvements.

Contribution

It systematically analyzes class-specific detection disparities and proposes focusing on localization modules and data distribution strategies for better marine species detection.

Findings

Foreground-background discrimination is the main challenge in localization.

Persistent precision gaps exist even with balanced data.

Algorithmic improvements should target localization modules.

Abstract

Underwater object detection is critical for monitoring marine ecosystems but poses unique challenges, including degraded image quality, imbalanced class distribution, and distinct visual characteristics. Not every species is detected equally well, yet underlying causes remain unclear. We address two key research questions: 1) What factors beyond data quantity drive class-specific performance disparities? 2) How can we systematically improve detection of under-performing marine species? We manipulate the DUO and RUOD datasets to separate the object detection task into localization and classification and investigate the under-performance of the scallop class. Localization analysis using YOLO11 and TIDE finds that foreground-background discrimination is the most problematic stage regardless of data quantity. Classification experiments reveal persistent precision gaps even with balanced data, indicating intrinsic feature-based challenges beyond data scarcity and inter-class dependencies. We recommend imbalanced distributions when prioritizing precision, and balanced distributions when prioritizing recall. Improving under-performing classes should focus on algorithmic advances, especially within localization modules. We publicly release our code and datasets.