SOURCE-LINKED INTELLIGENCE

QMSR: Query-Conditioned Mask-wise Expert Routing for Robust Open-Vocabulary Underwater Object Retrieval

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Open-vocabulary object retrieval remains challenging in complex underwater environments. Although underwater image enhancement (UIE) can improve visual quality, fixed UIE strategies may even underperform the Raw representation in retrieval, indicating that enhancement should not be applied as a uniform preprocessing step. To address this problem, we propose \textbf{QMSR}, a query-conditioned mask-wise expert routing framework for underwater open-vocabulary retrieval. Specifically, QMSR selects one pretrained UIE expert for each query--candidate pair and predicts a continuous Raw--Expert fusion

Read original source ↗ Open in workspace

recordType

paper

region

Global