QMSR: Query-Conditioned Mask-wise Expert Routing for Robust Open-Vocabulary Underwater Object Retrieval
cs.RO
Submitted: 2026-09-16
Updated: 2026-09-16
Comments: This paper has been submitted to ICRA2027
License: http://creativecommons.org/licenses/by/4.0/
The gist: Open-vocabulary object retrieval remains challenging in complex underwater environments.
Terminology
Abstract
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 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 strength, enabling adaptive enhancement while preserving useful Raw semantics. During training, a privileged ranking oracle provides expert-selection and fusion-strength supervision, while an annealed soft-routing relaxation facilitates optimization of the hard Top-1 routing policy. Experiments show that QMSR improves NDCG@10 by 17.6% over an image--query shared router, while consistently outperforming fixed UIE strategies and remaining effective on held-out query categories. These results demonstrate the effectiveness of query-conditioned and candidate-specific enhancement routing for underwater open-vocabulary retrieval.
Sources
- PLAF: Pixel-wise Language-Aligned Feature Extraction for Efficient 3D Scene Understanding
- WaterMamba: Visual State Space Model for Underwater Image Enhancement
- Argus-Retriever: Vision-LLM Late-Interaction Retrieval with Region-Aware Query-Conditioned MoE for Visual Document Retrieval
- CoRe-UIE: Rethinking Coexisting and Region-wise Degradation for Underwater Image Enhancement
- AMIEOD: Adaptive Multi-Experts Image Enhancement for Object Detection in Low-Illumination Scenes
- TrashCan: A Semantically-Segmented Dataset towards Visual Detection of Marine Debris
- Advancing Marine Research: UWSAM Framework and UIIS10K Dataset for Precise Underwater Instance Segmentation
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies