Metraipolis › archive › dc_7530858ed3bf
Robust Cross-Modal Foundation Model Perception for Underwater Robots under Degraded Visual Conditions — arXiv:2608.19710
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.19710
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T12:04:38.522Z
- SHA-256 of the archived text
2b44039d9ba457542026c4c46e40521a82653ef8220c018636627989343c097c- Stable URL of this page
https://metraipolis.com/documento/dc_7530858ed3bf
How to cite
Robust Cross-Modal Foundation Model Perception for Underwater Robots under Degraded Visual Conditions — arXiv:2608.19710 — arXiv (en), https://arxiv.org/abs/2608.19710 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7530858ed3bf (Metraipolis archive dc_7530858ed3bf, sha256 2b44039d9ba457542026c4c46e40521a82653ef8220c018636627989343c097c)
BibTeX
@misc{dc7530858ed3bf,
title = {Robust Cross-Modal Foundation Model Perception for Underwater Robots under Degraded Visual Conditions — arXiv:2608.19710},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.19710},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7530858ed3bf; sha256 2b44039d9ba457542026c4c46e40521a82653ef8220c018636627989343c097c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19710. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reliable underwater robotic perception remains difficult because optical imagery degrades under turbidity, wavelength-dependent attenuation, low illumination, scattering, and blur. Although sonar provides complementary information that is less affected by optical visibility, prior visual-sonar research has largely focused on feature alignment and nominal detection performance. We investigate cross-modal robustness as visual reliability deteriorates and assess whether pretrained visual foundation-model representations can be complemented by sonar under severe degradation. We use frozen DINOv2 as the visual encoder and construct a controlled five-level benchmark ranging from clean to extreme visual conditions. We compare conventional visual detection, frozen foundation-model representations, sonar context, fixed multimodal fusion, clean-trained adaptive gating, and degradation-aware gated fusion. Our method trains the fusion mechanism across the full range of degradation while keeping the visual and sonar encoders frozen, allowing modality contributions to adapt without fine-tuning the pretrained backbone. Under extreme combined degradation, the DINOv2 baseline achieves 0.4610 balanced accuracy, while degradation-aware visual-sonar fusion reaches 0.6152, a 33.5% relative improvement. The learned sonar contribution increases from 14.2% under clean conditions to 41.3% under extreme degradation, demonstrating adaptive redistribution of cross-modal reliance. Fusion provides the largest gains under severe turbidity and blur, whereas color attenuation alone yields little additional benefit. These results show that foundation-model representations remain valuable but insufficient under severe information loss, and that explicitly adapting fusion to modality reliability can improve robust underwater multimodal perception. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.19710 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T12:01:57.709Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).