A survey of sonar-based deep learning that identifies robustness, dataset scarcity, and sim-to-real gaps as the main obstacles to safe underwater autonomy.
Lambertian-based adversarial attacks on deep-learning-based underwater side-scan sonar image classification,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Sonar-based Deep Learning in Underwater Robotics: Overview, Robustness and Challenges
A survey of sonar-based deep learning that identifies robustness, dataset scarcity, and sim-to-real gaps as the main obstacles to safe underwater autonomy.