A new unsupervised driver attention predictor with knowledge embedding, uncertainty mining, and RoboMixup augmentation matches or beats several supervised baselines on clean and corrupted driving benchmarks.
Multi-source uncertainty mining for deep unsupervised saliency detection
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.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Towards Robust Unsupervised Attention Prediction in Autonomous Driving
A new unsupervised driver attention predictor with knowledge embedding, uncertainty mining, and RoboMixup augmentation matches or beats several supervised baselines on clean and corrupted driving benchmarks.