Using absolute normalizing flow gradients as a pixel-level out-of-distribution score lets a robot optimize camera parameters locally, improving object detection by 60% over global-score baselines in severe lighting.
Generalized odin: Detecting out-of-distribution image without learning from out-of-distribution data,
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Making the Flow Glow -- Robot Perception under Severe Lighting Conditions using Normalizing Flow Gradients
Using absolute normalizing flow gradients as a pixel-level out-of-distribution score lets a robot optimize camera parameters locally, improving object detection by 60% over global-score baselines in severe lighting.