A Mahalanobis distance computed in SAM feature space is used as an aleatoric uncertainty score for object instances, and filtering and reweighting by this score yields modest AP gains on COCO and BDD100K.
Towards robust adaptive object detection under noisy annotations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Exploring Aleatoric Uncertainty in Object Detection via Vision Foundation Models
A Mahalanobis distance computed in SAM feature space is used as an aleatoric uncertainty score for object instances, and filtering and reweighting by this score yields modest AP gains on COCO and BDD100K.