Replacing the logistic regression meta classifier with a lightweight fully connected network improves anomaly segmentation accuracy on the LostAndFound benchmark, and selecting proxy out-of-distribution images with sparse, clearly separated objects improves entropy maximization training.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation
Replacing the logistic regression meta classifier with a lightweight fully connected network improves anomaly segmentation accuracy on the LostAndFound benchmark, and selecting proxy out-of-distribution images with sparse, clearly separated objects improves entropy maximization training.