Pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation

cs.CV · 2024-12-14 · conditional · novelty 4.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation cs.CV · 2024-12-14 · conditional · none · ref 6

    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.