A GAN-based reconstruction dissimilarity method for detecting semantic segmentation errors achieves AUC ~0.55, below the softmax entropy baseline of 0.73.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
This is not what I imagined: Error Detection for Semantic Segmentation through Visual Dissimilarity
A GAN-based reconstruction dissimilarity method for detecting semantic segmentation errors achieves AUC ~0.55, below the softmax entropy baseline of 0.73.