Synthetic corruptions are a strong proxy for real-world corruptions when ranking semantic segmentation models on average, but individual corruption types like fog and night show weak correlation.
On the unreasonable vulnerability of transformers for image restoration-and an easy fix
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
Synthetic corruptions are a strong proxy for real-world corruptions when ranking semantic segmentation models on average, but individual corruption types like fog and night show weak correlation.