CWFA, a channel-wise global-average feature perturbation, improves robustness of Transformer segmentation models to common corruptions without hurting clean accuracy.
The cityscapes dataset for semantic urban scene understanding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Global Average Feature Augmentation for Robust Semantic Segmentation with Transformers
CWFA, a channel-wise global-average feature perturbation, improves robustness of Transformer segmentation models to common corruptions without hurting clean accuracy.