A denoising autoencoder placed before DeepLab V3 Plus partially restores segmentation accuracy after FGSM and I-FGSM attacks, but only against attacks that ignore the filter.
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
-
DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation
A denoising autoencoder placed before DeepLab V3 Plus partially restores segmentation accuracy after FGSM and I-FGSM attacks, but only against attacks that ignore the filter.