DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation
share
Nowadays, Deep learning techniques show dramatic performance on computer vision area, and they even outperform human. This is a problem combined with the safety of artificial intelligence, which has recently been studied a lot. These attack have shown that they can fool models of image classification, semantic segmentation, and object detection. We point out this attack can be protected by denoise autoencoder, which is used for denoising the perturbation and restoring the original images. We experiment with various noise distributions and verify the effect of denoise autoencoder against adversarial attack in semantic segmentation
READ FULL TEXT