Search Results for author:
Found 4 papers, 3 papers with code
Impact of architecture on robustness and interpretability of multispectral deep neural networks
At one extreme, known as "early fusion," additional bands are stacked as extra channels to obtain an input image with more than three channels.
Quantifying the robustness of deep multispectral segmentation models against natural perturbations and data poisoning
In this work, we seek to characterize the performance and robustness of a multispectral (RGB and near infrared) image segmentation model subjected to adversarial attacks and natural perturbations.
How many dimensions are required to find an adversarial example?
Past work exploring adversarial vulnerability have focused on situations where an adversary can perturb all dimensions of model input.
Testing predictions of representation cost theory with CNNs
It is widely acknowledged that trained convolutional neural networks (CNNs) have different levels of sensitivity to signals of different frequency.
