no code implementations • 26 Jul 2021 • Alberto Santamaria-Pang, Jianwei Qiu, Aritra Chowdhury, James Kubricht, Peter Tu, Iyer Naresh, Nurali Virani
Third, we generate new adversarial images by projecting back the original coefficients from the low scale and the perturbed coefficients from the high scale sub-space.
no code implementations • 18 Jul 2020 • Alberto Santamaria-Pang, James Kubricht, Aritra Chowdhury, Chitresh Bhushan, Peter Tu
A UNet-like architecture is used to generate input to the Sender network which produces a symbolic sentence, and a Receiver network co-generates the segmentation mask based on the sentence.