1 code implementation • 11 Oct 2023 • Kyuyeon Kim, Junsik Jung, Woo Jae Kim, Sung-Eui Yoon
To implement the prior knowledge, we first train the audio-visual network, which learns the correspondence between auditory and visual information.
1 code implementation • CVPR 2023 • Woo Jae Kim, Yoonki Cho, Junsik Jung, Sung-Eui Yoon
The Separation part disentangles the input feature map into the robust feature with activations that help the model make correct predictions and the non-robust feature with activations that are responsible for model mispredictions upon adversarial attack.