no code implementations • 1 Feb 2023 • Bo-Han Kung, Shang-Tse Chen
This observation leads to an efficient and effective input-specific randomized smoothing algorithm.
no code implementations • CVPR 2021 • Pin-Chun Chen, Bo-Han Kung, Jun-Cheng Chen
Meanwhile, instead of normalizing the total loss with the number of objects, the proposed approach decomposes the total loss into class-wise losses and normalizes each class loss using the number of objects for the class.
1 code implementation • ICCV 2021 • Yu-Chih-Tuan Hu, Bo-Han Kung, Daniel Stanley Tan, Jun-Cheng Chen, Kai-Lung Hua, Wen-Huang Cheng
Most prior works on physical adversarial attacks mainly focus on the attack performance but seldom enforce any restrictions over the appearance of the generated adversarial patches.