no code implementations • 21 Mar 2023 • Min Chen, Weizhuo Gao, Gaoyang Liu, Kai Peng, Chen Wang
In this paper, we refocus our attention from the parameter space to the decision space of the DNN model, and propose Boundary Unlearning, a rapid yet effective way to unlearn an entire class from a trained DNN model.
no code implementations • CVPR 2023 • Min Chen, Weizhuo Gao, Gaoyang Liu, Kai Peng, Chen Wang
In this paper, we refocus our attention from the parameter space to the decision space of the DNN model, and propose Boundary Unlearning, a rapid yet effective way to unlearn an entire class from a trained DNN model.