ViT-MUL: A Baseline Study on Recent Machine Unlearning Methods Applied to Vision Transformers

arXiv:2403.09681v1 Announce Type: cross
Abstract: Machine unlearning (MUL) is an arising field in machine learning that seeks to erase the learned information of specific training data points from a trained model. Despite the recent active research in MUL within computer vision, the majority of work has focused on ResNet-based models. Given that Vision Transformers (ViT) have become the predominant model architecture, a detailed study of MUL specifically tailored to ViT is essential. In this paper, we present comprehensive experiments on …

abstract arxiv computer computer vision cs.cv cs.lg data information machine machine learning research study training training data transformers type unlearning vision vision transformers vit work