2025
Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models
CVPR 2025poster
Existing unlearning algorithms in text-to-image generative models often fail to preserve the knowledge of semantically related concepts when removing specific target concepts--a challenge known as adjacency. To address this, we propose FADE (Fine-grained Attenuation for Diffusion Erasure), introduci…