5 papers
Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check
Sungjun Cho, Dasol Hwang, Frederic Sala +3
Current unlearning metrics for generative models evaluate success based on reference responses or classifier outputs rather than assessing the core objective: whether the unlearned…
APT: Adaptive Personalized Training for Diffusion Models with Limited Data
JungWoo Chae, Jiyoon Kim, JaeWoong Choi +2
Personalizing diffusion models using limited data presents significant challenges, including overfitting, loss of prior knowledge, and degradation of text alignment. Overfitting le…
Parallel Rescaling: Rebalancing Consistency Guidance for Personalized Diffusion Models
JungWoo Chae, Jiyoon Kim, Sangheum Hwang
Personalizing diffusion models to specific users or concepts remains challenging, particularly when only a few reference images are available. Existing methods such as DreamBooth a…
StochCA: A Novel Approach for Exploiting Pretrained Models with Cross-Attention
Seungwon Seo, Suho Lee, Sangheum Hwang
Utilizing large-scale pretrained models is a well-known strategy to enhance performance on various target tasks. It is typically achieved through fine-tuning pretrained models on t…
GTA: Guided Transfer of Spatial Attention from Object-Centric Representations
SeokHyun Seo, Jinwoo Hong, JungWoo Chae +2
Utilizing well-trained representations in transfer learning often results in superior performance and faster convergence compared to training from scratch. However, even if such go…