2 papers
cs.CV2025
SC-Pro: Training-Free Framework for Defending Unsafe Image Synthesis Attack
Junha Park, Jaehui Hwang, Ian Ryu +3
With advances in diffusion models, image generation has shown significant performance improvements. This raises concerns about the potential abuse of image generation, such as the…
cs.CV2024
Adaptive Explicit Knowledge Transfer for Knowledge Distillation
Hyungkeun Park, Jong-Seok Lee
Logit-based knowledge distillation (KD) for classification is cost-efficient compared to feature-based KD but often subject to inferior performance. Recently, it was shown that the…