4 papers
SSAFE: Simple and Strong AI-Generated Image Detection via Frozen Vision Encoders
Seunghyun Lee, Byoungkwon Kim, Jaehyun Nam +2
The rapid advancement of generative models has blurred the boundary between synthetic and real imagery, creating an urgent need for reliable deepfake detection. Yet most existing a…
CLIP Meets Diffusion: A Synergistic Approach to Anomaly Detection
Byeongchan Lee, John Won, Seunghyun Lee +1
Anomaly detection is a complex problem due to the ambiguity in defining anomalies, the diversity of anomaly types (e.g., local and global defect), and the scarcity of training data…
Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimation
Seunghyun Lee, Tae-Kyun Kim
Latest diffusion models have shown promising results in category-level 6D object pose estimation by modeling the conditional pose distribution with depth image input. The existing…
Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition
Dasol Choi, Seunghyun Lee, Youngsook Song
Vision-Language Models (VLMs) have shown capabilities in interpreting visual content, but their reliability in safety-critical scenarios remains insufficiently explored. We introdu…