5 papers
Unsupervised Anomaly Detection Using Diffusion Trend Analysis for Display Inspection
Eunwoo Kim, Un Yang, Cheol Lae Roh +1
Reconstruction-based anomaly detection via denoising diffusion model has limitations in determining appropriate noise parameters that can degrade anomalies while preserving normal…
Continual Learning for Multiple Modalities
Hyundong Jin, Eunwoo Kim
Continual learning aims to learn knowledge of tasks observed in sequential time steps while mitigating the forgetting of previously learned knowledge. Existing methods were designe…
Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models
Hyundong Jin, Hyung Jin Chang, Eunwoo Kim
Continual learning enables pre-trained generative vision-language models (VLMs) to incorporate knowledge from new tasks without retraining data from previous ones. Recent methods u…
RainbowPrompt: Diversity-Enhanced Prompt-Evolving for Continual Learning
Kiseong Hong, Gyeong-hyeon Kim, Eunwoo Kim
Prompt-based continual learning provides a rehearsal-free solution by tuning small sets of parameters while keeping pre-trained models frozen. To meet the complex demands of sequen…
Moiré Zero: An Efficient and High-Performance Neural Architecture for Moiré Removal
Seungryong Lee, Woojeong Baek, Younghyun Kim +4
Moiré patterns, caused by frequency aliasing between fine repetitive structures and a camera sensor's sampling process, have been a significant obstacle in various real-world appl…