3 papers
cs.LG2026
Residual SODAP: Residual Self-Organizing Domain-Adaptive Prompting with Structural Knowledge Preservation for Continual Learning
Gyutae Oh, Jungwoo Bae, Jitae Shin
Continual learning (CL) suffers from catastrophic forgetting, which is exacerbated in domain-incremental learning (DIL) where task identifiers are unavailable and storing past data…
cs.LG2025
UniPrompt-CL: Efficient Single-Inference Continual Learning for Medical Image Classification
Gyutae Oh, Jitae Shin
Medical AI systems must remain reliable as data distributions shift across hospitals, imaging devices, and patient populations, yet privacy constraints often prevent storing or rev…
cs.CV2024
Uncertainty Measurement of Deep Learning System based on the Convex Hull of Training Sets
Hyekyoung Hwang, Jitae Shin
Deep Learning (DL) has made remarkable achievements in computer vision and adopted in safety critical domains such as medical imaging or autonomous drive. Thus, it is necessary to…