Jae-Gil Lee

9

Papers

8

Total Citations

Papers (9)

RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language Models

VarDrop: Enhancing Training Efficiency by Reducing Variate Redundancy in Periodic Time Series Forecasting

Adaptive Shortcut Debiasing for Online Continual Learning

Active Prompt Learning in Vision Language Models

One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning

Task-Agnostic Undesirable Feature Deactivation Using Out-of-Distribution Data

Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning

Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy

SELFIE: Refurbishing Unclean Samples for Robust Deep Learning