Kyungwoo Song

7

Papers

63

Total Citations

Papers (7)

Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners

DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation

Sufficient Invariant Learning for Distribution Shift

BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning

LADA: Look-Ahead Data Acquisition via Augmentation for Deep Active Learning

Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation

Geodesic Multi-Modal Mixup for Robust Fine-Tuning