2 papers
cs.CV2026
Calibrating Uncertainty for Zero-Shot Adversarial CLIP
Wenjing Lu, Zerui Tao, Yuning Qiu +3
CLIP delivers strong zero-shot classification but remains highly vulnerable to adversarial attacks. Prior adversarial fine-tuning work primarily matches predicted logits between cl…
cs.CV2026
Harmonizing Generalization and Specialization: Uncertainty-Informed Collaborative Learning for Semi-supervised Medical Image Segmentation
Wenjing Lu, Yi Hong, Yang Yang
Vision foundation models have demonstrated strong generalization in medical image segmentation by leveraging large-scale, heterogeneous pretraining. However, they often struggle to…