Zhongnian Li

USimUL: Closing the Privacy Gap in Similarity-Based Weakly Supervised Learning

Unlocking the Power of Co-Occurrence in CLIP: A DualPrompt-Driven Method for Training-Free Zero-Shot Multi-Label Classification

Are Large Vision-Language Models Good Annotators for Image Tagging?

Learning from Aggregate-Masked Labels

Preventing Privacy Leakage in Vision-Language Models: A Secure Framework for Large-Scale Image Classification

Leveraging Human Collaboration: Learning from Human-Verified Labels

Learning from True-False Labels via Multi-modal Prompt Retrieving