← Search

Huimin Xiong

2 accepted papers

2024

VPL: Visual Proxy Learning Framework for Zero-Shot Medical Image Diagnosis

EMNLP 2024finding

Vision-language models like CLIP, utilizing class proxies derived from class name text features, have shown a notable capability in zero-shot medical image diagnosis which is vital in scenarios with limited disease databases or labeled samples. However, insufficient medical text precision and the mo…

Cited by 3SourcePDFScholar
2023

Fast Model DeBias with Machine Unlearning

NeurIPS 2023poster

Recent discoveries have revealed that deep neural networks might behave in a biased manner in many real-world scenarios. For instance, deep networks trained on a large-scale face recognition dataset CelebA tend to predict blonde hair for females and black hair for males. Such biases not only jeopard…

Cited by 60SourcePDFScholar