3 papers
cs.CV2026
Seeing Like Radiologists: Context- and Gaze-Guided Vision-Language Pretraining for Chest X-rays
Kang Liu, Zhuoqi Ma, Siyu Liang +5
Despite recent advances in medical vision-language pretraining, existing models still struggle to capture the diagnostic workflow: radiographs are typically treated as context-agno…
cs.CV2025
Noise-Tolerant Hybrid Prototypical Learning with Noisy Web Data
Chao Liang, Linchao Zhu, Zongxin Yang +2
We focus on the challenging problem of learning an unbiased classifier from a large number of potentially relevant but noisily labeled web images given only a few clean labeled ima…
cs.CV2024
Combating Label Noise With A General Surrogate Model For Sample Selection
Chao Liang, Linchao Zhu, Humphrey Shi +1
Modern deep learning systems are data-hungry. Learning with web data is one of the feasible solutions, but will introduce label noise inevitably, which can hinder the performance o…