Hong-Yu Zhou

ConvNets vs. Transformers: Whose Visual Representations are More Transferable?

2021

Vision transformers have attracted much attention from computer vision researchers as they are not restricted to the spatial inductive bias of ConvNets. However, although Transformer-based backbones have achieved much progress on ImageNet classification, it is …

GraVIS: Grouping Augmented Views From Independent Sources for Dermatology Analysis

2022 · IEEE Transactions on Medical Imaging

Self-supervised representation learning has been extremely successful in medical image analysis, as it requires no human annotations to provide transferable representations for downstream tasks. Recent self-supervised learning methods are dominated by noise-contrastive estimation (NCE, also …