Preprint
Sep 2026
Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding
Self-supervised pre-training with Vision Transformers, including Masked Autoencoders (MAE), is difficult to apply to gigapixel scientific images. Random masking is poorly matched to the structured, multi-scale morphology of scientific data, while uniform tokenization produces prohibitively long sequences that make $O(N...
En-Zhi Zhang, Du Wu, Rui Zhong et al.
· 0 citations