2 papers
cs.CV2026
MEMO: Human-like Crisp Edge Detection Using Masked Edge Prediction
Jiaxin Cheng, Yue Wu, Yicong Zhou
Learning-based edge detection models trained with cross-entropy loss often suffer from thick edge predictions, which deviate from the crisp, single-pixel annotations typically prov…
cs.CV2026
From Semantics to Pixels: Coarse-to-Fine Masked Autoencoders for Hierarchical Visual Understanding
Wenzhao Xiang, Yue Wu, Hongyang Yu +3
Self-supervised visual pre-training methods face an inherent tension: contrastive learning (CL) captures global semantics but loses fine-grained detail, while masked image modeling…