Preprint
Sep 2026
Extending Decoupled Attention to Dense Prediction and Masked Training for Multi-Channel Images
Across three classification and three segmentation benchmarks spanning fluorescence microscopy, imaging mass cytometry and satellite imaging, including dense prediction at high channel counts, the resulting formulation outperforms the strongest MC-ViT baseline.
Umar Marikkar, S. Husain, Muhammad Awais et al.
· 0 citations