SEP 10, 2026 · PREPRINT
TailProp: content-adaptive light- and heavy-tailed propagation for vision
arXiv
A novel computer vision architecture introduced without peer review; demonstrates computational and benchmark performance improvements but lacks independent validation and clinical or translational endpoints.
Reported
ImageNet-1K Top-1 accuracy (TailP…84.4%
COCO box AP (3x Mask R-CNN schedu…50.3
COCO mask AP (3x Mask R-CNN sched…44.8