arxivcs.AIcs.CV2026-07-06
FM-ChangeNet: Learning Change through Pathwise Feature Transport
Roie Kazoom, George Leifman, Genady Beryozkin
We present FM-ChangeNet, a pathwise-supervised framework for change detection that reformulates bi-temporal reasoning as continuous transport in feature space rather than static endpoint comparison. Given encoded pre and post-temporal representations, we construct intermediate la…