by Synced 2023-05-10 1
Georgia Tech’s ZipIt! Effectively Merges Vision Models Trained on Disjoint Tasks Without Additional Training
In the new paper ZipIt! Merging Models from Different Tasks Without Training, a Georgia Tech research team proposes ZipIt!, a general method that exploits redundant features to combine two or more models with the same architecture but trained on different tasks into one multi-task model without additional training.