Georgia Tech’s ZipIt! Effectively Merges Vision Models Trained on Disjoint Tasks Without Additional Training | Synced
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 ...
Source: Synced | AI Technology & Industry Review
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.