all AI news
Georgia Tech’s ZipIt! Effectively Merges Vision Models Trained on Disjoint Tasks Without Additional Training
Synced syncedreview.com
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.
The post Georgia Tech’s ZipIt! Effectively Merges Vision Models Trained on Disjoint Tasks Without Additional Training first appeared on Synced.
ai architecture artificial intelligence computer vision & graphics deep-neural-networks exploits features general georgia georgia tech machine learning machine learning & data science merging ml multitask learning paper research research team team tech technology training vision vision models