In this episode we discuss ZipIt! Merging Models from Different Tasks without Training
by George Stoica, Daniel Bolya, Jakob Bjorner, Taylor Hearn, Judy Hoffman. The paper introduces a method called “ZipIt!” that can merge two deep visual recognition models trained on separate tasks without additional training. The method incorporates a “zip” operation to handle non-shared features within each model and allows for partial merging up to a specified layer, creating a multi-head model. Experimental results demonstrate a substantial improvement of 20-60% compared to previous approaches, making it possible to merge models trained on different tasks.
arxiv preprint – ZipIt! Merging Models from Different Tasks without Training
by
Tags: