Visual Prompting is a technique for teaching models to perform a visual task via in-context examples, without any additional training. In this work, we analyze the activations of MAE-VQGAN, a recent Visual Prompting model, and find task vectors, activations that encode task-specific information. Equipped with this insight, we demonstrate that it is possible to identify the task vectors and use them to guide the network towards performing different tasks without providing any input-output examples. To find task vectors, we compute the average intermediate activations per task and use the REINFORCE algorithm to search for the subset of task vectors. The resulting task vectors guide the model towards performing a task better than the original model without the need for input-output examples.
Cite
@article{arxiv.2404.05729,
title = {Finding Visual Task Vectors},
author = {Alberto Hojel and Yutong Bai and Trevor Darrell and Amir Globerson and Amir Bar},
journal= {arXiv preprint arXiv:2404.05729},
year = {2024}
}