Finding Visual Task Vectors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hojel, Alberto, Bai, Yutong, Darrell, Trevor, Globerson, Amir, Bar, Amir
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909337983647744
author Hojel, Alberto
Bai, Yutong
Darrell, Trevor
Globerson, Amir
Bar, Amir
author_facet Hojel, Alberto
Bai, Yutong
Darrell, Trevor
Globerson, Amir
Bar, Amir
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_05729
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Finding Visual Task Vectors
Hojel, Alberto
Bai, Yutong
Darrell, Trevor
Globerson, Amir
Bar, Amir
Computer Vision and Pattern Recognition
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.
title Finding Visual Task Vectors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.05729