What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions

TL;DR

This paper introduces a novel visual representation learning method that incorporates human interaction and attention cues, outperforming traditional visual-only methods across multiple vision tasks.

Contribution

It presents a new dataset and approach using human interaction data to enhance visual representations, surpassing state-of-the-art visual-only methods.

Findings

Outperforms MoCo on various tasks

Uses human interaction cues for learning

Provides a new dataset for interaction-based learning

Abstract

Learning effective representations of visual data that generalize to a variety of downstream tasks has been a long quest for computer vision. Most representation learning approaches rely solely on visual data such as images or videos. In this paper, we explore a novel approach, where we use human interaction and attention cues to investigate whether we can learn better representations compared to visual-only representations. For this study, we collect a dataset of human interactions capturing body part movements and gaze in their daily lives. Our experiments show that our "muscly-supervised" representation that encodes interaction and attention cues outperforms a visual-only state-of-the-art method MoCo (He et al.,2020), on a variety of target tasks: scene classification (semantic), action recognition (temporal), depth estimation (geometric), dynamics prediction (physics) and walkable surface estimation (affordance). Our code and dataset are available at: https://github.com/ehsanik/muscleTorch.