论文标题
您可以从肌肉中学到什么?从人类互动中学习视觉表示
What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions
论文作者
论文摘要
学习有效的视觉数据的有效表示,将各种下游任务推广到计算机视觉一直是一个漫长的追求。大多数表示学习方法仅依赖于图像或视频等视觉数据。在本文中,我们探讨了一种新颖的方法,在该方法中,我们使用人类的互动和注意线索来研究与纯视觉表示相比,我们是否可以学习更好的表示。在这项研究中,我们收集了人类互动的数据集,以捕捉身体部位运动并凝视日常生活。我们的实验表明,在各种目标任务上,我们的“肌肉监督”表示的互动和注意力提示优于一种仅视觉的最先进的方法Moco(He等,2020),在各种目标任务上:场景分类(语义)(语义),动作识别(时间识别),深度估计(seeprics估算),表面估计(POSTHATICT),图表(物理)和漫步(物理)和绘制(物理)和次数(物理)和行动(物理)。我们的代码和数据集可在以下网址找到:https://github.com/ehsanik/muscletorch。
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.