Theia：面向机器人学习的多样化视觉基础模型蒸馏
Theia: Distilling Diverse Vision Foundation Models for Robot Learning
AI总结：
针对机器人策略学习需多样视觉理解的需求，提出蒸馏多现成视觉基础模型的Theia模型，以更少数据和更小尺寸实现更优性能，还探究了表征熵与学习效果的关联。
摘要：
基于视觉的机器人策略学习旨在将视觉输入映射为动作，它需要对多样化视觉任务具备整体理解，而非仅满足分类或分割等单任务需求。受此启发，我们提出了Theia——一款面向机器人学习的视觉基础模型，它对多个在不同视觉任务上训练的现成视觉基础模型进行蒸馏。Theia丰富的视觉表征编码了多样的视觉知识，可增强下游机器人学习效果。大量实验表明，Theia使用更少的训练数据、更小的模型尺寸，性能优于其教师模型及此前的机器人学习模型。此外，我们量化了预训练视觉表征的质量，并假设特征范数分布的熵越高，机器人学习性能越好。代码、模型和演示可访问https://theia.theaiinstitute.com获取。
英文摘要：
Vision-based robot policy learning, which maps visual inputs to actions, necessitates a holistic understanding of diverse visual tasks beyond single-task needs like classification or segmentation. Inspired by this, we introduce Theia, a vision foundation model for robot learning that distills multiple off-the-shelf vision foundation models trained on varied vision tasks. Theia's rich visual representations encode diverse visual knowledge, enhancing downstream robot learning. Extensive experiments demonstrate that Theia outperforms its teacher models and prior robot learning models using less training data and smaller model sizes. Additionally, we quantify the quality of pre-trained visual representations and hypothesize that higher entropy in feature norm distributions leads to improved robot learning performance. Code, models, and demo are available at https://theia.theaiinstitute.com.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
