マスク付き視覚事前学習による実世界ロボット学習
Real-World Robot Learning with Masked Visual Pre-training
多様な動画画像に対するMAEベースの自己教師あり視覚事前学習を行い、凍結した表現を制御モジュールに渡すことで、様々な実世界ロボットタスクでCLIPやImageNet事前学習を上回る性能を示した。
著者: Ilija Radosavovic, Tete Xiao, Stephen James, Pieter Abbeel, Jitendra Malik, Trevor Darrell
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
In this work, we explore self-supervised visual pre-training on images from diverse, in-the-wild videos for real-world robotic tasks. Like prior work, our visual representations are pre-trained via a masked autoencoder (MAE), frozen, and then passed into a learnable control module. Unlike prior work, we show that the pre-trained representations are effective across a range of real-world robotic tasks and embodiments. We find that our encoder consistently outperforms CLIP (up to 75%), supervised ImageNet pre-training (up to 81%), and training from scratch (up to 81%). Finally, we train a 307M parameter vision transformer on a massive collection of 4.5M images from the Internet and egocentric videos, and demonstrate clearly the benefits of scaling visual pre-training for robot learning.
