視覚運動制御における事前学習の再検討：スクラッチ学習ベースラインの再評価
On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
視覚運動制御タスクにおいて、データ拡張と浅いConvNetを用いた単純なスクラッチ学習ベースラインが、大規模視覚データセットで事前学習した表現を用いる最近の手法（PVR, MVP, R3M）と競合することを示し、事前学習データとベンチマーク間のドメインギャップの影響を明らかにした。
著者: Nicklas Hansen, Zhecheng Yuan, Yanjie Ze, Tongzhou Mu, Aravind Rajeswaran, Hao Su, Huazhe Xu, Xiaolong Wang
分類: cs.LG, cs.CV, cs.RO
原文アブストラクト
In this paper, we examine the effectiveness of pre-training for visuo-motor control tasks. We revisit a simple Learning-from-Scratch (LfS) baseline that incorporates data augmentation and a shallow ConvNet, and find that this baseline is surprisingly competitive with recent approaches (PVR, MVP, R3M) that leverage frozen visual representations trained on large-scale vision datasets -- across a variety of algorithms, task domains, and metrics in simulation and on a real robot. Our results demonstrate that these methods are hindered by a significant domain gap between the pre-training datasets and current benchmarks for visuo-motor control, which is alleviated by finetuning. Based on our findings, we provide recommendations for future research in pre-training for control and hope that our simple yet strong baseline will aid in accurately benchmarking progress in this area.
