Stem-OB: 拡散逆変換による幹状収束観測を用いた汎化可能な視覚模倣学習
Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion
事前学習済み拡散モデルの逆変換で観測画像から照明やテクスチャの違いを除去し、追加学習なしで視覚模倣学習の汎化性能を高めるプラグアンドプレイ手法を提案した。
著者: Kaizhe Hu, Zihang Rui, Yao He, Yuyao Liu, Pu Hua, Huazhe Xu
分類: cs.RO, cs.CV
原文アブストラクト
Visual imitation learning methods demonstrate strong performance, yet they lack generalization when faced with visual input perturbations, including variations in lighting and textures, impeding their real-world application. We propose Stem-OB that utilizes pretrained image diffusion models to suppress low-level visual differences while maintaining high-level scene structures. This image inversion process is akin to transforming the observation into a shared representation, from which other observations stem, with extraneous details removed. Stem-OB contrasts with data-augmentation approaches as it is robust to various unspecified appearance changes without the need for additional training. Our method is a simple yet highly effective plug-and-play solution. Empirical results confirm the effectiveness of our approach in simulated tasks and show an exceptionally significant improvement in real-world applications, with an average increase of 22.2% in success rates compared to the best baseline. See https://hukz18.github.io/Stem-Ob/ for more info.
