Learning from SAM: Harnessing a Foundation Model for Sim2Real Adaptation by Regularization

Mayara E. Bonani,Max Schwarz,Sven Behnke

CoRR(2023)

引用 0|浏览5
暂无评分
摘要
Domain adaptation is especially important for robotics applications, where target domain training data is usually scarce and annotations are costly to obtain. We present a method for self-supervised domain adaptation for the scenario where annotated source domain data (e.g. from synthetic generation) is available, but the target domain data is completely unannotated. Our method targets the semantic segmentation task and leverages a segmentation foundation model (Segment Anything Model) to obtain segment information on unannotated data. We take inspiration from recent advances in unsupervised local feature learning and propose an invariance-variance loss over the detected segments for regularizing feature representations in the target domain. Crucially, this loss structure and network architecture can handle overlapping segments and oversegmentation as produced by Segment Anything. We demonstrate the advantage of our method on the challenging YCB-Video and HomebrewedDB datasets and show that it outperforms prior work and, on YCB-Video, even a network trained with real annotations. Additionally, we provide insight through model ablations and show applicability to a custom robotic application.
更多
查看译文
关键词
sim2real domain adaptation,regularization,segmentation foundation model,learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要