RIO: Rotation-equivariance supervised learning of robust inertial odometry

Autor:	Xiya Cao, Caifa Zhou, Dandan Zeng, Yongliang Wang
Jazyk:	angličtina
Rok vydání:	2021
Předmět:	FOS: Computer and information sciences Computer Science - Machine Learning Statistics - Machine Learning Machine Learning (stat.ML) Machine Learning (cs.LG)
Popis:	This paper introduces rotation-equivariance as a self-supervisor to train inertial odometry models. We demonstrate that the self-supervised scheme provides a powerful supervisory signal at training phase as well as at inference stage. It reduces the reliance on massive amounts of labeled data for training a robust model and makes it possible to update the model using various unlabeled data. Further, we propose adaptive Test-Time Training (TTT) based on uncertainty estimations in order to enhance the generalizability of the inertial odometry to various unseen data. We show in experiments that the Rotation-equivariance-supervised Inertial Odometry (RIO) trained with 30% data achieves on par performance with a model trained with the whole database. Adaptive TTT improves models performance in all cases and makes more than 25% improvements under several scenarios. 12 pages, 17 figures, 2 tables
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bd3a3e472914f8f715843ae758b206d4 http://arxiv.org/abs/2111.11676 Zobrazit plný text záznamu