Multi-step Online Unsupervised Domain Adaptation

Abstract

In this paper, we address the Online Unsupervised Domain Adaptation (OUDA) problem, where the target data are unlabelled and arriving sequentially. The traditional methods on the OUDA problem mainly focus on transforming each arriving target data to the source domain, and they do not sufficiently consider the temporal coherency and accumulative statistics among the arriving target data. We propose a multi-step framework for the OUDA problem, which institutes a novel method to compute the mean-target subspace inspired by the geometrical interpretation on the Euclidean space. This mean-target subspace contains accumulative temporal information among the arrived target data. Moreover, the transformation matrix computed from the mean-target subspace is applied to the next target data as a preprocessing step, aligning the target data closer to the source domain. Experiments on four datasets demonstrated the contribution of each step in our proposed multi-step OUDA framework and its performance over previous approaches.

arXiv commentTo appear in ICASSP 2020. Copyright 2020 IEEE

References in corpus (3)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Learning Transferable Features with Deep Adaptation Networks
• Angles between subspaces and their tangents

Cited by in corpus (6)

• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
• Unsupervised Domain Adaptation via Discriminative Manifold Propagation
• A Multi-stage Framework with Mean Subspace Computation and Recursive Feedback for Online Unsupervised Domain Adaptation
• Self-supervised Learning of 3D Object Understanding by Data Association and Landmark Estimation for Image Sequence
• GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation
• Reinforced Domain Selection for Continuous Domain Adaptation