GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap
It addresses a challenging problem for video action recognition by handling large domain gaps, which is more realistic than prior incremental work.
The paper tackles unsupervised video domain adaptation for action recognition with large domain gaps, introducing a new Kinetics->BABEL scenario and achieving significant improvements over existing methods.
In this work, we tackle the challenging problem of unsupervised video domain adaptation (UVDA) for action recognition. We specifically focus on scenarios with a substantial domain gap, in contrast to existing works primarily deal with small domain gaps between labeled source domains and unlabeled target domains. To establish a more realistic setting, we introduce a novel UVDA scenario, denoted as Kinetics->BABEL, with a more considerable domain gap in terms of both temporal dynamics and background shifts. To tackle the temporal shift, i.e., action duration difference between the source and target domains, we propose a global-local view alignment approach. To mitigate the background shift, we propose to learn temporal order sensitive representations by temporal order learning and background invariant representations by background augmentation. We empirically validate that the proposed method shows significant improvement over the existing methods on the Kinetics->BABEL dataset with a large domain gap. The code is available at https://github.com/KHUVLL/GLAD.