Domain adaptive pose estimation via multi-level alignment

arXiv:2404.14885v1 Announce Type: new
Abstract: Domain adaptive pose estimation aims to enable deep models trained on source domain (synthesized) datasets produce similar results on the target domain (real-world) datasets. The existing methods have made significant progress by conducting image-level or feature-level alignment. However, only aligning at a single level is not sufficient to fully bridge the domain gap and achieve excellent domain adaptive results. In this paper, we propose a multi-level domain adaptation aproach, which aligns different domains at the …

abstract alignment arxiv cs.cv datasets domain feature however image progress results synthesized type via world