References & Citations
Computer Science > Computer Vision and Pattern Recognition
Title: Domain adaptive pose estimation via multi-level alignment
(Submitted on 23 Apr 2024 (v1), last revised 25 Apr 2024 (this version, v2))
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 image, feature, and pose levels. Specifically, we first utilize image style transer to ensure that images from the source and target domains have a similar distribution. Subsequently, at the feature level, we employ adversarial training to make the features from the source and target domains preserve domain-invariant characeristics as much as possible. Finally, at the pose level, a self-supervised approach is utilized to enable the model to learn diverse knowledge, implicitly addressing the domain gap. Experimental results demonstrate that significant imrovement can be achieved by the proposed multi-level alignment method in pose estimation, which outperforms previous state-of-the-art in human pose by up to 2.4% and animal pose estimation by up to 3.1% for dogs and 1.4% for sheep.
Submission history
From: Yugan Chen [view email][v1] Tue, 23 Apr 2024 10:13:31 GMT (1348kb,D)
[v2] Thu, 25 Apr 2024 07:38:25 GMT (1804kb,D)
Link back to: arXiv, form interface, contact.