POSTURE: Pose Guided Unsupervised Domain Adaptation for Human Body Part Segmentation
Existing algorithms for human body part segmentation have shown promising results on challenging datasets, primarily relying on end-to-end supervision. However, these algorithms exhibit severe performance drops in the face of domain shifts, leading to inaccurate segmentation masks. To tackle this issue, we introduce POSTURE: \underline{Po}se Guided Un\underline{s}upervised Domain Adap\underline{t}ation for H\underline{u}man Body Pa\underline{r}t S\underline{e}gmentation - an innovative pseudo-labelling approach designed to improve segmentation performance on the unlabeled target data. Distinct from conventional domain adaptive methods for general semantic segmentation, POSTURE stands out by considering the underlying structure of the human body and uses anatomical guidance from pose keypoints to drive the adaptation process. This strong inductive prior translates to impressive performance improvements, averaging 8\% over existing state-of-the-art domain adaptive semantic segmentation methods across three benchmark datasets. Furthermore, the inherent flexibility of our proposed approach facilitates seamless extension to source-free settings (SF-POSTURE), effectively mitigating potential privacy and computational concerns, with negligible drop in performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationSegmentationSemantic SegmentationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms
Existing 3D human pose estimation methods often suffer in performance, when applied to cross-scenario inference, due to domain shifts in characteristics such as camera viewpoint, position, posture, and body size. Among t…
3D Human Pose EstimationCross-domain 3D Human Pose EstimationDomain AdaptationPose Estimation+1Unsupervised Domain Adaptation Based on Source-guided Discrepancy
Unsupervised domain adaptation is the problem setting where data generating distributions in the source and target domains are different, and labels in the target domain are unavailable. One important question in unsuper…
Domain AdaptationUnsupervised Domain AdaptationPseudo-Label Guided Unsupervised Domain Adaptation of Contextual Embeddings
Contextual embedding models such as BERT can be easily fine-tuned on labeled samples to create a state-of-the-art model for many downstream tasks. However, the fine-tuned BERT model suffers considerably from unlabeled da…
Domain AdaptationLanguage ModelingLanguage ModellingMasked Language Modeling+3LAGUNA: LAnguage Guided UNsupervised Adaptation with structured spaces
Unsupervised domain adaptation remains a critical challenge in enabling the knowledge transfer of models across unseen domains. Existing methods struggle to balance the need for domain-invariant representations with pres…
Domain AdaptationTransfer LearningUnsupervised Domain AdaptationUncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data
Present domain adaptation methods usually perform explicit representation alignment by simultaneously accessing the source data and target data. However, the source data are not always available due to the privacy preser…
Domain AdaptationPrivacy PreservingSemi-supervised Domain AdaptationSource-Free Domain Adaptation