paper-with-me

Papers

POSTURE: Pose Guided Unsupervised Domain Adaptation for Human Body Part Segmentation

2024-07-04 · Arindam Dutta, Rohit Lal, Yash Garg, Calvin-Khang Ta, Dripta S. Raychaudhuri, Hannah Dela Cruz, Amit K. Roy-Chowdhury

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.

📄 PDF Abstract BibTeX arXiv:2407.03549

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationSegmentationSemantic SegmentationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms

2025-04-17 · Jingjing Liu, Zhiyong Wang, Xinyu Fan, Amirhossein Dadashzadeh 외

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+1

Unsupervised Domain Adaptation Based on Source-guided Discrepancy

2018-09-11 · Seiichi Kuroki, Nontawat Charoenphakdee, Han Bao, Junya Honda 외

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 Adaptation

Pseudo-Label Guided Unsupervised Domain Adaptation of Contextual Embeddings

2021-04-01 · EACL (AdaptNLP) 2021 4 · Tianyu Chen, Shaohan Huang, Furu Wei, JianXin Li

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+3

LAGUNA: LAnguage Guided UNsupervised Adaptation with structured spaces

2024-11-23 · Anxhelo Diko, Antonino Furnari, Luigi Cinque, Giovanni Maria Farinella

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 Adaptation

Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data

2021-07-14 · Ning Ma, Jiajun Bu, Zhen Zhang, Sheng Zhou

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