paper-with-me

홈 › Papers

Universal Semi-Supervised Learning

2021-12-01 · NeurIPS 2021 12 · Zhuo Huang, Chao Xue, Bo Han, Jian Yang, Chen Gong

Universal Semi-Supervised Learning (UniSSL) aims to solve the open-set problem where both the class distribution (i.e., class set) and feature distribution (i.e., feature domain) are different between labeled dataset and unlabeled dataset. Such a problem seriously hinders the realistic landing of classical SSL. Different from the existing SSL methods targeting at the open-set problem that only study one certain scenario of class distribution mismatch and ignore the feature distribution mismatch, we consider a more general case where a mismatch exists in both class and feature distribution. In this case, we propose a ''Class-shAring data detection and Feature Adaptation'' (CAFA) framework which requires no prior knowledge of the class relationship between the labeled dataset and unlabeled dataset. Particularly, CAFA utilizes a novel scoring strategy to detect the data in the shared class set. Then, it conducts domain adaptation to fully exploit the value of the detected class-sharing data for better semi-supervised consistency training. Exhaustive experiments on several benchmark datasets show the effectiveness of our method in tackling open-set problems.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation

Similar Papers 제목 키워드 기반

ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-Labeling

2025-11-19 · Yaxiong Chen, Qicong Wang, Chunlei Li, Jingliang Hu 외 arxiv

Existing approaches for the problem of ultrasound image segmentation, whether supervised or semi-supervised, are typically specialized for specific anatomical structures or tasks, limiting their practical utility in clin…

Image Segmentation

Universal Semi-Supervised Semantic Segmentation

2018-11-26 · ICCV 2019 10 · Tarun Kalluri, Girish Varma, Manmohan Chandraker, C. V. Jawahar

In recent years, the need for semantic segmentation has arisen across several different applications and environments. However, the expense and redundancy of annotation often limits the quantity of labels available for t…

Domain AdaptationSegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation+1

Regularized Boost for Semi-Supervised Learning

2007-12-01 · NeurIPS 2007 12 · Ke Chen, Shihai Wang

Semi-supervised inductive learning concerns how to learn a decision rule from a data set containing both labeled and unlabeled data. Several boosting algorithms have been extended to semi-supervised learning with various…

Ensemble LearningInductive Learning

Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias

2024-03-17 · CVPR 2024 1 · Wenyu Zhang, Qingmu Liu, Felix Ong Wei Cong, Mohamed Ragab 외

Domain adaptation is a critical task in machine learning that aims to improve model performance on a target domain by leveraging knowledge from a related source domain. In this work, we introduce Universal Semi-Supervise…

Domain AdaptationPseudo LabelSemi-supervised Domain AdaptationUniversal Domain Adaptation

Semi-supervised Hashing for Semi-Paired Cross-View Retrieval

2018-06-19 · Jun Yu, Xiao-Jun Wu, Josef Kittler

Recently, hashing techniques have gained importance in large-scale retrieval tasks because of their retrieval speed. Most of the existing cross-view frameworks assume that data are well paired. However, the fully-paired …

Retrieval