EurekAlert!

Robust semi-supervised learning in open environments

LAMDA-SSL toolkit delivers the first unified benchmarks and robust algorithms that safely exploit unlabeled data despite ...
EurekAlert!

A review on multi-view learning

Review re-maps multi-view learning into four supervised scenarios and three granular sub-tiers, delivering the first unified ...
Frontiers

Semi-supervised segmentation of forest fires from UAV remote sensing images via panoramic feature fusion and pixel contrastive learning

1 School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China 2 College of Information Science and Technology, Nanjing Forestry University, Nanjing, China ...
IEEE

Unsupervised/Semi-Supervised Magnetic Anomaly Detection Method Based on Deep Support Vector Data Description

Abstract: Existing magnetic anomaly detection (MAD) methods are widely categorized into target-, noise-, and machine learning-based methods. This article first analyzes the commonalities and ...
Frontiers

Weight-aware semi-supervised self-ensembling framework for interior decoration style classification

Automatic classification of interior decoration styles has great potential to guide and streamline the design process. Despite recent advancements, it remains challenging to construct an accurate ...
Scientific Research Publishing

Li, Y.G., Xu, C.Y., Tang, X. and Li, X.Y. (2023) A Review of SEMI-Supervised Learning Methods Research. World SCI-TECH R&D, 45, 26-40.

ABSTRACT: With the rapid development of science and technology, artificial intelligence plays a significant role across various domains. In recent years, frequent occurrences of natural disasters and ...
Scientific Research Publishing

Semi-Supervised Stochastic Configuration Networks Based on Manifold Regularization Framework ()

1 School of Mathematics and Statistics, Guilin University of Technology, Guilin, China. 2 Guangxi Colleges and Universities Key Laboratory of Applied Statistics, Guilin, China. The stochastic ...
IEEE

A Novel Comprehensive Semi-Supervised Learning Method for Fault Diagnosis Under Extremely Low Label Rate

Abstract: Intelligent fault diagnosis methods based on deep supervised learning require massive labeled data, which contradicts the typical engineering scenarios. Industrial datasets usually have low ...