☆ 4.7 Article

They are Not Completely Useless: Towards Recycling Transferable Unlabeled Data for Class-Mismatched Semi-Supervised Learning

IEEE TRANSACTIONS ON MULTIMEDIA (2023)

Related references

Note: Only part of the references are listed.

Article Automation & Control Systems

Laplacian Welsch Regularization for Robust Semisupervised Learning

Jingchen Ke et al.

Summary: In this article, a novel SSL algorithm called Laplacian Welsch regularization (LapWR) is proposed to enhance the robustness of SSL methods to outliers. The algorithm introduces a bounded, smooth, and nonconvex Welsch loss to suppress the adverse effect brought by labeled outliers. An iterative half-quadratic (HQ) optimization algorithm is adopted to handle the model nonconvexity caused by the Welsch loss. Experimental comparisons demonstrate that LapWR performs robustly to outliers and consistently achieves top-level results.

IEEE TRANSACTIONS ON CYBERNETICS (2022)

Add to Collection

Article Computer Science, Information Systems

Anisotropic Graph Convolutional Network for Semi-Supervised Learning

Mahsa Mesgaran et al.

Summary: An anisotropic graph convolutional network is proposed to address the issue of over-smoothing and shrinking effect in semi-supervised node classification, learning nonlinear representations based on local graph structure and node features. Experimental results demonstrate that the approach achieves better or comparable classification accuracy results on citation networks and image datasets compared to standard baseline methods.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Add to Collection

Article Computer Science, Information Systems

Staged Sketch-to-Image Synthesis via Semi-supervised Generative Adversarial Networks

Zeyu Li et al.

Summary: This study introduces a semi-supervised generative adversarial networks-based method for sketch-to-image synthesis, which can directly generate realistic images from novice sketches by incorporating class-wise representations. Compared with state-of-the-art image translation methods, our approach achieves more promising results in terms of Inception Scores and Frechet Inception Distance.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Add to Collection

Article Computer Science, Information Systems

Snowball: Iterative Model Evolution and Confident Sample Discovery for Semi-Supervised Learning on Very Small Labeled Datasets

Yang Li et al.

Summary: This work proposes a joint sample discovery and model evolution method for semi-supervised learning on very small labeled training sets, which significantly improves learning performance according to extensive experiments.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Add to Collection

Article Computer Science, Information Systems

A Mutually Attentive Co-Training Framework for Semi-Supervised Recognition

Shaobo Min et al.

Summary: This paper proposes a novel Mutually Attentive Co-training Framework (MACF) that effectively alleviates the negative impacts of incorrect labels on model retraining by exploring deep model disagreements. MACF trains two symmetrical sub-networks connected by attention modules to reduce noisy gradients from incorrect labels and improve pseudo labels. The experiments show that MACF is more robust to noisy labels than previous methods on various benchmarks.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

WCP: Worst-Case Perturbations for Semi-Supervised Deep Learning

Liheng Zhang et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning

Takeru Miyato et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2019)

Add to Collection

Article Computer Science, Information Systems

Unsupervised and Semi-Supervised Image Classification With Weak Semantic Consistency

Chunjie Zhang et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Semi-Supervised Learning by Augmented Distribution Alignment

Qin Wang et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Tangent-Normal Adversarial Regularization for Semi-supervised Learning

Bing Yu et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Learning to Transfer Examples for Partial Domain Adaptation

Zhangjie Cao et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Multi-Modal Curriculum Learning for Semi-Supervised Image Classification

Chen Gong et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2016)

Add to Collection

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Add to Collection

Article Computer Science, Artificial Intelligence

Fick's Law Assisted Propagation for Semisupervised Learning

Chen Gong et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2015)

Add to Collection

Article Computer Science, Artificial Intelligence

Deformed Graph Laplacian for Semisupervised Learning

Chen Gong et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2015)

Add to Collection

Article Computer Science, Artificial Intelligence

Ensemble Manifold Regularization

Bo Geng et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2012)

Add to Collection

Article

Semi-Supervised Learning (Chapelle, O. et al., Eds.; 2006) [Book reviews]

O. Chapelle et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS (2009)

Add to Collection

Article Computer Science, Artificial Intelligence

Label propagation through linear Neighborhoods

Fei Wang et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2008)

Add to Collection

© Peeref 2019-2024. All rights reserved.