Integrating Distribution Matching into Semi-Supervised Contrastive Learning for Labeled and Unlabeled Data
By: Shogo Nakayama, Masahiro Okuda
Potential Business Impact:
Teaches computers to learn from pictures without labels.
The advancement of deep learning has greatly improved supervised image classification. However, labeling data is costly, prompting research into unsupervised learning methods such as contrastive learning. In real-world scenarios, fully unlabeled datasets are rare, making semi-supervised learning (SSL) highly relevant in scenarios where a small amount of labeled data coexists with a large volume of unlabeled data. A well-known semi-supervised contrastive learning approach involves assigning pseudo-labels to unlabeled data. This study aims to enhance pseudo-label-based SSL by incorporating distribution matching between labeled and unlabeled feature embeddings to improve image classification accuracy across multiple datasets.
Similar Papers
CGMatch: A Different Perspective of Semi-supervised Learning
CV and Pattern Recognition
Teaches computers better with less examples.
Enhancing Semi-supervised Learning with Zero-shot Pseudolabels
Machine Learning (CS)
Teaches computers to learn with less labeled data.
Semi-Supervised Learning under General Causal Models
Machine Learning (Stat)
Teaches computers with less labeled examples.