Domain Constraint Approximation based Semi Supervision
This work addresses the challenge of expensive and rare annotated data in machine learning, offering a semi-supervised approach that is incremental in nature.
The paper tackles the problem of limited labeled data in deep learning by proposing a fuzzy domain-constraint-based framework for semi-supervised learning, which relaxes traditional constraint requirements and improves model quality, with simulations demonstrating its effectiveness.
Deep learning for supervised learning has achieved astonishing performance in various machine learning applications. However, annotated data is expensive and rare. In practice, only a small portion of data samples are annotated. Pseudo-ensembling-based approaches have achieved state-of-the-art results in computer vision related tasks. However, it still relies on the quality of an initial model built by labeled data. Less labeled data may degrade model performance a lot. Domain constraint is another way regularize the posterior but has some limitation. In this paper, we proposed a fuzzy domain-constraint-based framework which loses the requirement of traditional constraint learning and enhances the model quality for semi supervision. Simulations results show the effectiveness of our design.