Metric learning by Similarity Network for Deep Semi-Supervised Learning
This addresses a limitation in semi-supervised learning for domains requiring pairwise relationship modeling, but it appears incremental as it builds on existing co-training frameworks.
The paper tackles the problem of ignoring relationship information between data instances in deep semi-supervised learning by proposing Metric Learning by Similarity Network (MLSN), which learns a distance metric adaptively and achieves better performance on empirical tasks than state-of-the-art methods.
Deep semi-supervised learning has been widely implemented in the real-world due to the rapid development of deep learning. Recently, attention has shifted to the approaches such as Mean-Teacher to penalize the inconsistency between two perturbed input sets. Although these methods may achieve positive results, they ignore the relationship information between data instances. To solve this problem, we propose a novel method named Metric Learning by Similarity Network (MLSN), which aims to learn a distance metric adaptively on different domains. By co-training with the classification network, similarity network can learn more information about pairwise relationships and performs better on some empirical tasks than state-of-art methods.