Semi-Supervised Clustering with Neural Networks
This work addresses the challenge of clustering in semi-supervised settings for machine learning and computer vision applications, offering an incremental improvement over existing methods.
The authors tackled the problem of clustering with limited labeled data by proposing ClusterNet, which uses pairwise semantic constraints from very few labeled samples (<5%) and unlabeled data to improve clustering performance, achieving competitive results compared to state-of-the-art deep clustering approaches.
Clustering using neural networks has recently demonstrated promising performance in machine learning and computer vision applications. However, the performance of current approaches is limited either by unsupervised learning or their dependence on large set of labeled data samples. In this paper, we propose ClusterNet that uses pairwise semantic constraints from very few labeled data samples (<5% of total data) and exploits the abundant unlabeled data to drive the clustering approach. We define a new loss function that uses pairwise semantic similarity between objects combined with constrained k-means clustering to efficiently utilize both labeled and unlabeled data in the same framework. The proposed network uses convolution autoencoder to learn a latent representation that groups data into k specified clusters, while also learning the cluster centers simultaneously. We evaluate and compare the performance of ClusterNet on several datasets and state of the art deep clustering approaches.