Unsupervised Star Galaxy Classification with Cascade Variational Auto-Encoder
This addresses the challenge of processing large astronomical datasets without manual labeling, though it appears incremental as it builds on existing unsupervised methods for a specific task.
The paper tackles the star-galaxy classification problem in astronomy by proposing an unsupervised approach, achieving improved accuracy and stability compared to a baseline model.
The increasing amount of data in astronomy provides great challenges for machine learning research. Previously, supervised learning methods achieved satisfactory recognition accuracy for the star-galaxy classification task, based on manually labeled data set. In this work, we propose a novel unsupervised approach for the star-galaxy recognition task, namely Cascade Variational Auto-Encoder (CasVAE). Our empirical results show our method outperforms the baseline model in both accuracy and stability.