Image-Based Multi-Survey Classification of Light Curves with a Pre-Trained Vision Transformer
This work addresses classification challenges for astronomers in time-domain astronomy, but it is incremental as it applies an existing method to new data.
The paper tackled photometric classification of light curves from multiple astronomical surveys (ZTF and ATLAS) using a pre-trained Swin Transformer V2, finding that a joint multi-survey architecture achieved the best performance, though no concrete numbers were provided.
We explore the use of Swin Transformer V2, a pre-trained vision Transformer, for photometric classification in a multi-survey setting by leveraging light curves from the Zwicky Transient Facility (ZTF) and the Asteroid Terrestrial-impact Last Alert System (ATLAS). We evaluate different strategies for integrating data from these surveys and find that a multi-survey architecture which processes them jointly achieves the best performance. These results highlight the importance of modeling survey-specific characteristics and cross-survey interactions, and provide guidance for building scalable classifiers for future time-domain astronomy.