Pre-training vision models for the classification of alerts from wide-field time-domain surveys

TL;DR

This paper demonstrates that pre-trained, standardized CNN architectures, especially those pre-trained on galaxy images, outperform custom models in classifying alerts from wide-field time-domain surveys, offering improved efficiency and accuracy.

Contribution

It shows that adopting pre-trained, standardized vision models from computer vision significantly enhances alert classification in astronomy, surpassing custom CNNs in performance and efficiency.

Findings

Pre-trained models match or outperform custom CNNs.

Galaxy Zoo pre-training yields better results than ImageNet.

Standard architectures are more efficient than custom models.

Abstract

Modern wide-field time-domain surveys facilitate the study of transient, variable and moving phenomena by conducting image differencing and relaying alerts to their communities. Machine learning tools have been used on data from these surveys and their precursors for more than a decade, and convolutional neural networks (CNNs), which make predictions directly from input images, saw particularly broad adoption through the 2010s. Since then, continually rapid advances in computer vision have transformed the standard practices around using such models. It is now commonplace to use standardized architectures pre-trained on large corpora of everyday images (e.g., ImageNet). In contrast, time-domain astronomy studies still typically design custom CNN architectures and train them from scratch. Here, we explore the effects of adopting various pre-training regimens and standardized model architectures on the performance of alert classification. We find that the resulting models match or outperform a custom, specialized CNN like what is typically used for filtering alerts. Moreover, our results show that pre-training on galaxy images from Galaxy Zoo tends to yield better performance than pre-training on ImageNet or training from scratch. We observe that the design of standardized architectures are much better optimized than the custom CNN baseline, requiring significantly less time and memory for inference despite having more trainable parameters. On the eve of the Legacy Survey of Space and Time and other image-differencing surveys, these findings advocate for a paradigm shift in the creation of vision models for alerts, demonstrating that greater performance and efficiency, in time and in data, can be achieved by adopting the latest practices from the computer vision field.