Transformer-Based Neural Network for Transient Detection without Image Subtraction

TL;DR

This paper presents a transformer-based neural network that improves the accuracy and efficiency of transient detection in astronomical images by eliminating the need for difference imaging, achieving high classification accuracy with less computational cost.

Contribution

The paper introduces a novel transformer-based architecture tailored for transient detection, outperforming CNNs and reducing reliance on difference imaging in astronomical surveys.

Findings

Achieved 97.4% classification accuracy on DES autoScan dataset.

Maintained high performance with non-centered input images.

Reduced computational complexity by avoiding difference imaging.

Abstract

We introduce a transformer-based neural network for the accurate classification of real and bogus transient detections in astronomical images. This network advances beyond the conventional convolutional neural network (CNN) methods, widely used in image processing tasks, by adopting an architecture better suited for detailed pixel-by-pixel comparison. The architecture enables efficient analysis of search and template images only, thus removing the necessity for computationally-expensive difference imaging, while maintaining high performance. Our primary evaluation was conducted using the autoScan dataset from the Dark Energy Survey (DES), where the network achieved a classification accuracy of 97.4% and diminishing performance utility for difference image as the size of the training set grew. Further experiments with DES data confirmed that the network can operate at a similar level even when the input images are not centered on the supernova candidate. These findings highlight the network's effectiveness in enhancing both accuracy and efficiency of supernova detection in large-scale astronomical surveys.