Deep-learning Real/Bogus classification for the Tomo-e Gozen transient survey

TL;DR

This paper introduces a deep neural network classifier for the Tomo-e Gozen survey that effectively handles label errors, significantly reducing false positives while maintaining high detection accuracy, thereby improving transient candidate selection efficiency.

Contribution

A novel two-stage training method that detects and unlabeled label errors, enhancing deep learning classification performance in high-volume transient surveys.

Findings

Achieved an AUC of 0.9998 and FPR of 0.0002 at TPR of 0.9.

Reduced transient candidates from ~130 to ~40 objects per night.

Maintained high recovery rate of real transients despite fewer false positives.

Abstract

We present a deep neural network Real/Bogus classifier that improves classification performance in the Tomo-e Gozen transient survey by handling label errors in the training data. In the wide-field, high-frequency transient survey with Tomo-e Gozen, the performance of conventional convolutional neural network classifier is not sufficient as about $10^6$ bogus detections appear every night. In need of a better classifier, we have developed a new two-stage training method. In this training method, label errors in the training data are first detected by normal supervised learning classification, and then they are unlabeled and used for training of semi-supervised learning. For actual observed data, the classifier with this method achieves an area under the curve (AUC) of 0.9998 and a false positive rate (FPR) of 0.0002 at true positive rate (TPR) of 0.9. This training method saves relabeling effort by humans and works better on training data with a high fraction of label errors. By implementing the developed classifier in the Tomo-e Gozen pipeline, the number of transient candidates was reduced to $\sim$40 objects per night, which is $\sim$1/130 of the previous version, while maintaining the recovery rate of real transients. This enables more efficient selection of targets for follow-up observations.