# Domain Adaptation via Minimax Entropy for Real/Bogus Classification of Astronomical Alerts

arXiv: https://arxiv.org/abs/2308.07538 · HTML: https://mlsanity.com/paper/2308.07538/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 23 references that are in the map.
- First posted on arXiv 15 Aug 2023.

## Builds on (most cited first, 5 of 5)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection](https://mlsanity.com/paper/1701.00458/) (2017)
- [Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier](https://mlsanity.com/paper/2008.03309/) (2020)
- [A Two-Stage Deep Learning Detection Classifier for the ATLAS Asteroid Survey](https://mlsanity.com/paper/2101.08912/) (2021)

## Built on by (most cited first, 3 of 3)

- [Weak-to-Strong Generalization via Direct On-Policy Distillation](https://mlsanity.com/paper/2607.05394/) (2026)
- [Domain-Adaptive Neural Posterior Estimation for Strong Gravitational Lens Analysis](https://mlsanity.com/paper/2410.16347/) (2024)
- [Textual interpretation of transient image classifications from large language models](https://mlsanity.com/paper/2510.06931/) (2025)

## Abstract (arXiv)

Time domain astronomy is advancing towards the analysis of multiple massive datasets in real time, prompting the development of multi-stream machine learning models. In this work, we study Domain Adaptation (DA) for real/bogus classification of astronomical alerts using four different datasets: HiTS, DES, ATLAS, and ZTF. We study the domain shift between these datasets, and improve a naive deep learning classification model by using a fine tuning approach and semi-supervised deep DA via Minimax Entropy (MME). We compare the balanced accuracy of these models for different source-target scenarios. We find that both the fine tuning and MME models improve significantly the base model with as few as one labeled item per class coming from the target dataset, but that the MME does not compromise its performance on the source dataset.