用视觉Transformer和MLP-Mixer提升引力透镜自动识别准确率
GraViT: Transfer Learning with Vision Transformers and MLP-Mixer for Strong Gravitational Lens Discovery
- 结合ViT与MLP-Mixer模型，通过迁移学习实现引力透镜检测
- 在两个数据集上验证，最高分类性能超越传统卷积模型
- 适合天体物理研究者用于大规模引力透镜搜寻
引力透镜是探测暗物质性质和推断宇宙学参数的重要工具。预计下一代巡天项目‘空间与时间遗产调查’（LSST）将在未来十年发现约10⁵个引力透镜，亟需自动化分类器。本文提出GraViT，一个基于PyTorch的引力透镜检测框架，利用先进视觉变压器（ViT）和MLP-Mixer模型进行大规模预训练。通过分析数据质量、样本量、模型架构、微调策略及集成预测等影响因素，系统评估迁移学习对分类性能的影响。研究复现了先前神经网络比较实验，并在共同测试集上提供强引力透镜可探测性的新见解。使用HOLISMOKES VI和SuGOHI X数据集对十种架构进行微调，与卷积基线模型对比，讨论模型复杂度与推理效率。
原文摘要 · Abstract (English)
Gravitational lensing offers a powerful probe into the properties of dark matter and is crucial to infer cosmological parameters. The Legacy Survey of Space and Time (LSST) is predicted to find O(10^5) gravitational lenses over the next decade, demanding automated classifiers. In this work, we introduce GraViT, a PyTorch pipeline for gravitational lens detection that leverages extensive pretraining of state-of-the-art Vision Transformer (ViT) models and MLP-Mixer. We assess the impact of transfer learning on classification performance by examining data quality (source and sample size), model architecture (selection and fine-tuning), training strategies (augmentation, normalization, and optimization), and ensemble predictions. This study reproduces the experiments in a previous systematic comparison of neural networks and provides insights into the detectability of strong gravitational lenses on that common test sample. We fine-tune ten architectures using datasets from HOLISMOKES VI and SuGOHI X, and benchmark them against convolutional baselines, discussing complexity and inference-time analysis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。