用数学方法提升天文图像识别效率与精度，小模型也能高准确率
Compact neural networks for astronomy with optimal transport bias correction
- 结合小波分解与状态空间模型，设计轻量级神经网络
- 64x64分辨率下准确率达81.72%，参数仅354万，计算效率提升9.7倍
- 无需显式选源函数即可减少26.10%异常值，适合天文数据科学应用
天文成像面临效率与分辨率的权衡，制约大规模形态分类与红移预测。我们提出WaveletMamba，一种融合小波分解、状态空间建模、数学正则化与多层级偏差校正的理论驱动框架。该框架在64×64分辨率下实现81.72% ± 0.53%的分类准确率，仅需354万参数；在低分辨率输入下仍保持244×244分辨率的80.93% ± 0.27%准确率，计算效率提升9.7倍。框架表现出分辨率多稳定性：尽管内部表示不同，低分辨率训练模型在不同输入尺度上保持一致准确率。其多层级偏差校正结合HK距离（分布级最优传输）与颜色感知加权（样本级微调），实现22.96%的Log-MSE改进与26.10%的异常值减少，无需显式选源函数建模。结果表明，数学严谨性可推动科学人工智能在效率与偏差校正上的突破，连接计算机视觉与天体物理学，助力跨学科科学发现。
原文摘要 · Abstract (English)
Astronomical imaging confronts an efficiency-resolution tradeoff that limits large-scale morphological classification and redshift prediction. We introduce WaveletMamba, a theory-driven framework integrating wavelet decomposition with state-space modeling, mathematical regularization, and multi-level bias correction. WaveletMamba achieves 81.72% +/- 0.53% classification accuracy at 64x64 resolution with only 3.54M parameters, delivering high-resolution performance (80.93% +/- 0.27% at 244x244) at low-resolution inputs with 9.7x computational efficiency gains. The framework exhibits Resolution Multistability, where models trained on low-resolution data achieve consistent accuracy across different input scales despite divergent internal representations. The framework's multi-level bias correction synergizes HK distance (distribution-level optimal transport) with Color-Aware Weighting (sample-level fine-tuning), achieving 22.96% Log-MSE improvement and 26.10% outlier reduction without explicit selection function modeling. Here, we show that mathematical rigor enables unprecedented efficiency and comprehensive bias correction in scientific AI, bridging computer vision and astrophysics to revolutionize interdisciplinary scientific discovery.
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。