星系形态分类：不确定性建模与分布外检测
Galaxy Morphology Classification: Uncertainty Modeling and Out of Distribution Detection
AI总结：
该研究提出结合IsoMaxPlus损失与蒙特卡洛 dropout的ResNet-34框架，提升星系形态分类的分布外检测与不确定性量化，在9类星系上保持97%准确率，校准误差大幅降低，适用于大规模巡天。
AI中文摘要：
我们提出了一个用于星系形态分类的综合框架，该框架结合了增强的“分布外（OOD）”检测与改进的不确定性量化。使用“Galaxy Zoo DECaLS”数据集，我们在三种配置下训练了ResNet-34架构：以标准交叉熵损失作为基线、用于OOD检测的IsoMaxPlus损失函数，以及用于增强不确定性量化的混合IsoMaxPlus+蒙特卡洛 dropout（MonteCarlo Dropout）。IsoMaxPlus将传统的SoftMax对数几率替换为基于距离的类别表示，保留了类别间的可分性，无需额外的架构修改或超参数调整即可实现可靠的OOD检测。将IsoMaxPlus与MC Dropout结合，通过在推理过程中执行多次随机前向传播，提供了一种快速的贝叶斯近似方法。我们的结果表明，IsoMaxPlus大幅提升了OOD检测性能，相较于交叉熵基线，TNR@TPR95提高了近90%，同时在9个形态类别上保持了97%的竞争力准确率。此外，结合MC Dropout后，模型预测更稳定，校准误差降低，提供了更可靠的不确定性估计。与基线相比，IsoMaxPlus的预期校准误差（ECE）从0.0095降至0.0026（约73%），结合MC Dropout后降至0.0033（约65%）。分类错误或置信度不足的预测表现出更高的预测熵和更低的最小距离分数，为识别不可靠预测提供了可解释的指标。这些方法非常适用于当前及未来的大规模巡天项目，在这类项目中，可靠的自动形态分类及不确定性感知对于识别稀有或此前未被发现的星系形态至关重要。
英文摘要：
We present a comprehensive framework for galaxy morphology classification that combines enhanced ``out-of-distribution (OOD)'' detection with improved uncertainty quantification. Using ``Galaxy Zoo DECaLS'', we trained a ResNet-34 architecture under three configurations: standard cross-entropy loss as a baseline, IsoMaxPlus loss function for OOD detection, and hybrid IsoMaxPlus+MonteCarlo Dropout for enhanced uncertainty quantification. IsoMaxPlus replaces the conventional SoftMax logits with distance-based class representations, preserving inter-class separability and enabling reliable OOD detection, without requiring additional architectural modifications or hyperparameter tuning. Coalescing IsoMaxPlus with MC Dropout provides a fast Bayesian approximation by performing multiple stochastic forward passes during inference. Our results show that IsoMaxPlus substantially improves OOD detection, increasing TNR@TPR95 by nearly $90\%$ relative to the cross-entropy baseline, while maintaining a competitive accuracy of 97\% across nine morphological classes. Additionally, with MC Dropout, the model yields more stable predictions and a reduction in calibration error, providing more reliable uncertainty estimates. The Expected Calibration Error (ECE) is reduced from $0.0095$ to $0.0026$ ($\approx73\%$) for IsoMaxPlus and $0.0033$ ($\approx65\%$) when combined with MC Dropout, compared to the baseline. Misclassified or underconfident predictions exhibit higher predictive entropy and lower minimum distance scores, providing an interpretable metric for identifying unreliable predictions. These methods are well-suited for current and upcoming large-scale surveys, where reliable automated morphological classification and awareness of uncertainty are essential for identifying rare or previously unseen galaxy morphologies.
