AI 中文总结
STAMP提出一种仅用源域数据的准则，通过语义配对对比估计OOD性能，在医学和ImageNet模型上超越目标域方法，实现高效部署前模型选择。
AI 中文摘要
预测训练模型在分布偏移下能否泛化仍然困难，尤其是在目标域数据不可用时。我们提出STAMP（语义时间增强模型预测），一种仅使用源域、无目标标签的准则，通过配对的源域图像估计分布外（OOD）性能。STAMP通过对比语义稳定配对与随机配对，计算输出空间相关性比率η²=S_B/S_T：较高的η²表明模型输出随语义身份变化，而非随干扰变化。在涵盖CNN、ViT、MetaFormer、基础模型以及SSL/VLM探针的44个胸部X光模型中，时间STAMP在VinDr-CXR、CheXpert和MIMIC-CXR上实现了与宏观AUROC的Spearman相关系数0.844–0.855；类别匹配变体将单类别RSNA从0.311提升至0.663。STAMP在仅源域医学排序中取得最佳平均表现，并在无任何目标数据情况下优于目标域ATC和AoTL估计器。在27个ImageNet模型上，温度缩放STAMP_TS在ObjectNet上达到ρ=0.984，在四个额外分布偏移上ρ≥0.905，在控制ImageNet准确率后偏相关系数为0.662–0.949。STAMP在每个模型单GPU上约需12秒，是一种实用的部署前模型选择与审计工具。
英文摘要
Predicting whether a trained model will generalize under distribution shift remains difficult, especially when target-domain data are unavailable. We introduce STAMP (Semantic Temporal Augmented Model Prediction), a source-only, target-label-free criterion that estimates out-of-distribution (OOD) performance from paired source-domain images. STAMP computes the output-space correlation ratio $η^2=S_B/S_T$ by contrasting semantically stable pairs with random pairs: higher $η^2$ indicates that model outputs vary with semantic identity rather than nuisance variation. On 44 chest X-ray models spanning CNNs, ViTs, MetaFormers, foundation models, and SSL/VLM probes, temporal STAMP attains Spearman correlations of $0.844$--$0.855$ with macro AUROC on VinDr-CXR, CheXpert, and MIMIC-CXR; a class-matched variant improves single-class RSNA from $0.311$ to $0.663$. STAMP attains the best average source-only medical ranking and outperforms the target-domain ATC and AoTL estimators without any target data. On 27 ImageNet models, temperature-scaled STAMPTS attains $ρ{=}0.984$ on ObjectNet and $ρ\geq0.905$ on four additional distribution shifts, with partial correlations of $0.662$--$0.949$ after controlling for ImageNet accuracy. Requiring approximately 12s per model on one GPU, STAMP is a practical pre-deployment model-selection and auditing tool.
