超越顶级类别一致性：使用散度预测分布偏移下的性能
Beyond Top-Class Agreement: Using Divergences to Forecast Performance under Distribution Shift
AI总结：
为解决模型在野外数据的泛化预测问题以保障安全部署，研究基于Hellinger距离、Jensen-Shannon和Kullback-Leibler散度的全预测分布分歧方法，实验表明其在分布外数据的测试误差估计和检测率上优于top-1方法，验证了视觉与基础模型场景的有效性。
摘要：
了解模型能否泛化到“野外”数据对安全部署至关重要。为此，我们研究了考虑完整预测分布的模型分歧概念——具体而言是基于Hellinger距离、Jensen-Shannon散度和Kullback-Leibler散度的分歧。我们发现，与基于top-1的对应方法相比，基于散度的分数在分布外数据上能提供更优的测试误差估计和检测率。实验涉及标准视觉模型和基础模型。
英文摘要：
Knowing if a model will generalize to data 'in the wild' is crucial for safe deployment. To this end, we study model disagreement notions that consider the full predictive distribution - specifically disagreement based on Hellinger distance, Jensen-Shannon and Kullback-Leibler divergence. We find that divergence-based scores provide better test error estimates and detection rates on out-of-distribution data compared to their top-1 counterparts. Experiments involve standard vision and foundation models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
