Beyond Top-Class Agreement: Using Divergences to Forecast Performance under Distribution Shift
CoRR(2023)
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要