Unverified80% confidenceFactTime unknown

MixupMP在分类准确率上与最佳基线方法持平甚至更优

1

Sources

80%

Confidence

Long-term

Relevance

5/31/2026

First Seen

Sources

MixupMP: How Data Augmentation Fixes the Uncertainty Quantification Flaws of Deep Ensembles

rss

Related Entities

Related Claims

UnverifiedMixupMP在多个图像分类数据集上，在校准误差和分布外检测指标上优于标准深度集成、MC Dropout和变分推断等方法76% similar UnverifiedMixupMP可作为深度集成的即插即用替代品，无需修改网络架构或训练流程的核心部分70% similar UnverifiedMixupMP方法发表于AISTATS 2024会议66% similar UnverifiedMixupMP所展示的通过预测分布建模改善不确定性量化的思路，可能为大语言模型的幻觉检测和可靠性评估提供新的技术路径66% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/1018

API

curl https://kongchang.com/api/v1/knowledge/claims/1018

MCP

get_claim(id=1018)