用子片段预测方差提升模型不确定性估计效率
Efficient Post-Hoc Uncertainty Calibration via Variance-Based Smoothing
- 通过输入子片段的预测方差衡量不确定性
- 在分类任务中达到媲美先进方法的准确度
- 适合作为轻量级后处理校准工具，适合部署场景
由于当前先进的不确定性估计方法通常计算开销大，我们探讨是否可借助先验信息改进传统深度神经网络的不确定性估计。研究聚焦于能从输入子部分做出有意义预测的任务，如说话人识别中，语音波形可划分为连续片段，每个片段均包含同一说话人的信息。我们观察到，子预测间的方差在这些场景下是可靠的不确定性代理指标。所提出的基于方差的缩放框架，在分类任务中生成具有竞争力的不确定性估计，计算成本更低，且可作为后处理校准工具集成。该方法还简单扩展了深度集成，提升了其预测分布的表达能力。
原文摘要 · Abstract (English)
Since state-of-the-art uncertainty estimation methods are often computationally demanding, we investigate whether incorporating prior information can improve uncertainty estimates in conventional deep neural networks. Our focus is on machine learning tasks where meaningful predictions can be made from sub-parts of the input. For example, in speaker classification, the speech waveform can be divided into sequential patches, each containing information about the same speaker. We observe that the variance between sub-predictions serves as a reliable proxy for uncertainty in such settings. Our proposed variance-based scaling framework produces competitive uncertainty estimates in classification while being less computationally demanding and allowing for integration as a post-hoc calibration tool. This approach also leads to a simple extension of deep ensembles, improving the expressiveness of their predicted distributions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。