返回
SLOVA: Uncertainty estimation using single label one-vs-all classifier
DOI:10.1016/j.asoc.2022.109219.png)
摘要
En 中文
Deep neural networks present impressive performance, yet they cannot reliably estimate their predictive confidence, limiting their applicability in high-risk domains. We show that applying a multi -label one-vs-all loss reveals classification ambiguity and reduces model overconfidence. The introduced SLOVA (Single Label One-Vs-All) model redefines typical one-vs-all predictive probabilities to a single label situation, where only one class is the correct answer. The proposed classifier is confident only if a single class has a high probability and other probabilities are negligible. Unlike the typical softmax function, SLOVA naturally detects out-of-distribution samples if the probabilities of all other classes are small. The model is additionally fine-tuned with exponential calibration, which allows us to precisely align the confidence score with model accuracy. We verify our approach on three tasks. First, we demonstrate that SLOVA is competitive with the state-of-the-art on in-distribution calibration. Second, the performance of SLOVA is robust under dataset shifts. Finally, our approach performs extremely well in the detection of out-of-distribution samples. Consequently, SLOVA is a tool that can be used in various applications where uncertainty modeling is required. (c) 2022 Elsevier B.V. All rights reserved.
Keyword:
Uncertainty
One-vs-all
Calibration
Distribution shift
Out-of-distribution
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.6
论文数:
1.4W
被引数:
4.8W
机构
引用论文
Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records深度患者: 从电子健康记录中预测患者未来的无监督表示
SCIENTIFIC REPORTS
IF3.9
Duration of Herbivore Removal and Environmental Stress Affect the Ectomycorrhizae of Pinyon Pines
Ecology
IF0
Femtosecond Charge Transfer Dynamics of a Modified DNA Base: 2-Aminopurine in Complexes with Nucleotides
ChemPhysChem
IF0

