arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.05134cs.LGstat.ML
收藏

再论神经网络中预测不确定性和分布外检测的One-vs-All分类器

Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks

Google Research, Brain Team(谷歌研究院,Brain团队)

Shreyas Padhy, Zachary Nado, Jie Ren, Jeremiah Liu, Jasper Snoek, Balaji Lakshminarayanan

摘要:

现代神经网络中预测不确定性的准确估计对于实现良好校准的预测和检测分布外(OOD)输入至关重要。最有前途的方法主要集中在改善模型不确定性(例如深度集合和贝叶斯神经网络)和OOD检测的后处理技术(例如ODIN和Mahalanobis距离)。然而,有相对较少的调查如何参数化的概率在判别分类器影响的不确定性估计,和占主导地位的方法,softmax交叉熵,导致误导性的高置信度OOD数据和下协变量偏移。我们研究了使用(1)一对一的公式来捕捉“以上都没有”的概念,以及(2)基于距离的logit表示来将不确定性编码为到训练流形的距离的函数来制定概率的替代方法。我们表明,一对多的公式可以提高图像分类任务的校准,同时匹配softmax的预测性能,而不会产生任何额外的训练或测试时间复杂度。

英文摘要:

Accurate estimation of predictive uncertainty in modern neural networks is critical to achieve well calibrated predictions and detect out-of-distribution (OOD) inputs. The most promising approaches have been predominantly focused on improving model uncertainty (e.g. deep ensembles and Bayesian neural networks) and post-processing techniques for OOD detection (e.g. ODIN and Mahalanobis distance). However, there has been relatively little investigation into how the parametrization of the probabilities in discriminative classifiers affects the uncertainty estimates, and the dominant method, softmax cross-entropy, results in misleadingly high confidences on OOD data and under covariate shift. We investigate alternative ways of formulating probabilities using (1) a one-vs-all formulation to capture the notion of "none of the above", and (2) a distance-based logit representation to encode uncertainty as a function of distance to the training manifold. We show that one-vs-all formulations can improve calibration on image classification tasks, while matching the predictive performance of softmax without incurring any additional training or test-time complexity.

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。

↑