arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.11854cs.LGcs.AI
收藏

基于实例相关标签噪声的二阶学习方法

A Second-Order Approach to Learning with Instance-Dependent Label Noise

University of California Santa Cruz(加州大学圣克鲁兹分校);The University of Sydney(悉尼大学)

Zhaowei Zhu, Tongliang Liu, Yang Liu

摘要:

标签噪声的存在经常误导深度神经网络的训练。与最近的文献在很大程度上假设标签噪声率仅由真实标签类别确定不同,人类注释标签中的错误更可能取决于任务的难度水平,从而导致具有实例相关标签噪声的设置。我们首先提供的证据表明,异构的实例相关的标签噪声是有效地降低权重的例子与较高的噪声率在一个非均匀的方式,从而导致不平衡,呈现的策略,直接适用于类相关的标签噪声的方法值得怀疑。基于最近的工作对等损失[24],我们提出并研究了二阶方法的潜力,该方法利用了在依赖于实例的噪声率和贝叶斯最优标签之间定义的几个协方差项的估计。我们表明,这组二阶统计成功地捕捉到诱导的不平衡。我们进一步表明,与估计的二阶统计量的帮助下,我们确定了一个新的损失函数的分类器的预期风险下的实例相关的标签噪声相当于一个新的问题,只有类相关的标签噪声。这一事实使我们能够应用现有的解决方案来处理这个更好的研究设置。我们提供了一个有效的程序来估计这些二阶统计量,而无需访问地面真值标签或噪声率的先验知识。实验CIFAR10和CIFAR100与合成的实例相关的标签噪声和Clothing1M与现实世界的人类标签噪声验证我们的方法。我们的实现可以在https://github.com/UCSC-REAL/CAL上获得。

英文摘要:

The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined by the true label class, the errors in human-annotated labels are more likely to be dependent on the difficulty levels of tasks, resulting in settings with instance-dependent label noise. We first provide evidences that the heterogeneous instance-dependent label noise is effectively down-weighting the examples with higher noise rates in a non-uniform way and thus causes imbalances, rendering the strategy of directly applying methods for class-dependent label noise questionable. Built on a recent work peer loss [24], we then propose and study the potentials of a second-order approach that leverages the estimation of several covariance terms defined between the instance-dependent noise rates and the Bayes optimal label. We show that this set of second-order statistics successfully captures the induced imbalances. We further proceed to show that with the help of the estimated second-order statistics, we identify a new loss function whose expected risk of a classifier under instance-dependent label noise is equivalent to a new problem with only class-dependent label noise. This fact allows us to apply existing solutions to handle this better-studied setting. We provide an efficient procedure to estimate these second-order statistics without accessing either ground truth labels or prior knowledge of the noise rates. Experiments on CIFAR10 and CIFAR100 with synthetic instance-dependent label noise and Clothing1M with real-world human label noise verify our approach. Our implementation is available at https://github.com/UCSC-REAL/CAL.

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。

↑