arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.09595cs.LG
收藏

潜在类别条件噪声模型

Latent Class-Conditional Noise Model

Shanghai Jiao Tong University(上海交通大学);Shanghai AI Laboratory(上海人工智能实验室);Hong Kong Baptist University(香港浸会大学);A*STAR Centre for Frontier AI Research(新加坡科技研究局前沿人工智能研究中心)

Jiangchao Yao, Bo Han, Zhihan Zhou, Ya Zhang, Ivor W. Tsang

摘要:

在大数据时代,使用嘈杂的标签进行学习已经变得势在必行,这节省了精确注释的昂贵人力。先前的基于噪声转换的方法已经在类别条件噪声模型(CCN)下实现了理论上的性能。然而,这些方法建立在理想但不切实际的锚点集之上,可用于预先估计噪声过渡。即使后续的工作适应的估计作为一个神经层,其参数在反向传播的不适定的随机学习很容易落入不希望的局部最小值。我们通过引入潜在类条件噪声模型(LCCN)在贝叶斯框架下参数化噪声转换来解决这个问题。通过将噪声过渡投影到Dirichlet空间中,学习被约束在由完整数据集表征的单纯形上,而不是由神经层包裹的一些ad-hoc参数空间。然后,我们推导出一个动态标签回归方法LCCN,其吉布斯采样器允许我们有效地推断潜在的真实标签训练分类器和建模的噪声。我们的方法保障了噪声过渡的稳定更新,避免了先前从小批量样本中任意调整。我们进一步将LCCN推广到与开集噪声标签,半监督学习以及跨模型训练兼容的不同同行。一系列实验证明了LCCN及其变体优于当前最先进方法的优点。

英文摘要:

Learning with noisy labels has become imperative in the Big Data era, which saves expensive human labors on accurate annotations. Previous noise-transition-based methods have achieved theoretically-grounded performance under the Class-Conditional Noise model (CCN). However, these approaches builds upon an ideal but impractical anchor set available to pre-estimate the noise transition. Even though subsequent works adapt the estimation as a neural layer, the ill-posed stochastic learning of its parameters in back-propagation easily falls into undesired local minimums. We solve this problem by introducing a Latent Class-Conditional Noise model (LCCN) to parameterize the noise transition under a Bayesian framework. By projecting the noise transition into the Dirichlet space, the learning is constrained on a simplex characterized by the complete dataset, instead of some ad-hoc parametric space wrapped by the neural layer. We then deduce a dynamic label regression method for LCCN, whose Gibbs sampler allows us efficiently infer the latent true labels to train the classifier and to model the noise. Our approach safeguards the stable update of the noise transition, which avoids previous arbitrarily tuning from a mini-batch of samples. We further generalize LCCN to different counterparts compatible with open-set noisy labels, semi-supervised learning as well as cross-model training. A range of experiments demonstrate the advantages of LCCN and its variants over the current state-of-the-art methods.

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。

↑