Abstract
Noisy partial label learning (noisy PLL) is an important branch of weakly supervised learning. Unlike PLL where the ground-truth label must reside in the candidate set, noisy PLL relaxes this constraint and allows the ground-truth label may not be in the candidate set. To address this problem, existing works attempt to detect noisy samples and estimate the ground-truth label for each noisy sample. However, detection errors are inevitable, and these errors will accumulate during training and continuously affect model optimization. To address this challenge, we propose a novel framework for noisy PLL, called ``Dynamically Adjusted Label Importance (DALI)''. It aims to reduce the negative impact of detection errors by trading off the initial candidate set and model outputs with theoretical guarantees. Experimental results on multiple datasets demonstrate that our DALI succeeds over existing state-of-the-art approaches on noisy PLL. Our code will soon be publicly available.
Abstract (translated)
噪声部分标签学习(噪声PLL)是弱监督学习的一个重要分支。与PLL中,真值标签必须存在于候选集合不同,噪声PLL放松了这个约束,允许真值标签可能不在候选集合中。为了解决这个问题,现有的工作试图检测噪声样本并估计每个噪声样本的真值标签。然而,检测错误是不可避免的,这些错误将在训练期间累积,并持续影响模型优化。为了解决这个挑战,我们提出了一个 novel 框架,称为“Dynamically Adjusted Label Importance (DALI)”,它旨在通过理论保证来 trade off 初始候选集合和模型输出,以减少检测错误的负面影响。多个数据集的实验结果显示,我们的 DALI 在噪声PLL方面比现有的方法更有效。我们的代码将很快公开可用。
URL
https://arxiv.org/abs/2301.12077
