伪标签与标签平滑在噪声部分标签学习中的结合
Pseudo-labelling meets Label Smoothing for Noisy Partial Label Learning
AI总结：
本文针对噪声部分标签学习问题，提出一种结合加权最近邻伪标签生成、标签平滑训练和迭代伪标签细化的框架，在多个数据集上取得了最先进性能。
摘要：
我们提出弱监督学习作为一种有效的学习范式，适用于那些获取完美标注数据集成本高昂且可能需要领域专业知识的问题，例如细粒度分类。我们重点关注部分标签学习（Partial Label Learning, PLL），这是一种弱监督学习范式，其中每个训练实例都与一组候选标签（部分标签）配对，其中一个标签是真实标签。噪声部分标签学习（Noisy PLL, NPLL）通过允许某些部分标签不包含真实标签来放宽这一约束，从而增强了问题的实用性。我们的工作以NPLL为中心，提出了一个框架，该框架首先通过加权最近邻算法利用噪声部分标签为图像分配伪标签。然后，这些伪标签与图像对用于训练带有标签平滑的深度神经网络分类器。随后，利用该分类器的特征和预测来细化并提高伪标签的准确性。我们在七个数据集上进行了全面的实验，并与九种NPLL和PLL方法进行了比较。我们在先前文献中研究的所有设置下都取得了最先进的结果，在模拟的细粒度基准上获得了显著的性能提升。此外，我们展示了该框架在现实的、细粒度的、众包数据集上具有良好的泛化能力。
英文摘要：
We motivate weakly supervised learning as an effective learning paradigm for problems where curating perfectly annotated datasets is expensive and may require domain expertise such as fine-grained classification. We focus on Partial Label Learning (PLL), a weakly-supervised learning paradigm where each training instance is paired with a set of candidate labels (partial label), one of which is the true label. Noisy PLL (NPLL) relaxes this constraint by allowing some partial labels to not contain the true label, enhancing the practicality of the problem. Our work centres on NPLL and presents a framework that initially assigns pseudo-labels to images by exploiting the noisy partial labels through a weighted nearest neighbour algorithm. These pseudo-label and image pairs are then used to train a deep neural network classifier with label smoothing. The classifier's features and predictions are subsequently employed to refine and enhance the accuracy of pseudo-labels. We perform thorough experiments on seven datasets and compare against nine NPLL and PLL methods. We achieve state-of-the-art results in all studied settings from the prior literature, obtaining substantial gains in the simulated fine-grained benchmarks. Further, we show the promising generalisation capability of our framework in realistic, fine-grained, crowd-sourced datasets.
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。
