提出UAKNN方法，用不确定感知KNN实现高效标签分布学习。
UAKNN: Label Distribution Learning via Uncertainty-Aware KNN
- 基于不确定感知的KNN机制，无需参数训练
- 12个基准上表现优异，推理速度快适合工业部署
- 解决极端标签空间下的标签分布学习难题
标签分布学习（LDL）旨在通过为实例构建一组描述性程度来刻画其多义性。近年来，研究者尝试通过低秩约束、标签关系建模、专家经验及标签不确定性估计来获得准确的标签分布，多数方法基于线性（含核函数）或深度学习框架中的参数化算法。然而，这些方法因训练成本高、可扩展性差和对异常值敏感，难以在线部署与更新。为此，本文提出一种新型LDL方法UAKNN，结合KNN算法的优势与不确定性建模能力。此外，针对现有方法在极端标签分布空间中的困境，提供了有效解决方案。大量实验表明，该方法在12个基准上显著领先，且推理速度满足工业级应用需求。
原文摘要 · Abstract (English)
Label Distribution Learning (LDL) aims to characterize the polysemy of an instance by building a set of descriptive degrees corresponding to the instance. In recent years, researchers seek to model to obtain an accurate label distribution by using low-rank, label relations, expert experiences, and label uncertainty estimation. In general, these methods are based on algorithms with parameter learning in a linear (including kernel functions) or deep learning framework. However, these methods are difficult to deploy and update online due to high training costs, limited scalability, and outlier sensitivity. To address this problem, we design a novel LDL method called UAKNN, which has the advantages of the KNN algorithm with the benefits of uncertainty modeling. In addition, we provide solutions to the dilemma of existing work on extremely label distribution spaces. Extensive experiments demonstrate that our method is significantly competitive on 12 benchmarks and that the inference speed of the model is well-suited for industrial-level applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。