Epoch-evolving Gaussian Process Guided Learning（轮次演化高斯过程引导学习）
Epoch-evolving Gaussian Process Guided Learning
AI总结：
本研究提出轮次演化高斯过程引导学习（GPGL）方案，编码批次与全局数据分布的关联为每轮更新的上下文标签，结合三角一致性损失优化模型，可泛化到深度模型，在多个主流数据集上性能超越现有批次级最优模型。
摘要：
本文提出了一种名为轮次演化高斯过程引导学习（GPGL）的新型学习方案，旨在刻画批次级分布与全局数据分布之间的关联信息。该关联信息被编码为上下文标签，且每轮都需要更新。在上下文标签与真实标签的引导下，GPGL方案通过三角一致性损失更新模型参数，实现了更高效的优化。此外，我们的GPGL方案可进一步泛化，能自然应用于现有深度模型，在主流数据集（CIFAR-10、CIFAR-100和Tiny-ImageNet）上的表现显著优于现有基于批次的最优模型。
英文摘要：
In this paper, we propose a novel learning scheme called epoch-evolving Gaussian Process Guided Learning (GPGL), which aims at characterizing the correlation information between the batch-level distribution and the global data distribution. Such correlation information is encoded as context labels and needs renewal every epoch. With the guidance of the context label and ground truth label, GPGL scheme provides a more efficient optimization through updating the model parameters with a triangle consistency loss. Furthermore, our GPGL scheme can be further generalized and naturally applied to the current deep models, outperforming the existing batch-based state-of-the-art models on mainstream datasets (CIFAR-10, CIFAR-100, and Tiny-ImageNet) remarkably.
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。
