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 2312.06343cs.LG
收藏

RankMatch:一种利用标签间相关性的半监督标签分布学习新方法

RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Inter-label Correlations

Southeast University(东南大学)

Kouzhiqiang Yucheng Xie, Jing Wang, Yuheng Jia, Boyu Shi, Xin Geng

AI总结:

本文提出 RankMatch,通过弱增强集成平均生成伪标签分布并引入 PRR 损失建模标签相关性,在半监督标签分布学习中取得理论保证与优于现有方法的性能。

摘要:

本文介绍了 RankMatch,这是一种用于半监督标签分布学习(SSLDL)的创新方法。为应对标记数据有限的挑战,RankMatch 有效利用少量标记样本以及更大量的未标记数据,从而降低深度神经网络(DNN)应用中对大量人工标注的需求。具体而言,RankMatch 引入了一种受集成学习启发的平均策略,利用多张弱增强图像生成伪标签分布。这不仅稳定了预测,还增强了模型的鲁棒性。此外,RankMatch 结合了成对相关性排序(PRR)损失,以捕捉复杂的标签间相关性,并确保预测的标签分布与真实标签保持一致。我们为 RankMatch 建立了理论泛化界,并通过大量实验证明,其性能优于现有 SSLDL 方法。

英文摘要:

This paper introduces RankMatch, an innovative approach for Semi-Supervised Label Distribution Learning (SSLDL). Addressing the challenge of limited labeled data, RankMatch effectively utilizes a small number of labeled examples in conjunction with a larger quantity of unlabeled data, reducing the need for extensive manual labeling in Deep Neural Network (DNN) applications. Specifically, RankMatch introduces an ensemble learning-inspired averaging strategy that creates a pseudo-label distribution from multiple weakly augmented images. This not only stabilizes predictions but also enhances the model's robustness. Beyond this, RankMatch integrates a pairwise relevance ranking (PRR) loss, capturing the complex inter-label correlations and ensuring that the predicted label distributions align with the ground truth. We establish a theoretical generalization bound for RankMatch, and through extensive experiments, demonstrate its superiority in performance against existing SSLDL 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。

↑