GaussianMatch：基于多视图高斯一致性的伪标签过滤半监督回归
GaussianMatch: Semi-Supervised Regression with Pseudo-Label Filtering via Multi-View Gaussian Consistency
论文提出的高斯一致性过滤（GCF）与自适应高斯标准差平滑（AGDS）为视觉回归任务（如年龄估计、人脸关键点回归）在标签稀缺时提供了一种可复用的伪标签筛选机制，通过多视图预测一致性量化置信度，可直接嵌入半监督训练流程。
原文依据 GaussianMatch, a novel SSR framework enabling high-quality pseudo-label filtering, which selects reliable pseudo-labels through multi-view prediction consistency under feature-space smoothness assumptions.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论半监督回归（SSR）在情感分析和医疗保健等标注数据有限但无标注数据丰富的领域至关重要。尽管具有实际重要性，但由于缺乏针对连续输出的有效伪标签策略，SSR 仍未得到充分探索。与分类不同，回归缺乏固有的置信度度量，使得过滤和信任伪标签更加困难。这一局限导致低质量伪标签在训练过程中未经适当验证便传播，显著放大了 SSR 框架中的预测误差。在本工作中，我们提出了 GaussianMatch，一种新颖的 SSR 框架，能够实现高质量的伪标签过滤，其在特征空间平滑假设下通过多视图预测一致性选择可靠的伪标签。它引入了两项关键创新：1）高斯一致性过滤器（GCF），通过高斯相似度评分量化弱增强视图间的预测一致性，仅当所有预测均落在置信区间内时才保留伪标签；2）自适应高斯标准差平滑（AGDS），通过贝叶斯正则化课程增强 GCF 的鲁棒性，该课程将置信区间从预热阶段的保守边界逐步过渡到逐渐收紧的阈值。AGDS 的使用确保了训练全程稳定可靠的伪标签过滤。大量实验表明，GaussianMatch 在不同数据条件下均表现强劲，在极端标签稀缺情况下展现出显著的鲁棒性。例如，在 UTKFace（30 个标签）上，它超越了当前最优方法，将误差降低了 15.36%，并将决定系数提高了 50.21%。我们的代码可在 https://github.com/pywin/GaussianMatch 获取。
英文原文摘要 1791 字符
Semi-Supervised Regression (SSR) is essential in domains like sentiment analysis and healthcare where labeled data is limited but unlabeled data is plentiful. Despite its practical importance, SSR remains underexplored due to the lack of effective pseudo-labeling strategies for continuous outputs. Unlike classification, regression lacks inherent confidence measures, making it harder to filter and trust pseudo-labels. This limitation permits low-quality pseudo-labels to propagate during training without proper validation, significantly amplifying prediction errors in SSR frameworks. In this work, we propose GaussianMatch, a novel SSR framework enabling high-quality pseudo-label filtering, which selects reliable pseudo-labels through multi-view prediction consistency under feature-space smoothness assumptions. It has introduces two key innovations: 1) Gaussian Consistency Filter (GCF) that quantifies prediction consistency across weakly augmented views through Gaussian similarity scoring, retaining pseudo-labels only when all predictions fall within a confidence interval; 2) Adaptive Gaussian Standard Deviation Smoothing (AGDS) that enhances GCF's robustness through a Bayesian-regularized curriculum that phases confidence intervals from warm-up conservative bounds to progressively tightened thresholds. The use of AGDS ensures stable and reliable pseudo-label filtering throughout training. Extensive experiments demonstrate that GaussianMatch performs strongly across varying data conditions, showing notable robustness under extreme label scarcity. For instance, it outperforms the state of the art on UTKFace (30 labels), reducing error by 15.36% and improving the Coefficient of Determination by 50.21%. Our code is available at https://github.com/pywin/GaussianMatch.