Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridges

2026-08-20

AI Summary

本文针对长尾分布和噪声伪标签问题，提出了一种基于高斯特征桥的半监督学习框架GBC，通过动态原型图谱和桥一致性损失提高模型泛化能力。

Abstract

Real-world semi-supervised learning (SSL) often encounters significant challenges with long-tailed label distributions and noisy pseudo-labels, which hinder generalization and amplify confirmation bias. In this work, we introduce a novel framework, Gaussian Bridge Consistency (GBC), to address these challenges by constructing semantic interpolation paths between unlabeled samples and high-quality class anchors. Our method maintains a dynamic Prototype Atlas that stores a diverse and evolving set of labeled and pseudo-labeled exemplars per class. For each unlabeled instance, GBC forms a class-conditional Gaussian Feature Bridge in the latent space, enabling the student model to traverse a smooth trajectory from uncertain predictions to reliable class prototypes. A bridge consistency loss is applied along this path to enforce alignment with a geometrically interpolated target distribution. Furthermore, we propose BridgeMix, a confidence-aware feature mixing strategy that interpolates both sample and anchor pairs to amplify cross-sample generalization. Extensive experiments on CIFAR10-LT and ImageNet-LT (USB benchmarks) validate the robustness and effectiveness of GBC under realistic long-tailed SSL settings, consistently improving long tail-class performance without sacrificing scalability.

Problem

• Semi-Supervised Learning
• Long-Tailed Label Distributions
• Noisy Pseudo-Labels
• Generalization
• Confirmation Bias

Innovation

• Gaussian Bridge Consistency
• Prototype Atlas
• BridgeMix
• long-tailed SSL