动态阈值与重采样提升3D半监督学习中少数类性能
DyConfidMatch: Dynamic Thresholding and Re-sampling for 3D Semi-supervised Learning
- 基于类别置信度动态调整标签阈值，优化未标记数据利用
- 在3D分类与检测任务上超越现有方法，显著改善少数类表现
- 适合处理3D点云数据中类别不平衡问题的研究者
半监督学习（SSL）利用少量标注数据和大量未标注数据，但在3D场景中常面临数据分布不均的问题。本文研究了类别级置信度作为3D SSL中学习状态的指标，提出一种新方法：通过动态阈值策略更有效地利用未标注数据，尤其是低频类别。同时引入重采样策略，缓解对高频类别的偏差，确保各类别均衡表示。在多个3D SSL任务上的大量实验表明，该方法在分类与检测任务上均优于当前最优模型，有效解决了数据不平衡问题。本方法为3D数据集的半监督学习提供了稳健的解决方案。
原文摘要 · Abstract (English)
Semi-supervised learning (SSL) leverages limited labeled and abundant unlabeled data but often faces challenges with data imbalance, especially in 3D contexts. This study investigates class-level confidence as an indicator of learning status in 3D SSL, proposing a novel method that utilizes dynamic thresholding to better use unlabeled data, particularly from underrepresented classes. A re-sampling strategy is also introduced to mitigate bias towards well-represented classes, ensuring equitable class representation. Through extensive experiments in 3D SSL, our method surpasses state-of-the-art counterparts in classification and detection tasks, highlighting its effectiveness in tackling data imbalance. This approach presents a significant advancement in SSL for 3D datasets, providing a robust solution for data imbalance issues.
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。