论文标题
基于班级信心的3D半监督学习
Class-Level Confidence Based 3D Semi-Supervised Learning
论文作者
论文摘要
最新的最新方法FlexMatch首先证明，正确估计学习状态对于半监督学习（SSL）至关重要。但是，FlexMatch提出的估计方法没有考虑到不平衡的数据，这是3D半监督学习的常见情况。为了解决这个问题，我们实际上证明了未标记的数据类级信心可以代表3D不平衡数据集中的学习状态。基于这一发现，我们提出了一种基于班级置信度的新型3D SSL方法。首先，提出了一种动态阈值策略来利用更多未标记的数据，尤其是对于低学习状态类别。然后，重新采样策略旨在避免偏向于高学习状态类别，从而动态地改变了每个类别的采样概率。为了显示我们方法在3D SSL任务中的有效性，我们对3D SSL分类和检测任务进行了广泛的实验。我们的方法在所有数据集中都大大优于3D SSL分类和检测任务的最先进的方法。
Recent state-of-the-art method FlexMatch firstly demonstrated that correctly estimating learning status is crucial for semi-supervised learning (SSL). However, the estimation method proposed by FlexMatch does not take into account imbalanced data, which is the common case for 3D semi-supervised learning. To address this problem, we practically demonstrate that unlabeled data class-level confidence can represent the learning status in the 3D imbalanced dataset. Based on this finding, we present a novel class-level confidence based 3D SSL method. Firstly, a dynamic thresholding strategy is proposed to utilize more unlabeled data, especially for low learning status classes. Then, a re-sampling strategy is designed to avoid biasing toward high learning status classes, which dynamically changes the sampling probability of each class. To show the effectiveness of our method in 3D SSL tasks, we conduct extensive experiments on 3D SSL classification and detection tasks. Our method significantly outperforms state-of-the-art counterparts for both 3D SSL classification and detection tasks in all datasets.
