Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning. Existing methods often rely on empirical label selection strategies, such as confidence thresholding, to generate beneficial pseudo-labels for model training. This approach may, however, hinder the comprehensive exploitation of unlabeled data points. We hypothesize that this selective usage arises from the noise in pseudo-labels generated on unlabeled data. The noise in pseudo-labels may result in significant discrepancies between pseudo-labels and model predictions, thus confusing and affecting the model training greatly. To address this issue, we propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions. More specifically, our method introduces an Entropy Regularization loss and a Distribution Alignment loss for weakly supervised learning in 3D segmentation tasks, resulting in an ERDA learning strategy. Interestingly, by using KL distance to formulate the distribution alignment loss, it reduces to a deceptively simple cross-entropy-based loss which optimizes both the pseudo-label generation network and the 3D segmentation network simultaneously. Despite the simplicity, our method promisingly improves the performance. We validate the effectiveness through extensive experiments on various baselines and large-scale datasets. Results show that ERDA effectively enables the effective usage of all unlabeled data points for learning and achieves state-of-the-art performance under different settings. Remarkably, our method can outperform fully-supervised baselines using only 1% of true annotations. Code and model will be made publicly available.

翻译：伪标签广泛应用于弱监督三维分割任务中，此类任务仅能获取稀疏的真实标签用于学习。现有方法通常依赖经验性的标签选择策略（如置信度阈值法）来生成有益伪标签以训练模型。然而，这种策略可能阻碍未标注数据点的全面利用。我们推测选择性使用源于未标注数据生成的伪标签存在噪声。伪标签中的噪声可能导致其与模型预测之间存在显著偏差，从而严重干扰模型训练进程。为解决该问题，我们提出一种新型学习策略，通过正则化生成的伪标签，有效缩小伪标签与模型预测之间的差距。具体而言，该方法针对三维分割弱监督学习任务引入熵正则化损失与分布对齐损失，由此形成ERDA学习策略。有趣的是，通过使用KL散度构建分布对齐损失，该损失可简化为看似简单的交叉熵损失形式，同步优化伪标签生成网络与三维分割网络。尽管形式简洁，本方法仍能显著提升性能。我们通过在多种基线模型和大规模数据集上的广泛实验验证其有效性。结果表明，ERDA能有效利用所有未标注数据点进行学习，并在不同设定下取得最优性能。值得注意的是，本方法仅需1%的真实标注即可超越全监督基线。相关代码与模型将公开提供。