RePL: Pseudo-label Refinement for Semi-supervised LiDAR Semantic Segmentation
This addresses a chronic issue in semi-supervised learning for LiDAR semantic segmentation, which is important for applications like autonomous driving, but it appears incremental as it builds on existing pseudo-label methods.
The paper tackled the problem of error propagation and confirmation bias from noisy pseudo-labels in semi-supervised LiDAR semantic segmentation by introducing RePL, a framework that refines pseudo-labels using masked reconstruction and a dedicated training strategy, achieving state-of-the-art results on nuScenes-lidarseg and SemanticKITTI datasets.
Semi-supervised learning for LiDAR semantic segmentation often suffers from error propagation and confirmation bias caused by noisy pseudo-labels. To tackle this chronic issue, we introduce RePL, a novel framework that enhances pseudo-label quality by identifying and correcting potential errors in pseudo-labels through masked reconstruction, along with a dedicated training strategy. We also provide a theoretical analysis demonstrating the condition under which the pseudo-label refinement is beneficial, and empirically confirm that the condition is mild and clearly met by RePL. Extensive evaluations on the nuScenes-lidarseg and SemanticKITTI datasets show that RePL improves pseudo-label quality a lot and, as a result, achieves the state of the art in LiDAR semantic segmentation.