RePL: Pseudo-label Refinement for Semi-supervised LiDAR Semantic Segmentation

TL;DR

RePL is a novel semi-supervised LiDAR segmentation framework that refines pseudo-labels via masked reconstruction, significantly improving label quality and achieving state-of-the-art results.

Contribution

Introducing RePL, a framework that enhances pseudo-labels in semi-supervised LiDAR segmentation through error correction and theoretical validation.

Findings

RePL significantly improves pseudo-label quality.

RePL achieves state-of-the-art performance on nuScenes-lidarseg and SemanticKITTI.

Theoretical analysis confirms the conditions under which RePL is beneficial.

Abstract

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.