Exploring Single Domain Generalization of LiDAR-based Semantic Segmentation under Imperfect Labels

2025-10-10

AI Summary

This paper addresses the realistic challenge of co-occurring label noise and domain shift in LiDAR semantic segmentation, formally introducing the novel task of “Single-Domain Generalization for LiDAR Semantic Segmentation under Noisy Labels” (DGLSS-NL). Existing noisy-label learning methods fail to accommodate the sparse and permutation-invariant geometric structure of point clouds and lack explicit modeling of domain generalization. To tackle this, we propose DuNe, a dual-branch framework that enforces feature consistency between strong and weak views to enhance robust representation learning, and integrates confidence-aware filtering with weighted cross-entropy loss to suppress label noise. Evaluated on SemanticKITTI, nuScenes, and SemanticPOSS, our method achieves mIoU scores of 56.86%, 42.28%, and 52.58%, respectively, yielding an arithmetic mean of 49.57%—significantly outperforming prior approaches. This work establishes a new paradigm for robust cross-scenario perception in autonomous driving.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Natural Language Processing: Safety and Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Accurate perception is critical for vehicle safety, with LiDAR as a key enabler in autonomous driving. To ensure robust performance across environments, sensor types, and weather conditions without costly re-annotation, domain generalization in LiDAR-based 3D semantic segmentation is essential. However, LiDAR annotations are often noisy due to sensor imperfections, occlusions, and human errors. Such noise degrades segmentation accuracy and is further amplified under domain shifts, threatening system reliability. While noisy-label learning is well-studied in images, its extension to 3D LiDAR segmentation under domain generalization remains largely unexplored, as the sparse and irregular structure of point clouds limits direct use of 2D methods. To address this gap, we introduce the novel task Domain Generalization for LiDAR Semantic Segmentation under Noisy Labels (DGLSS-NL) and establish the first benchmark by adapting three representative noisy-label learning strategies from image classification to 3D segmentation. However, we find that existing noisy-label learning approaches adapt poorly to LiDAR data. We therefore propose DuNe, a dual-view framework with strong and weak branches that enforce feature-level consistency and apply cross-entropy loss based on confidence-aware filtering of predictions. Our approach shows state-of-the-art performance by achieving 56.86% mIoU on SemanticKITTI, 42.28% on nuScenes, and 52.58% on SemanticPOSS under 10% symmetric label noise, with an overall Arithmetic Mean (AM) of 49.57% and Harmonic Mean (HM) of 48.50%, thereby demonstrating robust domain generalization in DGLSS-NL tasks. The code is available on our project page.

Problem

• Addressing LiDAR semantic segmentation generalization under noisy label conditions
• Overcoming domain shift challenges with imperfect 3D point cloud annotations
• Extending noisy-label learning from 2D images to sparse LiDAR data

Innovation

• Dual-view framework with strong and weak branches
• Feature-level consistency enforcement across domains
• Confidence-aware filtering for cross-entropy loss optimization