LiDARNet: A Boundary-Aware Domain Adaptation Model for Point Cloud Semantic Segmentation

Abstract

We present a boundary-aware domain adaptation model for LiDAR scan full-scene semantic segmentation (LiDARNet). Our model can extract both the domain private features and the domain shared features with a two-branch structure. We embedded Gated-SCNN into the segmentor component of LiDARNet to learn boundary information while learning to predict full-scene semantic segmentation labels. Moreover, we further reduce the domain gap by inducing the model to learn a mapping between two domains using the domain shared and private features. Additionally, we introduce a new dataset (SemanticUSL\footnote{The access address of SemanticUSL:\url{https://unmannedlab.github.io/research/SemanticUSL}}) for domain adaptation for LiDAR point cloud semantic segmentation. The dataset has the same data format and ontology as SemanticKITTI. We conducted experiments on real-world datasets SemanticKITTI, SemanticPOSS, and SemanticUSL, which have differences in channel distributions, reflectivity distributions, diversity of scenes, and sensors setup. Using our approach, we can get a single projection-based LiDAR full-scene semantic segmentation model working on both domains. Our model can keep almost the same performance on the source domain after adaptation and get an 8\%-22\% mIoU performance increase in the target domain.

arXiv comment8 pages, 3 figures

References in corpus (13)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Domain Separation Networks
• Semantic Segmentation using Adversarial Networks
• A2D2: Audi Autonomous Driving Dataset
• SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving
• PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation
• D${}^2$-City: A Large-Scale Dashcam Video Dataset of Diverse Traffic Scenarios
• Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds
• SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances

Cited by in corpus (5)

• Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation
• ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation
• SemCal: Semantic LiDAR-Camera Calibration using Neural MutualInformation Estimator
• Calibrating LiDAR and Camera using Semantic Mutual information
• ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation