CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation

2022-07-20 · Cristiano Saltori, Fabio Galasso, Giuseppe Fiameni, Nicu Sebe, Elisa Ricci, Fabio Poiesi

3D LiDAR semantic segmentation is fundamental for autonomous driving. Several Unsupervised Domain Adaptation (UDA) methods for point cloud data have been recently proposed to improve model generalization for different sensors and environments. Researchers working on UDA problems in the image domain have shown that sample mixing can mitigate domain shift. We propose a new approach of sample mixing for point cloud UDA, namely Compositional Semantic Mix (CoSMix), the first UDA approach for point cloud segmentation based on sample mixing. CoSMix consists of a two-branch symmetric network that can process labelled synthetic data (source) and real-world unlabelled point clouds (target) concurrently. Each branch operates on one domain by mixing selected pieces of data from the other one, and by using the semantic information derived from source labels and target pseudo-labels. We evaluate CoSMix on two large-scale datasets, showing that it outperforms state-of-the-art methods by a large margin. Our code is available at https://github.com/saltoricristiano/cosmix-uda.

📄 PDF Abstract BibTeX arXiv:2207.09778

Code (2)

saltoricristiano/cosmix-uda 공식 구현 pytorch

xiaoaoran/SynLiDAR

Tasks

3D Unsupervised Domain AdaptationAutonomous Driving Domain Adaptation LIDAR Semantic Segmentation Point Cloud Segmentation Segmentation Semantic Segmentation Unsupervised Domain Adaptation

Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation

2023-08-28 · Cristiano Saltori, Fabio Galasso, Giuseppe Fiameni, Nicu Sebe 외

Deep-learning models for 3D point cloud semantic segmentation exhibit limited generalization capabilities when trained and tested on data captured with different sensors or in varying environments due to domain shift. Do…

Domain Adaptation Point Cloud Completion Point Cloud Segmentation Semantic Segmentation+1

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

2020-03-02 · Peng Jiang, Srikanth Saripalli

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 stru…

Diversity Domain Adaptation Segmentation Semantic Segmentation

Fake it, Mix it, Segment it: Bridging the Domain Gap Between Lidar Sensors

2022-12-19 · Frederik Hasecke, Pascal Colling, Anton Kummert

Segmentation of lidar data is a task that provides rich, point-wise information about the environment of robots or autonomous vehicles. Currently best performing neural networks for lidar segmentation are fine-tuned to s…

Autonomous Vehicles Domain Adaptation Segmentation Semantic Segmentation+2

Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapters

2021-07-20 · Mrigank Rochan, Shubhra Aich, Eduardo R. Corral-Soto, Amir Nabatchian 외

In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation. There is a significant drop in performance of an existing segmentation model when tr…

Domain Adaptation LIDAR Semantic Segmentation Segmentation Semantic Segmentation+1

Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds

2020-07-16 · CVPR 2021 1 · Li Yi, Boqing Gong, Thomas Funkhouser

We study an unsupervised domain adaptation problem for the semantic labeling of 3D point clouds, with a particular focus on domain discrepancies induced by different LiDAR sensors. Based on the observation that sparse 3D…

Domain Adaptation Semantic Segmentation Unsupervised Domain Adaptation