Enhanced Prototypical Learning for Unsupervised Domain Adaptation in LiDAR Semantic Segmentation

2022-05-23 · Eojindl Yi, JuYoung Yang, Junmo Kim

Despite its importance, unsupervised domain adaptation (UDA) on LiDAR semantic segmentation is a task that has not received much attention from the research community. Only recently, a completion-based 3D method has been proposed to tackle the problem and formally set up the adaptive scenarios. However, the proposed pipeline is complex, voxel-based and requires multi-stage inference, which inhibits it for real-time inference. We propose a range image-based, effective and efficient method for solving UDA on LiDAR segmentation. The method exploits class prototypes from the source domain to pseudo label target domain pixels, which is a research direction showing good performance in UDA for natural image semantic segmentation. Applying such approaches to LiDAR scans has not been considered because of the severe domain shift and lack of pre-trained feature extractor that is unavailable in the LiDAR segmentation setup. However, we show that proper strategies, including reconstruction-based pre-training, enhanced prototypes, and selective pseudo labeling based on distance to prototypes, is sufficient enough to enable the use of prototypical approaches. We evaluate the performance of our method on the recently proposed LiDAR segmentation UDA scenarios. Our method achieves remarkable performance among contemporary methods.

📄 PDF Abstract BibTeX arXiv:2205.11419

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation LIDAR Semantic SegmentationPseudo LabelSegmentation Semantic Segmentation Unsupervised Domain Adaptation

Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation

2021-03-31 · CVPR 2021 1 · Xiangyu Yue, Zangwei Zheng, Shanghang Zhang, Yang Gao 외

Unsupervised Domain Adaptation (UDA) transfers predictive models from a fully-labeled source domain to an unlabeled target domain. In some applications, however, it is expensive even to collect labels in the source domai…

Contrastive Learning Domain Adaptation Self-Supervised Learning Semantic Segmentation+1

Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation

2022-07-14 · Zhengkai Jiang, Yuxi Li, Ceyuan Yang, Peng Gao 외

Unsupervised Domain Adaptation (UDA) aims to adapt the model trained on the labeled source domain to an unlabeled target domain. In this paper, we present Prototypical Contrast Adaptation (ProCA), a simple and efficient …

Contrastive Learning Domain Adaptation Semantic Segmentation Unsupervised Domain Adaptation

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

SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation

2023-04-06 · Björn Michele, Alexandre Boulch, Gilles Puy, Tuan-Hung Vu 외

Learning models on one labeled dataset that generalize well on another domain is a difficult task, as several shifts might happen between the data domains. This is notably the case for lidar data, for which models can ex…

3D Unsupervised Domain Adaptation Domain Adaptation Semantic Segmentation Unsupervised Domain Adaptation

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