arXiv 2201.055852022-01cs.CVcs.LG

Domain Adaptation in LiDAR Semantic Segmentation via Alternating Skip Connections and Hybrid Learning

Huawei Noah’s Ark Lab（华为诺亚方舟实验室）

Eduardo R. Corral-Soto, Mrigank Rochan, Yannis Y. He, Shubhra Aich, Yang Liu, Liu Bingbing

备注：: 1) Introduced Fig 1, 2) Simplified Fig. 2 diagram, 3) Fixed typos in losses, 4) Introduced Fig. 3, 5) Updated evaluation results, included evaluation on SemanticPOSS, 6) Introduced Table 3 - effects on covariance matrix and mean, 7) Updated Fig. 5, 8) Added more references. Improved writing in general, especially the motivation and description of each element and contribution from the method

英文摘要：

In this paper we address the challenging problem of domain adaptation in LiDAR semantic segmentation. We consider the setting where we have a fully-labeled data set from source domain and a target domain with a few labeled and many unlabeled examples. We propose a domain adaption framework that mitigates the issue of domain shift and produces appealing performance on the target domain. To this end, we develop a GAN-based image-to-image translation engine that has generators with alternating connections, and couple it with a state-of-the-art LiDAR semantic segmentation network. Our framework is hybrid in nature in the sense that our model learning is composed of self-supervision, semi-supervision and unsupervised learning. Extensive experiments on benchmark LiDAR semantic segmentation data sets demonstrate that our method achieves superior performance in comparison to strong baselines and prior arts.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

英文摘要：

相关论文