Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.18469 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917624071323648 |
|---|---|
| author | Yuan, Zhimin Zeng, Wankang Su, Yanfei Liu, Weiquan Cheng, Ming Guo, Yulan Wang, Cheng |
| author_facet | Yuan, Zhimin Zeng, Wankang Su, Yanfei Liu, Weiquan Cheng, Ming Guo, Yulan Wang, Cheng |
| contents | 3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to annotating new domains. Self-training is a competitive approach for this task, but its performance is limited by different sensor sampling patterns (i.e., variations in point density) and incomplete training strategies. In this work, we propose a density-guided translator (DGT), which translates point density between domains, and integrates it into a two-stage self-training pipeline named DGT-ST. First, in contrast to existing works that simultaneously conduct data generation and feature/output alignment within unstable adversarial training, we employ the non-learnable DGT to bridge the domain gap at the input level. Second, to provide a well-initialized model for self-training, we propose a category-level adversarial network in stage one that utilizes the prototype to prevent negative transfer. Finally, by leveraging the designs above, a domain-mixed self-training method with source-aware consistency loss is proposed in stage two to narrow the domain gap further. Experiments on two synthetic-to-real segmentation tasks (SynLiDAR $\rightarrow$ semanticKITTI and SynLiDAR $\rightarrow$ semanticPOSS) demonstrate that DGT-ST outperforms state-of-the-art methods, achieving 9.4$\%$ and 4.3$\%$ mIoU improvements, respectively. Code is available at \url{https://github.com/yuan-zm/DGT-ST}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_18469 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds Yuan, Zhimin Zeng, Wankang Su, Yanfei Liu, Weiquan Cheng, Ming Guo, Yulan Wang, Cheng Computer Vision and Pattern Recognition Artificial Intelligence 3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to annotating new domains. Self-training is a competitive approach for this task, but its performance is limited by different sensor sampling patterns (i.e., variations in point density) and incomplete training strategies. In this work, we propose a density-guided translator (DGT), which translates point density between domains, and integrates it into a two-stage self-training pipeline named DGT-ST. First, in contrast to existing works that simultaneously conduct data generation and feature/output alignment within unstable adversarial training, we employ the non-learnable DGT to bridge the domain gap at the input level. Second, to provide a well-initialized model for self-training, we propose a category-level adversarial network in stage one that utilizes the prototype to prevent negative transfer. Finally, by leveraging the designs above, a domain-mixed self-training method with source-aware consistency loss is proposed in stage two to narrow the domain gap further. Experiments on two synthetic-to-real segmentation tasks (SynLiDAR $\rightarrow$ semanticKITTI and SynLiDAR $\rightarrow$ semanticPOSS) demonstrate that DGT-ST outperforms state-of-the-art methods, achieving 9.4$\%$ and 4.3$\%$ mIoU improvements, respectively. Code is available at \url{https://github.com/yuan-zm/DGT-ST}. |
| title | Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2403.18469 |