用稀疏标签+伪标签，让越野语义分割更准
COARSE: Collaborative Pseudo-Labeling with Coarse Real Labels for Off-Road Semantic Segmentation
- 用稀疏真实标签和密集模拟数据协同训练
- 在RUGD和Rellis-3D上分别提升9.7%和8.4%
- 适合缺乏密集标注的野外场景应用
自动驾驶越野导航面临环境多样、结构无序的挑战，需兼具几何与语义理解。但密集标注的语义数据稀缺，限制了跨域泛化能力。仿真数据虽可缓解，却带来领域适应问题。本文提出COARSE，一种半监督领域自适应框架，利用稀疏、粗粒度的本域标签和密集标注的域外数据。基于预训练视觉变压器，通过互补的像素级与块级解码器弥合领域差距，并在无标签数据上采用协作伪标签策略。在RUGD和Rellis-3D数据集上的评估显示，相比仅使用粗标签，分别提升9.7%和8.4%。在多生态真实越野车辆数据上的测试进一步验证了COARSE的实用性。
原文摘要 · Abstract (English)
Autonomous off-road navigation faces challenges due to diverse, unstructured environments, requiring robust perception with both geometric and semantic understanding. However, scarce densely labeled semantic data limits generalization across domains. Simulated data helps, but introduces domain adaptation issues. We propose COARSE, a semi-supervised domain adaptation framework for off-road semantic segmentation, leveraging sparse, coarse in-domain labels and densely labeled out-of-domain data. Using pretrained vision transformers, we bridge domain gaps with complementary pixel-level and patch-level decoders, enhanced by a collaborative pseudo-labeling strategy on unlabeled data. Evaluations on RUGD and Rellis-3D datasets show significant improvements of 9.7\% and 8.4\% respectively, versus only using coarse data. Tests on real-world off-road vehicle data in a multi-biome setting further demonstrate COARSE's applicability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。