仅用少量精选样本，实现3D目标检测跨域高效迁移。
Semi-Supervised Diversity-Aware Domain Adaptation for 3D Object detection
- 基于神经元激活模式选择关键样本，提升适配效率。
- 仅标注少量样本即达当前最优跨域检测性能。
- 适合资源有限但需跨区域部署的自动驾驶场景。
3D目标检测器是自动驾驶感知系统的核心组件。尽管在标准自动驾驶基准上表现优异，但在不同领域间泛化能力仍受限——例如在美国训练的模型在亚洲或欧洲地区性能显著下降。本文提出一种基于神经元激活模式的激光雷达域适应方法，证明仅需标注少量具有代表性和多样性的目标域样本，即可实现顶尖性能。该方法标注预算极低，结合受持续学习启发的后训练技术，有效防止模型权重偏移。实验表明，所提方法优于线性探测及现有最优域适应技术。
原文摘要 · Abstract (English)
3D object detectors are fundamental components of perception systems in autonomous vehicles. While these detectors achieve remarkable performance on standard autonomous driving benchmarks, they often struggle to generalize across different domains - for instance, a model trained in the U.S. may perform poorly in regions like Asia or Europe. This paper presents a novel lidar domain adaptation method based on neuron activation patterns, demonstrating that state-of-the-art performance can be achieved by annotating only a small, representative, and diverse subset of samples from the target domain if they are correctly selected. The proposed approach requires very small annotation budget and, when combined with post-training techniques inspired by continual learning prevent weight drift from the original model. Empirical evaluation shows that the proposed domain adaptation approach outperforms both linear probing and state-of-the-art domain adaptation techniques.
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。