用一致性教师模型提升单目3D检测跨域性能，显著减少传感器差异影响。
MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models
- 引入深度增强模块与伪标签评分机制，提升伪标签精度。
- 在六个基准上实现最高21%的AP Mod.提升，跨视角泛化能力强。
- 适合需要跨传感器部署的自动驾驶与无人机视觉系统使用。
针对不同传感器、环境和相机设置下的单目3D目标检测问题，本文提出一种新型无监督域适应方法MonoCT，通过生成高精度伪标签实现自监督学习。受观察启发：准确的深度估计对缓解域偏移至关重要，MonoCT引入广义深度增强（GDE）模块，结合集成思想提升深度估计性能；同时提出伪标签评分（PLS）模块，利用模型内一致性测量与多样性最大化策略，进一步生成高质量伪标签用于自训练。在六个基准上的大量实验表明，MonoCT相比现有最先进方法在AP Mod.指标上最低提升21%，且在汽车、交通摄像头和无人机视角下均表现良好，具有强泛化能力。
原文摘要 · Abstract (English)
We tackle the problem of monocular 3D object detection across different sensors, environments, and camera setups. In this paper, we introduce a novel unsupervised domain adaptation approach, MonoCT, that generates highly accurate pseudo labels for self-supervision. Inspired by our observation that accurate depth estimation is critical to mitigating domain shifts, MonoCT introduces a novel Generalized Depth Enhancement (GDE) module with an ensemble concept to improve depth estimation accuracy. Moreover, we introduce a novel Pseudo Label Scoring (PLS) module by exploring inner-model consistency measurement and a Diversity Maximization (DM) strategy to further generate high-quality pseudo labels for self-training. Extensive experiments on six benchmarks show that MonoCT outperforms existing SOTA domain adaptation methods by large margins (~21% minimum for AP Mod.) and generalizes well to car, traffic camera and drone views.
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。