Unsupervised Collaborative Domain Adaptation for Driving Scene Parsing
无监督协作域自适应用于驾驶场景解析
机构 * College of Electronic and Information Engineering, Tongji University(同济大学电子与信息学院) ; Department of Control Science and Engineering, Harbin Institute of Technology(控制科学与工程系,哈尔滨工业大学) ; Department of Vehicle Control System and Software Development, NIO(车辆控制系统与软件开发部,蔚来汽车) ; School of Computer Science and Technology, Tongji University(计算机科学与技术学院,同济大学) ; Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University(嵌入式系统与服务计算重点实验室(教育部),同济大学)
AI总结 提出无监督协作域自适应框架UCDA,通过多源模型协作优化和知识蒸馏,在无源数据条件下提升目标域驾驶场景解析的鲁棒性和泛化能力。