Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets . However, drasticperformance degradation remains a critical challenge for cross-domain deployment . We propose anovel and unified framework, Multi-Level Consistency Network (MLC-Net), whichemploys a teacher-student paradigm to generate adaptive and reliablepseudo-targets . Extensive experimentsdemonstrate that MLC-net outperforms existing state-of-the-art methods on standard benchmark tests . Notably, our approach is detector-agnostic, which achieves consistent gains on both single- and two-stage 3D detectors . MLCNet exploits point-, instance- and neural statistics-levelconsistency to facilitate cross- domain transfer

Author(s) : Zhipeng Luo, Zhongang Cai, Changqing Zhou, Gongjie Zhang, Haiyu Zhao, Shuai Yi, Shijian Lu, Hongsheng Li, Shanghang Zhang, Ziwei Liu

Links : PDF - Abstract

Code :

Keywords : domain - d - net - multi - level -

Leave a Reply

Your email address will not be published. Required fields are marked *