Guangyao Ding

2 accepted papers

2024

CTS: Sim-to-Real Unsupervised Domain Adaptation on 3D Detection

Meiying Zhang, Weiyuan Peng, Guangyao Ding, Chenyang Lei, Chunlin Ji, Qi Hao

IROS 2024poster

Simulation data can be accurately labeled and have been expected to improve the performance of data-driven algorithms, including object detection. However, due to the various domain inconsistencies from simulation to reality (sim-to-real), cross-domain object detection algorithms usually suffer from…

Cited by 0 Source ↗Scholar ↗

2022

JST: Joint Self-training for Unsupervised Domain Adaptation on 2D&3D Object Detection

Guangyao Ding, Meiying Zhang, E Li, Qi Hao

ICRA 2022poster

2D&3D object detection always suffers from a dramatic performance drop when transferring the model trained in the source domain to the target domain due to various domain shifts. In this paper, we propose a Joint Self-Training (JST) framework to improve 2D image and 3D point cloud detectors with ali…

Cited by 10 Source ↗Scholar ↗