Jingang Tan — accepted AI-conference papers

2020

3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection

Liang Du, Jingang Tan, Xiangyang Xue, Lili Chen, Hongkai Wen, Jianfeng Feng +2

ICRA 2020poster

We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation. Inspired by the human scene perception process, we design a novel coupled feature selection module, named CFSM, that adaptiv…

Cited by 16 Source ↗code ↗Scholar ↗

2019

SSF-DAN: Separated Semantic Feature Based Domain Adaptation Network for Semantic Segmentation

Liang Du, Jingang Tan, Hongye Yang, Jianfeng Feng, Xiangyang Xue, Qibao Zheng +2

ICCV 2019poster

Despite the great success achieved by supervised fully convolutional models in semantic segmentation, training the models requires a large amount of labor-intensive work to generate pixel-level annotations. Recent works exploit synthetic data to train the model for semantic segmentation, but the dom…

Cited by 208 PDF ↗Scholar ↗