Search Results for author: Huiqun Wang

Found 2 papers, 0 papers with code

iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization

no code implementations25 Aug 2021 Huiqun Wang, Ruijie Yang, Di Huang, Yunhong Wang

Differentiable ARchiTecture Search (DARTS) uses a continuous relaxation of network representation and dramatically accelerates Neural Architecture Search (NAS) by almost thousands of times in GPU-day.

Neural Architecture Search

PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimation

no code implementations ICCV 2021 Guangyuan Zhou, Huiqun Wang, Jiaxin Chen, Di Huang

This paper proposes a novel deep learning approach, namely Graph Convolutional Network with Point Refinement (PR-GCN), to simultaneously address the issues above in a unified way.

6D Pose Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.