Search Results for author: Shengjun Zhang

Found 4 papers, 1 papers with code

GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds

1 code implementation28 Mar 2024 Shengjun Zhang, Xin Fei, Yueqi Duan

In this paper, we propose geometry-to-voxel auxiliary learning to enable voxel representations to access point-level geometric information, which supports better generalisation of the voxel-based backbone with additional interpretations of multi-sensor point clouds.

Auxiliary Learning Representation Learning

Convergence Analysis of Nonconvex Distributed Stochastic Zeroth-order Coordinate Method

no code implementations24 Mar 2021 Shengjun Zhang, Yunlong Dong, Dong Xie, Lisha Yao, Colleen P. Bailey, Shengli Fu

This paper investigates the stochastic distributed nonconvex optimization problem of minimizing a global cost function formed by the summation of $n$ local cost functions.

Stochastic Optimization

A Primal-Dual SGD Algorithm for Distributed Nonconvex Optimization

no code implementations4 Jun 2020 Xinlei Yi, Shengjun Zhang, Tao Yang, Tianyou Chai, Karl H. Johansson

The distributed nonconvex optimization problem of minimizing a global cost function formed by a sum of $n$ local cost functions by using local information exchange is considered.

Optimization and Control

Extremal Region Analysis based Deep Learning Framework for Detecting Defects

no code implementations19 Mar 2020 Zelin Deng, Xiaolong Yan, Shengjun Zhang, Colleen P. Bailey

A maximally stable extreme region (MSER) analysis based convolutional neural network (CNN) for unified defect detection framework is proposed in this paper.

Defect Detection

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