Bo Chen

Bo Chen

Research Fellow

Australian Institute for Machine Learning, the University of Adelaide

Biography

I am a research fellow at the Australian Institute for Machine Learning (AIML), the University of Adelaide. My research interests lie in the intersection of machine learning and computer vision. Specific topics include: object pose estimation, differentiable geometric optimisation, adversarial machine learning and AI application on edge devices.

Interests
  • Artificial Intelligence
  • Deep Learning
  • Computer Vision
Education

  • PhD in Artificial Intelligence, 2019

    Monash University

  • MSc in Statistics, 2013

    The University of Queensland

  • BBM in E-Commerce, 2006

    Sun Yat-Sen University

Experience

 
 
 
 
 
Research Fellow
AIML, the University of Adelaide
Feb 2019 – Present Adelaide, Australia
 
 
 
 
 
Teaching Associate
Monash University
Jul 2017 – Dec 2018 Melbourne, Australia
 
 
 
 
 
Data Analysis Lead
Moonbasa
Jul 2011 – Jun 2012 Guangzhou, China
 
 
 
 
 
Assistant Research Executive
Ipsos
Sep 2010 – Feb 2011 Guangzhou, China

Featured Publications

Bo Chen, Alvaro Parra, Jiewei Cao, Nan Li, Tat-Jun Chin
June 2020 In CVPR 2020
End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization
End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization

We propose BPnP, a network module for backpropagation through a PnP optimizer, as if the optimizer were a differentiable function.
PDF Cite Project
Bo Chen, Jiewei Cao, Alvaro Parra, Tat-Jun Chin
September 2019 In ICCVW 2019
Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement
Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement

We proposed an approach to estimate the 6DOF pose of a satellite. Our method won the first place in the Kelvins Pose Estimation Challenge organised by the European Space Agency (ESA).
PDF Cite Project

Publications

Physical Adversarial Attacks on an Aerial Imagery Object Detector
Deep neural networks (DNNs) have become essential for processing the vast amounts of aerial imagery collected using earth-observing …
Andrew Du, Bo Chen, Tat-Jun Chin, Yee Wei Law, Michele Sasdelli, Ramesh Rajasegaran, Dillon Campbell
PDF Cite Video
A Spacecraft Dataset for Detection, Segmentation and Parts Recognition
Virtually all aspects of modern life depend on space technology. Thanks to the great advancement of computer vision in general and deep …
Hoang Anh Dung, Bo Chen, Tat-Jun Chin
PDF Cite Dataset
Spot the GEO Satellites: From Dataset to Kelvins SpotGEO Challenge
The Geosynchronous Equatorial Orbit (GEO) is home to many important space assets such as telecommunication and navigational satellites. …
Bo Chen, Daqi Liu, Tat-Jun Chin, Mark Rutten, Dawa Derksen, Marcus Märtens, Moritz von Looz, Gurvan Lecuyer, Dario Izzo
PDF Cite Dataset Project
End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization
We propose BPnP, a network module for backpropagation through a PnP optimizer, as if the optimizer were a differentiable function.
Bo Chen, Alvaro Parra, Jiewei Cao, Nan Li, Tat-Jun Chin
PDF Cite Project
End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization
Anomaly Detection via Neighbourhood Contrast
Relative scores such as Local Outlying Factor and mass ratio have been shown to be better scores than global scores in detecting …
Bo Chen, Kai Ming Ting, Tat-Jun Chin
PDF Cite DOI
See all publications

Projects

*
Edge AI
AI application on the edge
Edge AI
Robust Object Pose Estimation
Estimating the 6 degrees of freedom object pose from an RGB image.
Robust Object Pose Estimation
Cactus Mapping
Aerial cactus mapping in the Flinders Ranges
Cactus Mapping
Kelvins SpotGEO Challenge
Spot the GEO satellites challenge co-organised with ESA
Kelvins SpotGEO Challenge
Sattelite Pose Estimation
Estimate the relative attitude and position of a known spacecraft.
PDF Video Follow
Sattelite Pose Estimation

Contact