I am a PhD candidate at The University of Queensland (UQ), Australia. My research focuses on 3D scene understanding and machine learning under the supervision of Dr Yadan Luo, Prof Helen Huang, and Dr Mahsa Baktashmotlagh. I received my Bachelor of Computer Science degree with First Class Honours from UQ in 2021. I was selected as the Valedictorian in the graduation ceremony in Dec 2021.
Email: zhuoxiao [dot] chen [at] uq [dot] edu [dot] auGoogle Scholar  /  GitHub  /  DBLP  /  IG
Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling
Zhuoxiao Chen, Yadan Luo, Zi Huang, Zheng Wang, Mahsa Baktashmotlagh
ICCV 2023
[paper]
[code]
[video]
Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection.
While effective, existing DA methods suffer from a substantial drop in performance when applied to a multi-class training setting,
due to the co-existence of low-quality pseudo labels and class imbalance issues.
In this paper, we address this challenge by proposing a novel ReDB framework tailored for learning to detect all classes at once.
Our approach produces Reliable, Diverse, and class-Balanced pseudo 3D boxes to iteratively guide the self-training on a distributionally
different target domain.
KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection
Yadan Luo, Zhuoxiao Chen, Zhen Fang, Zheng Zhang, Zi Huang, Mahsa Baktashmotlagh
ICCV 2023
[arXiv]
[code]
Active learning (AL) seeks to mitigate the annotation burden through algorithms that use fewer labels and can attain performance comparable to fully supervised learning.
Although AL has shown promise, current approaches prioritize the selection of unlabeled point clouds with high aleatoric and/or epistemic uncertainty,
leading to the selection of more instances for labeling and reduced computational efficiency.
In this paper, we resort to a novel kernel coding rate maximization (KECOR) strategy which aims to identify the most informative point clouds to acquire labels
through the lens of information theory.
Exploring Active 3D Object Detection from a Generalization Perspective
Yadan Luo*, Zhuoxiao Chen*, Zijian Wang, Xin Yu, Zi Huang, Mahsa Baktashmotlagh
ICLR (Spotlight) 2023
[paper]
[code]
To alleviate the high annotation cost in LiDAR-based 3D object detection,
active learning is a promising solution that learns to select only a small portion of unlabeled data to annotate,
without compromising model performance. We jointly investigate three novel criteria in our framework CRB for point cloud acquisition - label conciseness, feature representativeness and
geometric balance, which hierarchically filters out the point clouds of redundant 3D bounding box labels, latent features and geometric characteristics (e.g., point cloud density)
from the unlabeled sample pool and greedily selects informative ones with fewer objects to annotate.
Source-Free Progressive Graph Learning for Open-Set Domain Adaptation
Yadan Luo, Zijian Wang, Zhuoxiao Chen, Zi Huang, Mahsa Baktashmotlagh
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
[paper]
[code]
We propose a Progressive Graph Learning (PGL) framework that decomposes the target hypothesis space into the shared and unknown subspaces, and then progressively pseudo-labels the most confident known samples from the target domain for
hypothesis adaptation.
Conditional Extreme Value Theory for Open Set Video Domain Adaptation
Zhuoxiao Chen, Yadan Luo, Mahsa Baktashmotlagh
MMAsia 2021
[arXiv]
[paper]
[code]
In this work, we propose an open-set video domain adaptation approach to mitigate the domain discrepancy between the source and target data,
allowing the target data to contain additional classes that do not belong to the source domain. The class-conditional extreme value theory is applied to enhance the unknown recognition.
RoadAtlas: Intelligent Platform for Automated Road Defect Detection and Asset Management
Zhuoxiao Chen, Yiyun Zhang, Yadan Luo, Zijian Wang, Jinjiang Zhong, Anthony Southon
MMAsia (demo) 2021
[arXiv]
[paper]
[project page]
[demo video]
We present RoadAtlas, a novel end-to-end integrated system that can support 1) road defect detection, 2) road
marking parsing, 3) a web-based dashboard for presenting and inputting data by users, and 4) a backend containing a well-structured database and developed APIs.