profile photo

Aoran XIAO (肖傲然)

​Postdocral Researcher
Geoinformatics Team
RIKEN Center for Advanced Intelligence Project, Japan
Email: aoran.xiao [at] riken.jp (preferred) | aoran.xiao [at] ntu.edu.sg

google scholar gitjub

Short Bio

​I am currently a Postdoctoral Researcher in the Geoinformatics Team at RIKEN AIP, Japan, under the leadership of Professor Naoto Yokoya. My research focuses on data-efficient learning, 2D/3D computer vision, and the efficient fine-tuning of large foundation models for multimodal data. Prior to joining RIKEN, I earned my PhD from the College of Computing and Data Science at Nanyang Technological University, Singapore, under the supervision of Professor Shijian Lu. I obtained my Master’s degree from LIESMARS, Wuhan University, where I was co-advised by Professors Deren Li and Ruizhi Chen, and my Bachelor’s degree from the School of Remote Sensing and Information Engineering, Wuhan University.

I’m open to exploring collaborations and engaging in discussions. Feel free to reach out to me!

News

[2024-10] I’ve joined RIKEN AIP, embarking on an exciting new chapter!
[2024-07] Our CAT-SAM is accepted to ECCV2024!
[2024-06] Our survey for label-efficient learning of 3D point clouds is accepted to TPAMI!

Selected Publications
clean-usnob

Segment Anything with Multiple Modalities
Aoran Xiao*, Weihao Xuan*, Heli Qi, Yun Xing, Naoto Yokoya, Shijian Lu (*Equal contribution)
arXiv, 2024.
[paper] [project]

clean-usnob

CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model
Aoran Xiao*, Weihao Xuan*, Heli Qi, Yun Xing, Ruijie Ren, Xiaoqin Zhang, Ling Shao, Shijian Lu (*Equal contribution)
European Conference on Computer Vision (ECCV), 2024. (Oral paper)
[paper] [project]

clean-usnob

A Survey of Label-Efficient Deep Learning for 3D Point Clouds
Aoran Xiao, Xiaoqin Zhang, Ling Shao, Shijian Lu.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2024.
[paper] [project]

clean-usnob

Domain Adaptive LiDAR Point Cloud Segmentation With 3D Spatial Consistency
Aoran Xiao, Dayan Guan, Xiaoqin Zhang, Shijian Lu
IEEE Transactions on Multimedia (T-MM), 2024.
[paper]

clean-usnob

Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation
Yun Xing, Jian Kang, Aoran Xiao, Jiahao Nie, Ling Shao, Shijian Lu
Advances in Neural Information Processing Systems (NeurIPS), 2023.
[paper] [project]

clean-usnob

3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds
Aoran Xiao, Jiaxing Huang, Weihao Xuan, Ruijie Ren, Kangcheng Liu, Dayan Guan, Abdulmotaleb El Saddik, Shijian Lu, Eric Xing.
IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023.
[paper] [project]

clean-usnob

Unsupervised Representation Learning for Point Clouds with Deep Neural Networks: A Survey
Aoran Xiao*, Jiaxing Huang*, Dayan Guan, Xiaoqin Zhang, Shijian Lu (*Equal contribution).
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023.
[paper] [project]

clean-usnob

PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds
Aoran Xiao, Jiaxing Huang, Dayan Guan, Kaiwen Cui, Shijian Lu, Ling Shao.
Advances in Neural Information Processing Systems (NeurIPS), 2022.
[paper] [project]

clean-usnob

Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu, Ling Shao.
IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2022.
[paper] [project]

clean-usnob

Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation
Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu, Ling Shao.
IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2022.
[paper] [project]

clean-usnob

Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation
Aoran Xiao, Jiaxing Huang, Dayan Guan, Fangneng Zhan, Shijian Lu.
AAAI Conference on Artificial Intelligence (AAAI), 2022.
[paper] [project]

clean-usnob

Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu
Advances in Neural Information Processing Systems (NeurIPS), 2021.
[paper] [project]

clean-usnob

RDA: Robust Domain Adaptation via Fourier Adversarial Attacking
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu
International Conference on Computer Vision (ICCV), 2021.
[paper] [project]

clean-usnob

Domain Adaptive Video Segmentation via Temporal Consistency Regularization
Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu
International Conference on Computer Vision (ICCV), 2021.
[paper] [project]

clean-usnob

Cross-View Regularization for Domain Adaptive Panoptic Segmentation
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu, Ling Shao.
IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2021.
[paper] [project]

clean-usnob

FSDR: Frequency Space Domain Randomization for Domain Generalization
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu, Ling Shao.
IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2021.
[paper]

clean-usnob

FPS-Net: A convolutional fusion network for large-scale LiDAR point cloud segmentation
Aoran Xiao, Xiaofei Yang, Shijian Lu, Dayan Guan, Jiaxing Huang.
ISPRS journal of Photogrammetry and Remote Sensing, 2021.
[paper] [project]

clean-usnob

Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection
Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu, Yanpeng Cao.
IEEE Transactions on Multimedia (T-MM), 2021.
[paper] [project]

Released Datasets

SynLiDAR: A Large-Scale Synthetic LiDAR Point Cloud Dataset with Point-Wise Annotations
SynLiDAR is a large-scale synthetic LiDAR sequential point cloud dataset with point-wise annotations. 13 sequences of LiDAR point cloud with around 20k scans (over 19 billion points and 32 semantic classes) are collected from virtual urban cities, suburban towns, neighborhood, and harbor.
[paper] [project] [download]

SemanticSTF: An Adverse-Weather LiDAR Point Cloud Dataset
SemanticSTF is a large-scale adverse-weather point cloud dataset that provides dense point-level annotations and allows to study 3D semantic segmentation under various adverse weather conditions.
[paper] [project] [download]

Miscellaneous

Professional Activities
  • Conference Reviews:

International Conference on Computer Vision (ICCV) 2023.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024,2023,2022.
Conference and Workshop on Neural Information Processing Systems (NeurIPS) 2024,2023.
European Conference on Computer Vision (ECCV) 2024, 2022.
International Conference on Learning Representations (ICLR) 2025,2024.
International Conference on Machine Learning (ICML) 2024.
AAAI Conference on Artificial Intelligence (AAAI) 2025,2024.

  • Journal Reviews:

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
IEEE Transactions on Image Processing (TIP).
IEEE Transactions on Intelligent Vehicles (TIV).
IEEE Transactions on Multimedia (TMM).
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT).
ISPRS Journal of Photogrammetry and Remote Sensing.
Pattern Recognition.