About me
I am a postdoctoral researcher with S-Lab at the School of Computer Science and Engineering, Nanyang Technological University. I received my Ph.D. degree from the School of Computer Science and Engineering, Nanyang Technological University in 2023, supervised by Prof. Shijian Lu. I obtained my Bachelor’s degrees from University of Glasgow and University of Electronic Science and Technology of China in 2018.
My research interests are machine learning and computer vision. My research focuses on efficient artificial intelligence, etc., and will explore the following research directions:
- Transfer Learning, e.g., domain adaptation, domain generalization.
- Self-Supervised Learning, e.g., contrastive learning, masked image modelling.
- Multimodal Learning, e.g., multimodal large language model, vision-language model, 3D model.
- Efficient tuning for foundation models, e.g., instruction tuning, RLHF, visual instruction tuning.
News
· [Oct, 2024] Three papers are accepted by NeurIPS 2024.
· [Sep, 2024] I was listed among the 2024 World’s Top 2% Scientists by Stanford University.
· [July, 2024] Serving as an Area Chair for WACV 2025.
· [July, 2024] One paper accepted by ECCV 2024.
· [May, 2024] Serving as an Area Chair for BMVC 2024.
· [Mar, 2024] One paper accepted by CVPR 2024.
· [Feb, 2024] One paper accepted by TPAMI.
· [Jan, 2024] One paper accepted by IJCV; One paper accepted by ICLR 2024.
· [Oct, 2023] One paper accepted by TIP.
· [July, 2023] Two papers are accepted by ICCV 2023.
· [Mar, 2023] Three papers are accepted by CVPR 2023; Two papers are accepted by TPAMI.
· [Feb, 2023] Two papers are accepted by TPAMI 2023.
· [Dec, 2022] Two papers are accepted by NeurIPS 2022.
· [July, 2022] Two papers are accepted by ECCV 2022.
· [Mar, 2022] Three papers are accepted by CVPR 2022.
Publications
Prompt Ensemble Self-training for Open-Vocabulary Domain Adaptation
Jiaxing Huang^, Jingyi Zhang^, Han Qiu, Sheng Jin, Shijian Lu
arXiv preprint, 2023
[Paper]
Vision-Language Models for Vision Tasks: A Survey
Jingyi Zhang^, Jiaxing Huang^, Sheng Jin and Shijian Lu
TPAMI, 2024
[Paper] [Project]
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
Computer Vision and Pattern Recognition (CVPR), 2023
[Paper] [Project&Code]
DA-DETR: Domain Adaptive Detection Transformer With Information Fusion
Jingyi Zhang^, Jiaxing Huang^, Zhipeng Luo, Gongjie Zhang, Xiaoqin Zhang, Shijian Lu
Computer Vision and Pattern Recognition (CVPR), 2023
[Paper] [Project&Code (Under preparation)]
UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration
Jingyi Zhang^, Jiaxing Huang^, Xiaoqin Zhang, Shijian Lu
Computer Vision and Pattern Recognition (CVPR), 2023
[Paper]
Unsupervised Representation Learning for Point Clouds with Deep Neural Networks: A Survey
Aoran Xiao^, Jiaxing Huang^, Dayan Guan, Xiaoqin Zhang, Shijian Lu
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023
[Paper] [Project]
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&Code]
Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu, Ling Shao
Computer Vision and Pattern Recognition (CVPR), 2022
[Paper] [Project&Code]
Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation
Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu
Computer Vision and Pattern Recognition (CVPR), 2022
[Paper] [Project&Code]
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&Code]
GenCo: Generative Co-training for Generative Adversarial Networks with Limited Data
Kaiwen Cui^, Jiaxing Huang^, Zhipeng Luo, Gongjie Zhang, Fangneng Zhan,Shijian Lu
AAAI Conference on Artificial Intelligence (AAAI), 2022
[Paper] [Project&Code]
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&Code]
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&Code]
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&Code]
Cross-View Regularization for Domain Adaptive Panoptic Segmentation
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu
Computer Vision and Pattern Recognition (CVPR), 2021
[Paper] [Project&Code]
FSDR: Frequency Space Domain Randomization for Domain Generalization
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu
Computer Vision and Pattern Recognition (CVPR), 2021
[Paper]
Scale Variance Minimization for Unsupervised Domain Adaptation in Image Segmentation
Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu
Pattern Recognition (PR), 2021
[Paper] [Project&Code]
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&Code]
Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation
Jiaxing Huang, Shijian Lu, Dayan Guan, Xiaobing Zhang
European Conference on Computer Vision (ECCV), 2020
[Paper]
Projects & Datasets
SynLiDAR: A Synthetic LiDAR Point Cloud Dataset for Transfer Learning
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&Code] [Dataset]
SemanticSTF: An Adverse-Weather Point Cloud Dataset
SemanticSTF is an adverse-weather point cloud dataset that provides dense point-level annotations and allows to study 3DSS under various adverse weather conditions.
[Paper] [Project&Code] [Dataset]
Academic Services
Area Chair,
WACV’25, BMVC’24.
Program Committee Member:
∙ AAAI
Conference & Journal Reviewer:
∙ NeurIPS, CVPR, ICCV, ECCV, BMVC, ACCV, WACV, etc.
∙ T-PAMI, T-IP, T-NNLS, T-CSVT, Pattern Recognition, T-MM, ISPRS Journal, Neurocomputing, etc.