I am currently a Postdoctoral Research Fellow at the Australian Institute for Machine Learning (AIML) at The University of Adelaide, working under the supervision of Prof. Lingqiao Liu. Prior to that, I earned my Ph.D. degree in Computer Science from The University of Adelaide in 2022. Before coming to Adelaide, I completed my M.S. degree in Computer Science in 2018 at the PAttern Learning and Mining (PALM) Lab, Southeast University, China in 2018, where I was supervised by Prof. Hui Xue. My B.S. degree in Computer Science was awarded by China University of Mining and Technology in 2015.

I am interested in general ML and CV research problems, such as Multimodal Large Language Models (MLLMs), Semi-supervised Learning (SSL) for Multiple Domains (e.g., 2D image/3D point-cloud segmentation and text classification), Pretrained Foundation Models for Various Applications (e.g., few-shot segmentation and class-agnostic counting).

🔥 News

2024.12: 🎉 The code and OCG benchmark for our TAG work (AAAI 2025) are now open-sourced. Feel free to explore and give it a try!
2024.12: 🎉 Our paper is accepted to AAAI 2025. Topic: Vision-based GUI Grounding
2024.10: 🎉 Our paper is accepted to WACV 2025. Topic: Class-agnostic Counting
2024.02: 🎉 Our paper is accepted to CVPR 2024. Topic: Few-shot Semantic Segmentation
2023.07: Three papers are accepted to ICCV 2023. Topic: SSL with Pretrained Models; KD for DETR Models; Point Cloud Segmentation
2023.02: Our paper is accepted to CVPR 2023. Topic: Domain Generalization for 3D Detection in BEV
2022.10: Our paper is accepted to BMVC 2022. Topic: Open-Set Panoptic Segmentation
2022.09: Our paper is accepted to NeurIPS 2022. Topic: Semi-supervised Semantic Segmentation
2022.07: Our paper is accepted to ECCV 2022. Topic: FGVR with Few Data
2022.04: Our paper is accepted to NAACL 2022. Topic: Semi-supervised Text Classification

📝 Publications

Attention-driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models without Fine-Tuning

Hai-Ming Xu, Qi Chen, Lei Wang, Lingqiao Liu

The 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025)

[Code]

A Simple-but-effective Baseline for Training-free Class-Agnostic Counting

Yuhao Lin⁺, Hai-Ming Xu⁺, Lingqiao Liu, Javen Qinfeng Shi

(⁺: Equal contribution)

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)

MuseBarControl: Enhancing Fine-Grained Control in Symbolic Music Generation through Pre-Training and Counterfactual Loss

Yangyang Shu, Hai-Ming Xu, Ziqin Zhou, Anton van den Hengel, Lingqiao Liu

[Project]

Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors

Ziqin Zhou, Hai-Ming Xu, Yangyang Shu, Lingqiao Liu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024)

[Code]

Revisiting Open-Set Panoptic Segmentation

Yufei Yin, Hao Chen, Wengang Zhou, Jiajun Deng, Hai-Ming Xu, Houqiang Li

The 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024)

Progressive Feature Adjustment for Semi-supervised Learning from Pretrained Models

Hai-Ming Xu, Lingqiao Liu, Hao Chen, Ehsan Abbasnejad, Rafael Felix

IEEE/CVF International Conference on Computer Vision Workshop (ICCVW 2023)

[Code]

DETRDistill: A Universal Knowledge Distillation Framework for DETR-families

Jiahao Chang⁺, Shuo Wang⁺, Hai-Ming Xu⁺, Zehui Chen, Chenhongyi Yang, Feng Zhao

(⁺: Equal contribution)

IEEE/CVF International Conference on Computer Vision (ICCV 2023)

[Code]

ProtoTransfer: Cross-Modal Prototype Transfer for Point Cloud Segmentation

Pin Tang, Hai-Ming Xu, Chao Ma

IEEE/CVF International Conference on Computer Vision (ICCV 2023)

Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View

Shuo Wang, Xinhai Zhao, Hai-Ming Xu, Zehui Chen, Dameng Yu, Jiahao Chang, Zhen Yang, Feng Zhao

IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR 2023)

Dual Decision Improves Open-Set Panoptic Segmentation

Hai-Ming Xu, Hao Chen, Lingqiao Liu, Yufei Yin

The 33rd British Machine Vision Conference (BMVC 2022)

[Code]

Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization

Hai-Ming Xu, Lingqiao Liu, Qiuchen Bian, Zhen Yang

Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)

[Code]

Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism

Yangyang Shu, Baosheng Yu, Hai-Ming Xu, Lingqiao Liu

Proceedings of the European Conference on Computer Vision (ECCV), 2022.

Progressive Class Semantic Matching for Semi-supervised Text Classification

Hai-Ming Xu, Lingqiao Liu, Ehsan Abbasnejad

Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022), selected as Oral presentation.

IJCAI 2017 Multiple indefinite kernel learning for feature selection, Hui Xue, Yu Song, Hai-Ming Xu
AAAI 2017 Solving indefinite kernel support vector machine with difference of convex functions programming, Hai-Ming Xu, Hui Xue, Xiao-Hong Chen, Yun-Yun Wang. | [Code]

🎖 Awards

2018-2022: University of Adelaide Research Scholarships.
2018: Outstanding Graduates, Ministry of Education of P.R. China
2016: National Scholarship, Ministry of Education of P.R. China (Graduate)
2013: National Scholarship, Ministry of Education of P.R. China (Undergraduate)
2013: Honorable Mention of 2013 International Mathematical Contest in Modeling (MCM)
2012: Bronze Medal for Youth Group of The Sixth Olympic International Youth Calligraphy and Painting Contest (Calligraphy)

💼 Employment

2023.06 - (now): Postdoc at AIML, The University of Adelaide, Australia. Working with Prof. Lingqiao Liu.
2021.03 - 2023.03, Research intern at Noah’s Ark Lab, Huawei, China. Working with Dr. Hao Chen

📜 Services

Journal Reviewer: IEEE Transactions on Image Processing (TIP), IEEE Transactions on Neural Networks and Learning Systems(TNNLS), Neural Networks, Pattern Recognition, Neurocomputing
Conference Reviewer: ICLR, ICCV, ECCV, BMVC, ACCV, WACV, ACL, NAACL, EMNLP