Research
Reliable Machine Learning, Uncertainty Quantification, Computer Vision
Interests
My research interest is machine learning, including trustworthy and robust machine learning, uncertainty of foundation models and interpretable machine learning. The main goal of my research is to quantify and mitigate the risk of machine learning systems so that the deployment of machine learning benefits each individual in our society.
Publications
Publications of specific relevance to the Centre for Multimodal AI
2024
A Secure Image Watermarking Framework with Statistical Guarantees via Adversarial Attacks on Secret Key NetworksChen F, Lin W,
Liu Z and Chan AB
Lecture Notes in Computer Science. vol. 15098, 428-445.
10-11-2024 
The Pitfalls and Promise of Conformal Inference Under Adversarial AttacksLiu Z, Cui Y, Yan Y, Xu Y, Ji X, Liu X and Chan AB
Proceedings of Machine Learning Research. vol. 235, 30908-30928.
01-01-20242023
Variational Nested DropoutCui Y, Mao Y,
Liu Z, Li Q, Chan AB, Liu X, Kuo T-W and Xue CJ
Ieee Transactions on Pattern Analysis and Machine Intelligence,
Institute of Electrical and Electronics Engineers (Ieee) vol. 45 (8), 10519-10534.
30-06-2023 DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking TasksWu Q, Yang T,
Liu Z, Wu B, Shan Y and Chan AB
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). vol. 00, 14561-14571.
24-06-2023 Clustering Hidden Markov Models With Variational Bayesian Hierarchical EMLan H,
Liu Z, Hsiao JH, Yu D and Chan AB
Ieee Transactions on Neural Networks and Learning Systems,
Institute of Electrical and Electronics Engineers (Ieee) vol. 34 (3), 1537-1551.
28-02-2023 Retrieval-Augmented Multiple Instance LearningCui Y,
Liu Z, Chen Y, Lu Y, Yu X, Liu X, Kuo TW, Rodrigues MRD, Xue CJ and Chan AB
Advances in Neural Information Processing Systems. vol. 36
01-01-2023 BAYES-MIL: A NEW PROBABILISTIC PERSPECTIVE ON ATTENTION-BASED MULTIPLE INSTANCE LEARNING FOR WHOLE SLIDE IMAGESCui Y,
Liu Z, Liu X, Wang C, Kuo TW, Xue CJ and Chan AB
11th International Conference on Learning Representations, ICLR 2023.
01-01-2023 2022
PRIMAL-GMM: PaRametrIc MAnifold Learning of Gaussian Mixture ModelsLiu Z, Yu L, Hsiao JH and Chan AB
Ieee Transactions on Pattern Analysis and Machine Intelligence,
Institute of Electrical and Electronics Engineers (Ieee) vol. 44 (6), 3197-3211.
05-05-2022 Improved Fine-Tuning by Better Leveraging Pre-Training DataLiu Z, Xu Y, Qian Q, Li H, Ji X, Chan AB and Jin R
Advances in Neural Information Processing Systems. vol. 35
01-01-2022 Boosting Adversarial Robustness From The Perspective of Effective Margin RegularizationLiu Z and Chan AB
BMVC 2022 - 33rd British Machine Vision Conference Proceedings.
01-01-2022 2021
Bayesian Nested Neural Networks for Uncertainty Calibration and Adaptive CompressionCui Y,
Liu Z, Li Q, Chan AB and Xue CJ
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). vol. 00, 2392-2401.
25-06-2021 A Generalized Loss Function for Crowd Counting and LocalizationWan J,
Liu Z and Chan AB
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). vol. 00, 1974-1983.
25-06-2021 2020
Fully nested neural network for adaptive compression and quantizationCui Y,
Liu Z, Yao W, Li Q, Chan AB, Kuo TW and Xue CJ
IJCAI International Joint Conference on Artificial Intelligence. vol. 2021-January, 2080-2087.
01-01-2020 2019
Parametric Manifold Learning of Gaussian Mixture ModelsLiu Z, Yu L, Hsiao JH and Chan AB
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence., 3073-3079.
01-08-2019
