Weiming Zhuang
Profile
Weiming is a research scientist in Privacy-Preserving Machine Learning (PPML) at Sony AI. His research interests and expertise span federated learning, AI privacy and security, computer vision, and machine learning systems. Before joining Sony AI, Weiming was a Ph.D. researcher under SenseTime-NTU Talent Programme and received his Ph.D. from Nanyang Technological University. He spent two years in software engineering building large-scale distributed systems and completed his Bachelor's from the National University of Singapore, School of Computing. Weiming has published papers in top-tier conferences and journals, including ICLR, ICCV, etc., and his papers have been selected as oral presentations at top conferences.
Publications
Argus: A Compact and Versatile Foundation Model for Vision
CVPR, 2025 | Weiming Zhuang, Chen Chen, Zhizhong Li, Sina Sajadmanesh, Jingtao Li, Jiabo Huang, Vikash Sehwag, Vivek Sharma, Hirotaka Shinozaki, Felan Carlo Garcia, Yihao Zhan, Naohiro Adachi, Ryoji Eki, Michael Spranger, Peter Stone, Lingjuan Lyu
While existing vision and multi-modal foundation models can handle multiple computer vision tasks, they often suffer from significant limitations, including huge demand for data and computational resources during training and inconsistent performance across vision tasks at d...
A Simple Background Augmentation Method for Object Detection with Diffusion Model
ECCV, 2024 | Yuhang Li, Xin Dong, Chen Chen, Weiming Zhuang, Lingjuan Lyu
In computer vision, it is well-known that a lack of data diversity will impair model performance. In this study, we address the challenges of enhancing the dataset diversity problem in order to benefit various downstream tasks such as object detection and instance segmentati...
COALA: A Practical and Vision-Centric Federated Learning Platform
ICML, 2024 | Weiming Zhuang, Jian Xu, Chen Chen, Jingtao Li, Lingjuan Lyu
We present COALA, a vision-centric Federated Learning (FL) platform, and a suite of benchmarks for practical FL scenarios, which we categorize as task, data, and model levels. At the task level, COALA extends support from simple classification to 15 computer vision tasks, in...
FedMef: Towards Memory-efficient Federated Dynamic Pruning
CVPR, 2024 | Hong Huang, Weiming Zhuang, Chen Chen, Lingjuan Lyu
Federated learning (FL) promotes decentralized training while prioritizing data confidentiality. However, its application on resource-constrained devices is challenging due to the high demand for computation and memory resources for training deep learning models. Neural netw...
Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators
AAAI, 2024 | Sikai Bai*, Shuaicheng Li*, Weiming Zhuang, Jie Zhang*, Kunlin Yang*, Jun Hou*, Shuai Yi*, Shuai Zhang*, Junyu Gao*
Federated learning has become a popular method to learn from decentralized heterogeneous data. Federated semi-supervised learning (FSSL) emerges to train models from a small fraction of labeled data due to label scarcity on decentralized clients. Existing FSSL methods assume...
FedWon: Triumphing Multi-domain Federated Learning Without Normalization
ICLR, 2024 | Weiming Zhuang, Lingjuan Lyu
Federated learning (FL) enhances data privacy with collaborative in-situ training on decentralized clients. Nevertheless, FL encounters challenges due to non-independent and identically distributed (non-i.i.d) data, leading to potential performance degradation and hindered c...
Is Heterogeneity Notorious? Taming Heterogeneity to Handle Test-Time Shift in Federated Learning
NEURIPS, 2023 | Yue Tan, Chen Chen, Weiming Zhuang, Xin Dong, Lingjuan Lyu, Guodong Long*
Federated learning (FL) is an effective machine learning paradigm where multiple clients can train models based on heterogeneous data in a decentralized manner without accessing their private data. However, existing FL systems undergo performance deterioration due to feature...
MAS: Towards Resource-Efficient Federated Multiple-Task Learning
ICCV, 2023 | Weiming Zhuang, Yonggang Wen*, Shuai Zhang*, Lingjuan Lyu
Federated learning (FL) is an emerging distributed machine learning method that empowers in-situ model training on decentralized edge devices. However, multiple simultaneous FL tasks could overload resource-constrained devices. In this work, we propose the first FL system to...
TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation
ICCV, 2023 | Jie Zhang*, Chen Chen, Weiming Zhuang, Lingjuan Lyu
This paper focuses on an under-explored yet important problem: Federated Class-Continual Learning (FCCL), where new classes are dynamically added in federated learning. Existing FCCL works suffer from various limitations, such as requiring additional datasets or storing the ...
Blog Posts
Sony AI Reveals New Research Contributions at NeurIPS 2023
December 13, 2023 | Peter Stone, Alice Xiang, Jerone Andrews, Events, Kazuki Shimada, Apostolos Modas, Tarek Besold, William Thong, Dora Zhao*, Lingjuan Lyu, Orestis Papakyriakopoulos*, Xin Dong, Nidham Gazagnadou, Weiming Zhuang, Vivek Sharma, Yuki Mitsufuji, Chen Chen
Sony Group Corporation and Sony AI have been active participants in the annual NeurIPS Conference for years, contributing pivotal research that has ...
Advancements in Federating Learning Highlighted in Papers Presented at ICCV 2023
October 6, 2023 | Lingjuan Lyu, PPML, Weiming Zhuang
As the field of machine learning continues to evolve, Sony AI researchers are constantly exploring innovative solutions to address the pressing ...
Recent Breakthroughs Tackle Challenges in Federated Learning
June 8, 2023 | Machine Learning, Lingjuan Lyu, Weiming Zhuang
Privacy-Preserving Machine Learning Blog Series At Sony AI, the Privacy-Preserving Machine Learning (PPML) team focuses on fundamental and applied ...