Zhiqiang Shen
Assistant Professor of Machine Learning
Research interests
Professor Shen’s research interests focus on the broad areas of efficient deep learning, machine learning, and computer vision. Specifically, he is interested in deep learning methods for image recognition and object detection, efficient deep architectures and parameter-efficient fine-tuning strategies, etc. Email
Prior to joining MBZUAI, Professor Shen was an assistant research professor in the Department of Computer Science and Engineering at Hong Kong University of Science and Technology (HKUST), China. He was a postdoctoral researcher at CyLab, Carnegie Mellon University (CMU). Prior to CMU, he was a joint-training Ph.D. student at University of Illinois Urbana-Champaign (UIUC) and Fudan University. He was also an IAS Junior Fellow from the Jockey Club Institute for Advanced Study at HKUST.
Professor Shen’s research interests focus on the broad areas of efficient deep learning, machine learning, and computer vision. Specifically, he is interested in deep learning methods for image recognition and object detection, efficient deep architectures and parameter-efficient fine-tuning strategies, etc. Most recently, he is focusing on: (1) low-bit neural networks; (2) knowledge distillation for models and data; (3) designing and training highly efficient network architectures for CNNs and transformers; (4) un(self-)supervised / weakly-supervised learning; (5) image understanding including object detection, recognition, and captioning; and (6) few-shot learning.
- Ph.D. in computer science from Fudan University, China
- Joint-training Ph.D. student in engineering from University of Illinois Urbana-Champaign, USA
- CVPR 2019 doctoral consortium award
- AAAI 2019 student scholarship award
- iMaterialist Challenge on Product Recognition (Fine-grained image classification of products at FGVC6, CVPR'19 workshop): Ranked fourth globally (team leader)
- MSR-VTT Challenge (video captioning) 2016: Ranked fourth in human evaluation and ranked fifth in the automatic evaluation metrics (team leader)
- Top 10% in Kaggle Competition of Right Whale Recognition, 2016
Shen has been a conference and journal reviewer for top tier computer science conferences and journals. In 2023, he was a meta-reviewer (SPC) at the Association for the Advancement of Artificial Intelligence (AAAI) Conference on Artificial Intelligence 2023.
- Zhiqiang Shen, Eric Xing. “A Fast Knowledge Distillation Framework for Visual Recognition”. ECCV 2022.
- Zhiqiang Shen, Zechun Liu, Eric Xing. “Sliced Recursive Transformer”. ECCV 2022.
- Zhiqiang Shen, Zechun Liu, Dejia Xu, Zitian Chen, Kwang-Ting Cheng, Marios Savvides. “Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study”. ICLR 2021.
- Zechun Liu*, Zhiqiang Shen*, Shichao Li, Koen Helwegen, Dong Huang, Kwang-Ting Cheng. “How Do Adam and Training Strategies Help BNNs Optimization?”. ICML 2021.
- Zhiqiang Shen, Zechun Liu, Zhuang Liu, Marios Savvides, Trevor Darrell, Eric Xing. “Un-Mix: Rethinking Image Mixture for Unsupervised Visual Representation Learning”. AAAI 2022.
- Zhiqiang Shen, Zechun Liu, Jie Qin, Lei Huang, Kwang-Ting Cheng, Marios Savvides. “S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration”. CVPR 2021.
Related
Web2Code: A new dataset to enhance multimodal LLM performance presented at NeurIPS
A team from MBZUAI used instruction tuning to help multimodal LLMs generate HTML code and answer questions…
Read more
How computer vision model architecture and training affect performance
Zhiqiang Shen, assistant professor of machine learning at MBZUAI, discusses one of 25 studies being presented by…
Read moreContact faculty affairs
Interested in working with
our renowned faculty?
Fill out the below form and we will get back to you.